MAD: A Scalable Dataset for Language Grounding in Videos from Movie Audio Descriptions
Paper
•
2112.00431
•
Published
Alejandro Pardo
pardoalejo
·
AI & ML interests
None yet
Recent Activity
authored
a paper
16 days ago
MAD: A Scalable Dataset for Language Grounding in Videos from Movie
Audio Descriptions
authored
a paper
16 days ago
OpenTAD: A Unified Framework and Comprehensive Study of Temporal Action
Detection
authored
a paper
16 days ago
MatchDiffusion: Training-free Generation of Match-cuts
Organizations
