Dataset Viewer
images
images listlengths 1
1
| data_source
stringclasses 2
values | reward_model
dict | extra_info
dict | prompt
listlengths 2
2
| ability
stringclasses 3
values | env_name
stringclasses 1
value |
|---|---|---|---|---|---|---|
sealvqa_vaw
|
{
"ground_truth": "Yes, the color of the flowers is yellow."
}
|
{
"answer": "Yes, the color of the flowers is yellow.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2364899.jpg",
"index": "sealvqa_vaw_0",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nIs the color of the flowers yellow?"
},
{
"from": "gpt",
"value": "Yes, the color of the flowers is yellow."
}
],
"question": "Is the color of the flowers yellow?",
"question_id": "sealvqa_vaw_0",
"search": 1,
"target_instances": [
{
"bbox": [
141.66666666666666,
335,
62.666666666666686,
33.5
],
"instance_id": "2364899006",
"name": "flowers"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nIs the color of the flowers yellow?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The color of the pants is white."
}
|
{
"answer": "The color of the pants is white.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2409126.jpg",
"index": "sealvqa_vaw_1",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the color of the pants?"
},
{
"from": "gpt",
"value": "The color of the pants is white."
}
],
"question": "What is the color of the pants?",
"question_id": "sealvqa_vaw_1",
"search": 1,
"target_instances": [
{
"bbox": [
421.6666666666667,
115,
17.666666666666686,
32.66666666666666
],
"instance_id": "2409126013",
"name": "pants"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the color of the pants?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The material of the wheels is wooden."
}
|
{
"answer": "The material of the wheels is wooden.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2383494.jpg",
"index": "sealvqa_vaw_2",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the material of the wheels?"
},
{
"from": "gpt",
"value": "The material of the wheels is wooden."
}
],
"question": "What is the material of the wheels?",
"question_id": "sealvqa_vaw_2",
"search": 1,
"target_instances": [
{
"bbox": [
332.5,
115,
20.166666666666686,
93.5
],
"instance_id": "2383494000",
"name": "wheels"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the material of the wheels?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "No, the pose of the zebras is not running."
}
|
{
"answer": "No, the pose of the zebras is not running.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/150488.jpg",
"index": "sealvqa_vaw_3",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nIs the pose of the zebras running?"
},
{
"from": "gpt",
"value": "No, the pose of the zebras is not running."
}
],
"question": "Is the pose of the zebras running?",
"question_id": "sealvqa_vaw_3",
"search": 1,
"target_instances": [
{
"bbox": [
276.48,
320.85333333333335,
99.98666666666662,
77.79999999999995
],
"instance_id": "150488004",
"name": "zebras"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nIs the pose of the zebras running?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_general
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The color of the feathers is gray."
}
|
{
"answer": "The color of the feathers is gray.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2391278.jpg",
"index": "sealvqa_vaw_4",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the color of the feathers?"
},
{
"from": "gpt",
"value": "The color of the feathers is gray."
}
],
"question": "What is the color of the feathers?",
"question_id": "sealvqa_vaw_4",
"search": 1,
"target_instances": [
{
"bbox": [
180.83333333333334,
264.1666666666667,
64.33333333333331,
22.66666666666663
],
"instance_id": "2391278003",
"name": "feathers"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the color of the feathers?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The color of the basket is red."
}
|
{
"answer": "The color of the basket is red.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2375917.jpg",
"index": "sealvqa_vaw_5",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the color of the basket?"
},
{
"from": "gpt",
"value": "The color of the basket is red."
}
],
"question": "What is the color of the basket?",
"question_id": "sealvqa_vaw_5",
"search": 1,
"target_instances": [
{
"bbox": [
417.5,
97.5,
73.5,
67.66666666666666
],
"instance_id": "2375917004",
"name": "basket"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the color of the basket?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The color of the kite is red."
}
|
{
"answer": "The color of the kite is red.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2415879.jpg",
"index": "sealvqa_vaw_6",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the color of the kite?"
},
{
"from": "gpt",
"value": "The color of the kite is red."
}
],
"question": "What is the color of the kite?",
"question_id": "sealvqa_vaw_6",
"search": 1,
"target_instances": [
{
"bbox": [
268.125,
215,
74.125,
107.875
],
"instance_id": "2415879003",
"name": "kite"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the color of the kite?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The color of the cabinets is white."
}
|
{
"answer": "The color of the cabinets is white.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2320937.jpg",
"index": "sealvqa_vaw_7",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the color of the cabinets?"
},
{
"from": "gpt",
"value": "The color of the cabinets is white."
}
],
"question": "What is the color of the cabinets?",
"question_id": "sealvqa_vaw_7",
"search": 1,
"target_instances": [
{
"bbox": [
144.16666666666666,
217.5,
52.666666666666686,
58.5
],
"instance_id": "2320937006",
"name": "cabinets"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the color of the cabinets?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "No, the opaqeness of the cup is not transparent."
}
|
{
"answer": "No, the opaqeness of the cup is not transparent.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2411637.jpg",
"index": "sealvqa_vaw_8",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nIs the opaqeness of the cup transparent?"
},
{
"from": "gpt",
"value": "No, the opaqeness of the cup is not transparent."
