Focal and Global Spatial-Temporal Transformer for Skeleton-based Action Recognition.
Zhimin GaoPeitao WangPei LvXiaoheng JiangQidong LiuPichao WangMingliang XuWanqing LiPublished in: CoRR (2022)
Keyphrases
- spatial temporal
- action recognition
- human actions
- bag of words
- activity recognition
- computer vision
- action classification
- recognition of human actions
- recognizing human actions
- recognizing actions
- bag of features
- human activities
- pose estimation
- action recognition in videos
- view invariant
- search engine
- space time interest points
- video database
- co occurrence
- object recognition