STMT: A Spatial-Temporal Mesh Transformer for MoCap-Based Action Recognition.
Xiaoyu ZhuPo-Yao HuangJunwei LiangCelso M. de MeloAlexander G. HauptmannPublished in: CoRR (2023)
Keyphrases
- spatial temporal
- action recognition
- human actions
- activity recognition
- bag of words
- action classification
- motion capture
- computer vision
- body parts
- bag of features
- human activities
- recognition of human actions
- recognizing human actions
- video database
- action recognition in videos
- text classification
- co occurrence
- semi supervised
- multiscale