Lorenzo Bianchi

lorebianchi98's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper 1 day ago

CountingDINO: A Training-free Pipeline for Class-Agnostic Counting using Unsupervised Backbones

Paper • 2504.16570 • Published Apr 23

updated a collection 6 days ago

Talk2DINO

Collection

Official Collection of the ICCV 2025 paper "Talking to DINO: Bridging Self-Supervised Vision Backbones with Language for Open-Vocabulary Segmentation" • 4 items • Updated 6 days ago

published a Space 6 days ago

Running

1

1

NoctOWL

🦀

Fine-grained open-vocabulary object detection using NoctOWL

updated a Space 6 days ago

Running

1

1

NoctOWL

🦀

Fine-grained open-vocabulary object detection using NoctOWL

upvoted a collection 8 days ago

Patch-ioner

Collection

The official collection of all the Patch-ioner framework models • 9 items • Updated 4 days ago • 2

updated a Space 8 days ago

Running on Zero

12

12

Talk2DINO

💻

Demo of Talk2DINO, model presented at ICCV 2025.

New activity in lorebianchi98/Talk2DINO 9 days ago

Apply for community grant: Academic project (gpu)

1

#1 opened 9 days ago by

lorebianchi98

published a Space 9 days ago

Running on Zero

12

12

Talk2DINO

💻

Demo of Talk2DINO, model presented at ICCV 2025.

authored a paper 9 days ago

One Patch to Caption Them All: A Unified Zero-Shot Captioning Framework

Paper • 2510.02898 • Published 14 days ago • 4

upvoted a paper 10 days ago

One Patch to Caption Them All: A Unified Zero-Shot Captioning Framework

Paper • 2510.02898 • Published 14 days ago • 4

updated 2 models 10 days ago

lorebianchi98/Talk2DINO-ViTL

Image Segmentation • Updated 10 days ago • 91 • 3

lorebianchi98/Talk2DINO-ViTB

Image Segmentation • Updated 10 days ago • 309 • 2

liked a Space 14 days ago

Running on Zero

3

3

Patch Ioner

🏆

Repo for the Paper "One Patch to Caption Them All: ...

authored a paper 16 days ago

Talking to DINO: Bridging Self-Supervised Vision Backbones with Language for Open-Vocabulary Segmentation

Paper • 2411.19331 • Published Nov 28, 2024 • 5

upvoted a paper 17 days ago

Talking to DINO: Bridging Self-Supervised Vision Backbones with Language for Open-Vocabulary Segmentation

Paper • 2411.19331 • Published Nov 28, 2024 • 5

New activity in lorebianchi98/Talk2DINO-ViTB 20 days ago

Improve model card: Update GitHub link, add abstract, library_name, tags, and sample usage

1

#1 opened about 1 month ago by

nielsr

updated a model 2 months ago

lorebianchi98/Talk2DINO-ViTB

Image Segmentation • Updated 10 days ago • 309 • 2