}
],
"question": "Is the opaqeness of the cup transparent?",
"question_id": "sealvqa_vaw_8",
"search": 1,
"target_instances": [
{
"bbox": [
179.16666666666666,
100,
22.666666666666686,
30.166666666666686
],
"instance_id": "2411637001",
"name": "cup"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nIs the opaqeness of the cup transparent?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_general
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The color of the shirt is red."
}
|
{
"answer": "The color of the shirt is red.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2370229.jpg",
"index": "sealvqa_vaw_9",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the color of the shirt?"
},
{
"from": "gpt",
"value": "The color of the shirt is red."
}
],
"question": "What is the color of the shirt?",
"question_id": "sealvqa_vaw_9",
"search": 1,
"target_instances": [
{
"bbox": [
160,
137,
49,
42
],
"instance_id": "2370229005",
"name": "shirt"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the color of the shirt?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "No, the color of the design is not black."
}
|
{
"answer": "No, the color of the design is not black.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2381719.jpg",
"index": "sealvqa_vaw_10",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nIs the color of the design black?"
},
{
"from": "gpt",
"value": "No, the color of the design is not black."
}
],
"question": "Is the color of the design black?",
"question_id": "sealvqa_vaw_10",
"search": 1,
"target_instances": [
{
"bbox": [
341.6666666666667,
174.16666666666666,
76,
46.00000000000003
],
"instance_id": "2381719002",
"name": "design"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nIs the color of the design black?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "No, the color of the stars is not orange."
}
|
{
"answer": "No, the color of the stars is not orange.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2389715.jpg",
"index": "sealvqa_vaw_11",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nIs the color of the stars orange?"
},
{
"from": "gpt",
"value": "No, the color of the stars is not orange."
}
],
"question": "Is the color of the stars orange?",
"question_id": "sealvqa_vaw_11",
"search": 1,
"target_instances": [
{
"bbox": [
44.25,
186.375,
53.5,
20.125
],
"instance_id": "2389715002",
"name": "stars"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nIs the color of the stars orange?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "Yes, the color of the blouse is green."
}
|
{
"answer": "Yes, the color of the blouse is green.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2372007.jpg",
"index": "sealvqa_vaw_12",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nIs the color of the blouse green?"
},
{
"from": "gpt",
"value": "Yes, the color of the blouse is green."
}
],
"question": "Is the color of the blouse green?",
"question_id": "sealvqa_vaw_12",
"search": 1,
"target_instances": [
{
"bbox": [
162.5,
299.1666666666667,
36.83333333333334,
81.83333333333331
],
"instance_id": "2372007003",
"name": "blouse"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nIs the color of the blouse green?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The color of the building is blue."
}
|
{
"answer": "The color of the building is blue.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2383501.jpg",
"index": "sealvqa_vaw_13",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the color of the building?"
},
{
"from": "gpt",
"value": "The color of the building is blue."
}
],
"question": "What is the color of the building?",
"question_id": "sealvqa_vaw_13",
"search": 1,
"target_instances": [
{
"bbox": [
403.3333333333333,
30.833333333333336,
76,
122.66666666666666
],
"instance_id": "2383501004",
"name": "building"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the color of the building?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "Yes, the color of the grass is green."
}
|
{
"answer": "Yes, the color of the grass is green.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2324713.jpg",
"index": "sealvqa_vaw_14",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nIs the color of the grass green?"
},
{
"from": "gpt",
"value": "Yes, the color of the grass is green."
}
],
"question": "Is the color of the grass green?",
"question_id": "sealvqa_vaw_14",
"search": 1,
"target_instances": [
{
"bbox": [
400.8333333333333,
241.66666666666666,
96.00000000000006,
57.66666666666666
],
"instance_id": "2324713004",
"name": "grass"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nIs the color of the grass green?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The face expression of the woman is smiling."
}
|
{
"answer": "The face expression of the woman is smiling.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2408270.jpg",
"index": "sealvqa_vaw_15",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the face expression of the woman?"
},
{
"from": "gpt",
"value": "The face expression of the woman is smiling."
}
],
"question": "What is the face expression of the woman?",
"question_id": "sealvqa_vaw_15",
"search": 1,
"target_instances": [
{
"bbox": [
242,
168,
51,
86
],
"instance_id": "2408270002",
"name": "woman"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the face expression of the woman?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The color of the line is yellow."
}
|
{
"answer": "The color of the line is yellow.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/4508.jpg",
"index": "sealvqa_vaw_16",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the color of the line?"
},
{
"from": "gpt",
"value": "The color of the line is yellow."
}
],
"question": "What is the color of the line?",
"question_id": "sealvqa_vaw_16",
"search": 1,
"target_instances": [
{
"bbox": [
249,
213.5,
50,
73.5
],
"instance_id": "4508001",
"name": "line"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the color of the line?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The color of the word is yellow."
}
|
{
"answer": "The color of the word is yellow.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2406739.jpg",
"index": "sealvqa_vaw_17",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the color of the word?"
},
{
"from": "gpt",
"value": "The color of the word is yellow."
