sming256
Follow
-
minimal_video_pairs Public
Forked from facebookresearch/minimal_video_pairsA Shortcut-aware Video-QA Benchmark for Physical Understanding via Minimal Video Pairs
Python Other UpdatedJun 17, 2025 -
OpenTAD Public
OpenTAD is an open-source temporal action detection (TAD) toolbox based on PyTorch.
-
BOLT Public
[CVPR2025] BOLT: Boost Large Vision-Language Model Without Training for Long-form Video Understanding
-
TimeLoc Public
TimeLoc: A Unified End-to-End Framework for Precise Timestamp Localization in Long Videos
9 UpdatedMar 11, 2025 -
activitynet.github.io Public
Forked from activitynet/activitynet.github.ioWebsite
JavaScript UpdatedOct 17, 2024 -
ETAD Public
[CVPRW2023] The official implementation of ETAD: A Unified Framework for Efficient Temporal Action Detection
-
AdaTAD Public
[CVPR2024] The official implementation of AdaTAD: End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames
-
mmaction2 Public
Forked from open-mmlab/mmaction2OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
Python Apache License 2.0 UpdatedAug 29, 2023 -
TSI Public
TSI: Temporal Scale Invariant Network for Action Proposal Generation
-
KAUSTian_Handbook_CN Public
Forked from guochengqian/KAUSTian_Handbook_CNKAUST Handbook (in Chinese)
MIT License UpdatedJul 28, 2022 -
denseflow Public
Forked from bityangke/denseflowdenseflow, extract frames, optical flow, resize, and more!