简体中文 | English
We implemented action recgonition model and action localization model in this repo.
Action recognition method | ||||
PP-TSM (PP series) | PP-TSN (PP series) | PP-TimeSformer (PP series) | TSN (2D’) | TSM (2D') |
SlowFast (3D’) | TimeSformer (Transformer') | VideoSwin (Transformer’) | TokenShift (3D’) | AttentionLSTM (RNN‘) |
MoViNet (Lite‘) | ||||
Skeleton based action recognition | ||||
ST-GCN (Custom’) | AGCN (Adaptive') | 2s-AGCN (Adaptive') | CTR-GCN (GCN‘) | |
Sequence action detection method | ||||
BMN (One-stage') | ||||
temporal segment | ||||
MS-TCN | ASRF | |||
Spatio-temporal motion detection method | ||||
SlowFast+Fast R-CNN | ||||
Multimodal | ||||
ActBERT (Learning') | T2VLAD (Retrieval') | |||
Video target segmentation | ||||
CFBI (Semi') | MA-Net (Supervised') | |||
Monocular depth estimation | ||||
ADDS (Unsupervised‘) |