}
],
"question": "What is the color of the word?",
"question_id": "sealvqa_vaw_17",
"search": 1,
"target_instances": [
{
"bbox": [
127.5,
281.06666666666666,
39.53333333333333,
45.19999999999999
],
"instance_id": "2406739001",
"name": "word"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the color of the word?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The color of the uniform is blue."
}
|
{
"answer": "The color of the uniform is blue.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2319880.jpg",
"index": "sealvqa_vaw_18",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the color of the uniform?"
},
{
"from": "gpt",
"value": "The color of the uniform is blue."
}
],
"question": "What is the color of the uniform?",
"question_id": "sealvqa_vaw_18",
"search": 1,
"target_instances": [
{
"bbox": [
308,
104,
23,
44
],
"instance_id": "2319880004",
"name": "uniform"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the color of the uniform?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The color of the shoes is red."
}
|
{
"answer": "The color of the shoes is red.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2406860.jpg",
"index": "sealvqa_vaw_19",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the color of the shoes?"
},
{
"from": "gpt",
"value": "The color of the shoes is red."
}
],
"question": "What is the color of the shoes?",
"question_id": "sealvqa_vaw_19",
"search": 1,
"target_instances": [
{
"bbox": [
28.333333333333332,
200.83333333333334,
171,
41
],
"instance_id": "2406860003",
"name": "shoes"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the color of the shoes?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The color of the lighthouse is red."
}
|
{
"answer": "The color of the lighthouse is red.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2395045.jpg",
"index": "sealvqa_vaw_20",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the color of the lighthouse?"
},
{
"from": "gpt",
"value": "The color of the lighthouse is red."
}
],
"question": "What is the color of the lighthouse?",
"question_id": "sealvqa_vaw_20",
"search": 1,
"target_instances": [
{
"bbox": [
233.33333333333334,
47.5,
38.49999999999997,
76
],
"instance_id": "2395045002",
"name": "lighthouse"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the color of the lighthouse?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The material of the spoon is stainless steel."
}
|
{
"answer": "The material of the spoon is stainless steel.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2372786.jpg",
"index": "sealvqa_vaw_21",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the material of the spoon?"
},
{
"from": "gpt",
"value": "The material of the spoon is stainless steel."
}
],
"question": "What is the material of the spoon?",
"question_id": "sealvqa_vaw_21",
"search": 1,
"target_instances": [
{
"bbox": [
102,
352,
97,
67
],
"instance_id": "2372786015",
"name": "spoon"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the material of the spoon?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "Yes, the color of the sign is blue."
}
|
{
"answer": "Yes, the color of the sign is blue.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2393730.jpg",
"index": "sealvqa_vaw_22",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nIs the color of the sign blue?"
},
{
"from": "gpt",
"value": "Yes, the color of the sign is blue."
}
],
"question": "Is the color of the sign blue?",
"question_id": "sealvqa_vaw_22",
"search": 1,
"target_instances": [
{
"bbox": [
4,
106,
47,
68
],
"instance_id": "2393730003",
"name": "sign"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nIs the color of the sign blue?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The material of the table is wooden."
}
|
{
"answer": "The material of the table is wooden.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2319270.jpg",
"index": "sealvqa_vaw_23",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the material of the table?"
},
{
"from": "gpt",
"value": "The material of the table is wooden."
}
],
"question": "What is the material of the table?",
"question_id": "sealvqa_vaw_23",
"search": 1,
"target_instances": [
{
"bbox": [
1.67,
371.2966666666666,
75.59333333333333,
73.36666666666673
],
"instance_id": "2319270010",
"name": "table"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the material of the table?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "Yes, the color of the fur is black."
}
|
{
"answer": "Yes, the color of the fur is black.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2404579.jpg",
"index": "sealvqa_vaw_24",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nIs the color of the fur black?"
},
{
"from": "gpt",
"value": "Yes, the color of the fur is black."
}
],
"question": "Is the color of the fur black?",
"question_id": "sealvqa_vaw_24",
"search": 1,
"target_instances": [
{
"bbox": [
82.5,
77.5,
72.66666666666669,
80.16666666666669
],
"instance_id": "2404579000",
"name": "fur"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nIs the color of the fur black?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The color of the plane is white."
}
|
{
"answer": "The color of the plane is white.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2398589.jpg",
"index": "sealvqa_vaw_25",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the color of the plane?"
},
{
"from": "gpt",
"value": "The color of the plane is white."
}
],
"question": "What is the color of the plane?",
"question_id": "sealvqa_vaw_25",
"search": 1,
"target_instances": [
{
"bbox": [
223.33333333333331,
162.5,
51.83333333333337,
26.833333333333314
],
"instance_id": "2398589000",
"name": "plane"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the color of the plane?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "No, the pose of the propeller is not turning."
}
|
{
"answer": "No, the pose of the propeller is not turning.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2375066.jpg",
"index": "sealvqa_vaw_26",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nIs the pose of the propeller turning?"
},
{
"from": "gpt",
"value": "No, the pose of the propeller is not turning."
}
],
"question": "Is the pose of the propeller turning?",
"question_id": "sealvqa_vaw_26",
"search": 1,
"target_instances": [
{
"bbox": [
394.1666666666667,
126.66666666666667,
55.16666666666663,
51.83333333333333
],
"instance_id": "2375066006",
"name": "propeller"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nIs the pose of the propeller turning?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_general
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "No, the color of the painting is not orange."
