Pinned Repositories
VideoEspresso
VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection
Continual-LLaVA
DCNet
[ACM MM 22] Correspondence Matters for Video Referring Expression Comprehension
LocVTP
[ECCV 22] LocVTP: Video-Text Pre-training for Temporal Localization
mengcaopku.github.io
SLM
PhysGame
PhysGame Benchmark for Physical Commonsense Evaluation in Gameplay Videos
mengcaopku's Repositories
mengcaopku/LocVTP
[ECCV 22] LocVTP: Video-Text Pre-training for Temporal Localization
mengcaopku/DCNet
[ACM MM 22] Correspondence Matters for Video Referring Expression Comprehension
mengcaopku/Continual-LLaVA
mengcaopku/mengcaopku.github.io