}
|
{
"answer": "No, the color of the painting is not orange.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2399355.jpg",
"index": "sealvqa_vaw_27",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nIs the color of the painting orange?"
},
{
"from": "gpt",
"value": "No, the color of the painting is not orange."
}
],
"question": "Is the color of the painting orange?",
"question_id": "sealvqa_vaw_27",
"search": 1,
"target_instances": [
{
"bbox": [
113,
16,
56,
59
],
"instance_id": "2399355000",
"name": "painting"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nIs the color of the painting orange?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "No, the color of the frame is not cream colored."
}
|
{
"answer": "No, the color of the frame is not cream colored.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2318829.jpg",
"index": "sealvqa_vaw_28",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nIs the color of the frame cream colored?"
},
{
"from": "gpt",
"value": "No, the color of the frame is not cream colored."
}
],
"question": "Is the color of the frame cream colored?",
"question_id": "sealvqa_vaw_28",
"search": 1,
"target_instances": [
{
"bbox": [
39.16666666666667,
143.33333333333334,
66.83333333333333,
89.33333333333331
],
"instance_id": "2318829004",
"name": "frame"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nIs the color of the frame cream colored?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "Yes, the color of the window is white."
}
|
{
"answer": "Yes, the color of the window is white.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/3128.jpg",
"index": "sealvqa_vaw_29",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nIs the color of the window white?"
},
{
"from": "gpt",
"value": "Yes, the color of the window is white."
}
],
"question": "Is the color of the window white?",
"question_id": "sealvqa_vaw_29",
"search": 1,
"target_instances": [
{
"bbox": [
296,
419,
47,
141
],
"instance_id": "3128001",
"name": "window"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nIs the color of the window white?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The material of the bat is metal."
}
|
{
"answer": "The material of the bat is metal.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2369622.jpg",
"index": "sealvqa_vaw_30",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the material of the bat?"
},
{
"from": "gpt",
"value": "The material of the bat is metal."
}
],
"question": "What is the material of the bat?",
"question_id": "sealvqa_vaw_30",
"search": 1,
"target_instances": [
{
"bbox": [
373.33333333333337,
155.83333333333331,
33.49999999999994,
98.50000000000003
],
"instance_id": "2369622005",
"name": "bat"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the material of the bat?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The color of the van is red."
}
|
{
"answer": "The color of the van is red.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2415548.jpg",
"index": "sealvqa_vaw_31",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the color of the van?"
},
{
"from": "gpt",
"value": "The color of the van is red."
}
],
"question": "What is the color of the van?",
"question_id": "sealvqa_vaw_31",
"search": 1,
"target_instances": [
{
"bbox": [
140,
62.5,
96,
96.83333333333331
],
"instance_id": "2415548001",
"name": "van"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the color of the van?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The material of the pillow is fluffy."
}
|
{
"answer": "The material of the pillow is fluffy.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2396597.jpg",
"index": "sealvqa_vaw_32",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the material of the pillow?"
},
{
"from": "gpt",
"value": "The material of the pillow is fluffy."
}
],
"question": "What is the material of the pillow?",
"question_id": "sealvqa_vaw_32",
"search": 1,
"target_instances": [
{
"bbox": [
100,
146.66666666666666,
105.16666666666666,
67.66666666666669
],
"instance_id": "2396597001",
"name": "pillow"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the material of the pillow?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "Yes, the color of the text is white."
}
|
{
"answer": "Yes, the color of the text is white.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2397023.jpg",
"index": "sealvqa_vaw_33",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nIs the color of the text white?"
},
{
"from": "gpt",
"value": "Yes, the color of the text is white."
}
],
"question": "Is the color of the text white?",
"question_id": "sealvqa_vaw_33",
"search": 1,
"target_instances": [
{
"bbox": [
179.20000000000002,
190.93333333333334,
135.4,
50.06666666666666
],
"instance_id": "2397023001",
"name": "text"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nIs the color of the text white?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The color of the speaker is gray."
}
|
{
"answer": "The color of the speaker is gray.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2391687.jpg",
"index": "sealvqa_vaw_34",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the color of the speaker?"
},
{
"from": "gpt",
"value": "The color of the speaker is gray."
}
],
"question": "What is the color of the speaker?",
"question_id": "sealvqa_vaw_34",
"search": 1,
"target_instances": [
{
"bbox": [
66,
57,
67,
14
],
"instance_id": "2391687005",
"name": "speaker"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the color of the speaker?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The color of the train is silver."
}
|
{
"answer": "The color of the train is silver.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2381611.jpg",
"index": "sealvqa_vaw_35",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the color of the train?"
},
{
"from": "gpt",
"value": "The color of the train is silver."
}
],
"question": "What is the color of the train?",
"question_id": "sealvqa_vaw_35",
"search": 1,
"target_instances": [
{
"bbox": [
56.666666666666664,
85,
113.5,
61
],
"instance_id": "2381611004",
"name": "train"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the color of the train?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "No, the color of the roof is not brown."
}
|
{
"answer": "No, the color of the roof is not brown.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2326987.jpg",
"index": "sealvqa_vaw_36",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nIs the color of the roof brown?"
},
{
"from": "gpt",
"value": "No, the color of the roof is not brown."
}
],
"question": "Is the color of the roof brown?",
"question_id": "sealvqa_vaw_36",
"search": 1,
"target_instances": [
{
"bbox": [
256.41,
237.54000000000002,
29.859999999999957,
15.430000000000007
],
"instance_id": "2326987003",
"name": "roof"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nIs the color of the roof brown?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The color of the box is white."
}
|
{
"answer": "The color of the box is white.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2355374.jpg",
"index": "sealvqa_vaw_37",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the color of the box?"
},
{
"from": "gpt",
"value": "The color of the box is white."
}
],
"question": "What is the color of the box?",
"question_id": "sealvqa_vaw_37",
"search": 1,
"target_instances": [
{
"bbox": [
345,
429,
30,
69
],
"instance_id": "2355374008",
"name": "box"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the color of the box?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "No, the material of the doll is not fluffy."
}
|
{
"answer": "No, the material of the doll is not fluffy.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2321166.jpg",
"index": "sealvqa_vaw_38",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nIs the material of the doll fluffy?"
},
{
"from": "gpt",
"value": "No, the material of the doll is not fluffy."
}
],
"question": "Is the material of the doll fluffy?",
"question_id": "sealvqa_vaw_38",
"search": 1,
"target_instances": [
{
"bbox": [
405,
203.33333333333334,
93.5,
106.00000000000003
],
"instance_id": "2321166001",
"name": "doll"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nIs the material of the doll fluffy?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The color of the cloud is dark gray."
}
|
{
"answer": "The color of the cloud is dark gray.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2390143.jpg",
"index": "sealvqa_vaw_39",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the color of the cloud?"
},
{
"from": "gpt",
"value": "The color of the cloud is dark gray."
}
],
"question": "What is the color of the cloud?",
"question_id": "sealvqa_vaw_39",
"search": 1,
"target_instances": [
{
"bbox": [
380,
152,
111,
85
],
"instance_id": "2390143006",
"name": "cloud"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the color of the cloud?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The color of the shorts is black."
}
|
{
"answer": "The color of the shorts is black.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2379103.jpg",
"index": "sealvqa_vaw_40",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the color of the shorts?"
},
{
"from": "gpt",
"value": "The color of the shorts is black."
}
],
"question": "What is the color of the shorts?",
"question_id": "sealvqa_vaw_40",
"search": 1,
"target_instances": [
{
"bbox": [
130,
149.16666666666666,
81,
66.00000000000003
],
"instance_id": "2379103003",
"name": "shorts"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the color of the shorts?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The color of the pants is gray."
}
|
{
"answer": "The color of the pants is gray.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2397139.jpg",
"index": "sealvqa_vaw_41",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the color of the pants?"
},
{
"from": "gpt",
"value": "The color of the pants is gray."
}
],
"question": "What is the color of the pants?",
"question_id": "sealvqa_vaw_41",
"search": 1,
"target_instances": [
{
"bbox": [
187,
184,
51,
70
],
"instance_id": "2397139006",
"name": "pants"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the color of the pants?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The color of the towel is white."
}
|
{
"answer": "The color of the towel is white.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2414657.jpg",
"index": "sealvqa_vaw_42",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the color of the towel?"
},
{
"from": "gpt",
"value": "The color of the towel is white."
}
],
"question": "What is the color of the towel?",
"question_id": "sealvqa_vaw_42",
"search": 1,
"target_instances": [
{
"bbox": [
138.195,
196.47,
91.465,
87.025
],
"instance_id": "2414657004",
"name": "towel"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the color of the towel?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The color of the boat is black."
}
|
{
"answer": "The color of the boat is black.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2399497.jpg",
"index": "sealvqa_vaw_43",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the color of the boat?"
},
{
"from": "gpt",
"value": "The color of the boat is black."
}
],
"question": "What is the color of the boat?",
"question_id": "sealvqa_vaw_43",
"search": 1,
"target_instances": [
{
"bbox": [
182,
198,
109,
25
],
"instance_id": "2399497004",
"name": "boat"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the color of the boat?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "No, the color of the branches is not light brown."
}
|
{
"answer": "No, the color of the branches is not light brown.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2377890.jpg",
"index": "sealvqa_vaw_44",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nIs the color of the branches light brown?"
},
{
"from": "gpt",
"value": "No, the color of the branches is not light brown."
}
],
"question": "Is the color of the branches light brown?",
"question_id": "sealvqa_vaw_44",
"search": 1,
"target_instances": [
{
"bbox": [
66.66666666666667,
4.166666666666667,
151.83333333333331,
56
],
"instance_id": "2377890001",
"name": "branches"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nIs the color of the branches light brown?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The color of the shoes is black."
}
|
{
"answer": "The color of the shoes is black.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2371600.jpg",
"index": "sealvqa_vaw_45",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the color of the shoes?"
},
{
"from": "gpt",
"value": "The color of the shoes is black."
}
],
"question": "What is the color of the shoes?",
"question_id": "sealvqa_vaw_45",
"search": 1,
"target_instances": [
{
"bbox": [
382.5,
282.5,
61,
36
],
"instance_id": "2371600003",
"name": "shoes"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the color of the shoes?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The color of the wing is white."
}
|
{
"answer": "The color of the wing is white.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2383438.jpg",
"index": "sealvqa_vaw_46",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the color of the wing?"
},
{
"from": "gpt",
"value": "The color of the wing is white."
}
],
"question": "What is the color of the wing?",
"question_id": "sealvqa_vaw_46",
"search": 1,
"target_instances": [
{
"bbox": [
12,
257,
276,
17
],
"instance_id": "2383438005",
"name": "wing"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the color of the wing?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The color of the jacket is blue."
}
|
{
"answer": "The color of the jacket is blue.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2376230.jpg",
"index": "sealvqa_vaw_47",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the color of the jacket?"
},
{
"from": "gpt",
"value": "The color of the jacket is blue."
}
],
"question": "What is the color of the jacket?",
"question_id": "sealvqa_vaw_47",
"search": 1,
"target_instances": [
{
"bbox": [
284,
123,
54,
134
],
"instance_id": "2376230010",
"name": "jacket"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the color of the jacket?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The color of the pants is black."
}
|
{
"answer": "The color of the pants is black.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2414709.jpg",
"index": "sealvqa_vaw_48",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the color of the pants?"
},
{
"from": "gpt",
"value": "The color of the pants is black."
}
],
"question": "What is the color of the pants?",
"question_id": "sealvqa_vaw_48",
"search": 1,
"target_instances": [
{
"bbox": [
304.16666666666663,
239.16666666666666,
44.33333333333337,
98.50000000000003
],
"instance_id": "2414709002",
"name": "pants"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the color of the pants?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The color of the scissors is orange."
}
|
{
"answer": "The color of the scissors is orange.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2360507.jpg",
"index": "sealvqa_vaw_49",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the color of the scissors?"
},
{
"from": "gpt",
"value": "The color of the scissors is orange."
}
],
"question": "What is the color of the scissors?",
"question_id": "sealvqa_vaw_49",
"search": 1,
"target_instances": [
{
"bbox": [
154.375,
191.25,
74.74999999999997,
39.125
],
"instance_id": "2360507005",
"name": "scissors"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the color of the scissors?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The color of the jacket is black."
}
|
{
"answer": "The color of the jacket is black.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/744.jpg",
"index": "sealvqa_vaw_50",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the color of the jacket?"
},
{
"from": "gpt",
"value": "The color of the jacket is black."
}
],
"question": "What is the color of the jacket?",
"question_id": "sealvqa_vaw_50",
"search": 1,
"target_instances": [
{
"bbox": [
599,
354,
78,
112
],
"instance_id": "744002",
"name": "jacket"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the color of the jacket?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The color of the lettering is black."
}
|
{
"answer": "The color of the lettering is black.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2339091.jpg",
"index": "sealvqa_vaw_51",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the color of the lettering?"
},
{
"from": "gpt",
"value": "The color of the lettering is black."
}
],
"question": "What is the color of the lettering?",
"question_id": "sealvqa_vaw_51",
"search": 1,
"target_instances": [
{
"bbox": [
202.5,
81.66666666666667,
170.16666666666663,
21
],
"instance_id": "2339091012",
"name": "lettering"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the color of the lettering?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "Yes, the color of the line is white."
}
|
{
"answer": "Yes, the color of the line is white.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2385831.jpg",
"index": "sealvqa_vaw_52",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nIs the color of the line white?"
},
{
"from": "gpt",
"value": "Yes, the color of the line is white."
}
],
"question": "Is the color of the line white?",
"question_id": "sealvqa_vaw_52",
"search": 1,
"target_instances": [
{
"bbox": [
255.855,
320.235,
77.035,
11.544999999999959
],
"instance_id": "2385831006",
"name": "line"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nIs the color of the line white?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The color of the pole is gray."
}
|
{
"answer": "The color of the pole is gray.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2394494.jpg",
"index": "sealvqa_vaw_53",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the color of the pole?"
},
{
"from": "gpt",
"value": "The color of the pole is gray."
}
],
"question": "What is the color of the pole?",
"question_id": "sealvqa_vaw_53",
"search": 1,
"target_instances": [
{
"bbox": [
167.66,
148.84666666666666,
20.366666666666674,
112.77333333333334
],
"instance_id": "2394494001",
"name": "pole"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the color of the pole?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The color of the jacket is yellow."
}
|
{
"answer": "The color of the jacket is yellow.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2369892.jpg",
"index": "sealvqa_vaw_54",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the color of the jacket?"
},
{
"from": "gpt",
"value": "The color of the jacket is yellow."
}
],
"question": "What is the color of the jacket?",
"question_id": "sealvqa_vaw_54",
"search": 1,
"target_instances": [
{
"bbox": [
170,
132.5,
62.66666666666666,
52.666666666666686
],
"instance_id": "2369892001",
"name": "jacket"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the color of the jacket?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "No, the pose of the deer is not walking."
}
|
{
"answer": "No, the pose of the deer is not walking.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2417170.jpg",
"index": "sealvqa_vaw_55",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nIs the pose of the deer walking?"
},
{
"from": "gpt",
"value": "No, the pose of the deer is not walking."
}
],
"question": "Is the pose of the deer walking?",
"question_id": "sealvqa_vaw_55",
"search": 1,
"target_instances": [
{
"bbox": [
253,
20,
56,
57
],
"instance_id": "2417170005",
"name": "deer"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nIs the pose of the deer walking?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_general
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The color of the statue is golden."
}
|
{
"answer": "The color of the statue is golden.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2377841.jpg",
"index": "sealvqa_vaw_56",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the color of the statue?"
},
{
"from": "gpt",
"value": "The color of the statue is golden."
}
],
"question": "What is the color of the statue?",
"question_id": "sealvqa_vaw_56",
"search": 1,
"target_instances": [
{
"bbox": [
254.19,
204.795,
38.74000000000001,
45.95500000000001
],
"instance_id": "2377841001",
"name": "statue"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the color of the statue?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "Yes, the material of the track is metal."
}
|
{
"answer": "Yes, the material of the track is metal.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2396282.jpg",
"index": "sealvqa_vaw_57",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nIs the material of the track metal?"
},
{
"from": "gpt",
"value": "Yes, the material of the track is metal."
}
],
"question": "Is the material of the track metal?",
"question_id": "sealvqa_vaw_57",
"search": 1,
"target_instances": [
{
"bbox": [
355,
267.5,
68.5,
66
],
"instance_id": "2396282002",
"name": "track"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nIs the material of the track metal?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The color of the sign is white."
}
|
{
"answer": "The color of the sign is white.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/3396.jpg",
"index": "sealvqa_vaw_58",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the color of the sign?"
},
{
"from": "gpt",
"value": "The color of the sign is white."
}
],
"question": "What is the color of the sign?",
"question_id": "sealvqa_vaw_58",
"search": 1,
"target_instances": [
{
"bbox": [
681.3333333333334,
218.66666666666666,
59.66666666666663,
52.99999999999997
],
"instance_id": "3396002",
"name": "sign"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the color of the sign?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The color of the platter is black."
}
|
{
"answer": "The color of the platter is black.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/1524.jpg",
"index": "sealvqa_vaw_59",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the color of the platter?"
},
{
"from": "gpt",
"value": "The color of the platter is black."
}
],
"question": "What is the color of the platter?",
"question_id": "sealvqa_vaw_59",
"search": 1,
"target_instances": [
{
"bbox": [
329,
41,
127,
72
],
"instance_id": "1524001",
"name": "platter"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the color of the platter?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The color of the sky is blue."
}
|
{
"answer": "The color of the sky is blue.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2412093.jpg",
"index": "sealvqa_vaw_60",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the color of the sky?"
},
{
"from": "gpt",
"value": "The color of the sky is blue."
}
],
"question": "What is the color of the sky?",
"question_id": "sealvqa_vaw_60",
"search": 1,
"target_instances": [
{
"bbox": [
250.83333333333334,
64.16666666666666,
65.16666666666666,
110.16666666666669
],
"instance_id": "2412093000",
"name": "sky"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the color of the sky?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "Yes, the color of the stripe is black."
}
|
{
"answer": "Yes, the color of the stripe is black.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2317654.jpg",
"index": "sealvqa_vaw_61",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nIs the color of the stripe black?"
},
{
"from": "gpt",
"value": "Yes, the color of the stripe is black."
}
],
"question": "Is the color of the stripe black?",
"question_id": "sealvqa_vaw_61",
"search": 1,
"target_instances": [
{
"bbox": [
76.80000000000001,
218.24,
63.079999999999984,
57.31999999999999
],
"instance_id": "2317654001",
"name": "stripe"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nIs the color of the stripe black?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The color of the logo is green."
}
|
{
"answer": "The color of the logo is green.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2379090.jpg",
"index": "sealvqa_vaw_62",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the color of the logo?"
},
{
"from": "gpt",
"value": "The color of the logo is green."
}
],
"question": "What is the color of the logo?",
"question_id": "sealvqa_vaw_62",
"search": 1,
"target_instances": [
{
"bbox": [
82.5,
130,
92.66666666666666,
86.83333333333331
],
"instance_id": "2379090000",
"name": "logo"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the color of the logo?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "Yes, the material of the skyscraper is glass."
}
|
{
"answer": "Yes, the material of the skyscraper is glass.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2388436.jpg",
"index": "sealvqa_vaw_63",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nIs the material of the skyscraper glass?"
},
{
"from": "gpt",
"value": "Yes, the material of the skyscraper is glass."
}
],
"question": "Is the material of the skyscraper glass?",
"question_id": "sealvqa_vaw_63",
"search": 1,
"target_instances": [
{
"bbox": [
237,
0,
68,
69
],
"instance_id": "2388436004",
"name": "skyscraper"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nIs the material of the skyscraper glass?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "Yes, the color of the skirt is blue."
}
|
{
"answer": "Yes, the color of the skirt is blue.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2386450.jpg",
"index": "sealvqa_vaw_64",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nIs the color of the skirt blue?"
},
{
"from": "gpt",
"value": "Yes, the color of the skirt is blue."
}
],
"question": "Is the color of the skirt blue?",
"question_id": "sealvqa_vaw_64",
"search": 1,
"target_instances": [
{
"bbox": [
56,
210,
101,
77
],
"instance_id": "2386450002",
"name": "skirt"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nIs the color of the skirt blue?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The color of the gloves is black."
}
|
{
"answer": "The color of the gloves is black.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2366589.jpg",
"index": "sealvqa_vaw_65",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the color of the gloves?"
},
{
"from": "gpt",
"value": "The color of the gloves is black."
}
],
"question": "What is the color of the gloves?",
"question_id": "sealvqa_vaw_65",
"search": 1,
"target_instances": [
{
"bbox": [
205.83333333333334,
228.33333333333334,
31.833333333333314,
40.99999999999997
],
"instance_id": "2366589004",
"name": "gloves"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the color of the gloves?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "Yes, the material of the trash can is stainless steel."
}
|
{
"answer": "Yes, the material of the trash can is stainless steel.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2413414.jpg",
"index": "sealvqa_vaw_66",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nIs the material of the trash can stainless steel?"
},
{
"from": "gpt",
"value": "Yes, the material of the trash can is stainless steel."
}
],
"question": "Is the material of the trash can stainless steel?",
"question_id": "sealvqa_vaw_66",
"search": 1,
"target_instances": [
{
"bbox": [
321,
154,
41,
77
],
"instance_id": "2413414004",
"name": "trash can"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nIs the material of the trash can stainless steel?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The color of the cloud is white."
}
|
{
"answer": "The color of the cloud is white.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2371946.jpg",
"index": "sealvqa_vaw_67",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the color of the cloud?"
},
{
"from": "gpt",
"value": "The color of the cloud is white."
}
],
"question": "What is the color of the cloud?",
"question_id": "sealvqa_vaw_67",
"search": 1,
"target_instances": [
{
"bbox": [
291.375,
124.95,
23.05000000000001,
87.10000000000001
],
"instance_id": "2371946003",
"name": "cloud"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the color of the cloud?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "No, the state of the jacket is not open."
}
|
{
"answer": "No, the state of the jacket is not open.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2398772.jpg",
"index": "sealvqa_vaw_68",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nIs the state of the jacket open?"
},
{
"from": "gpt",
"value": "No, the state of the jacket is not open."
}
],
"question": "Is the state of the jacket open?",
"question_id": "sealvqa_vaw_68",
"search": 1,
"target_instances": [
{
"bbox": [
221,
133,
63,
62
],
"instance_id": "2398772002",
"name": "jacket"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nIs the state of the jacket open?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_general
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The color of the mask is blue."
}
|
{
"answer": "The color of the mask is blue.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2404310.jpg",
"index": "sealvqa_vaw_69",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the color of the mask?"
},
{
"from": "gpt",
"value": "The color of the mask is blue."
}
],
"question": "What is the color of the mask?",
"question_id": "sealvqa_vaw_69",
"search": 1,
"target_instances": [
{
"bbox": [
136.38333333333333,
194.83333333333334,
46.09,
36.62666666666664
],
"instance_id": "2404310001",
"name": "mask"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the color of the mask?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The color of the lines is yellow."
}
|
{
"answer": "The color of the lines is yellow.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2362978.jpg",
"index": "sealvqa_vaw_70",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the color of the lines?"
},
{
"from": "gpt",
"value": "The color of the lines is yellow."
}
],
"question": "What is the color of the lines?",
"question_id": "sealvqa_vaw_70",
"search": 1,
"target_instances": [
{
"bbox": [
310,
312.5,
71,
21.833333333333314
],
"instance_id": "2362978002",
"name": "lines"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the color of the lines?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "No, the state of the rod is not empty."
}
|
{
"answer": "No, the state of the rod is not empty.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2320709.jpg",
"index": "sealvqa_vaw_71",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nIs the state of the rod empty?"
},
{
"from": "gpt",
"value": "No, the state of the rod is not empty."
}
],
"question": "Is the state of the rod empty?",
"question_id": "sealvqa_vaw_71",
"search": 1,
"target_instances": [
{
"bbox": [
5,
3.3333333333333335,
211,
46
],
"instance_id": "2320709005",
"name": "rod"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nIs the state of the rod empty?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_general
|
visual_toolbox_v2
|
|
sealvqa_vaw
|
{
"ground_truth": "The color of the deck is red."
}
|
{
"answer": "The color of the deck is red.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "vaw_attribute",
"has_targets": true,
"image_path": "gqa/images/2405871.jpg",
"index": "sealvqa_vaw_72",
"original_conversations": [
{
"from": "human",
"value": "<image>\nAdditional visual information to focus on: <object>.\nWhat is the color of the deck?"
},
{
"from": "gpt",
"value": "The color of the deck is red."
}
],
"question": "What is the color of the deck?",
"question_id": "sealvqa_vaw_72",
"search": 1,
"target_instances": [
{
"bbox": [
322.5,
238.33333333333334,
59.33333333333337,
44.33333333333334
],
"instance_id": "2405871001",
"name": "deck"
}
]
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the color of the deck?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
sealvqa_vaw_attribute
|
visual_toolbox_v2
|
End of preview. Expand
in Data Studio
README.md exists but content is empty.
- Downloads last month
- 100