Attention module-based spatial-temporal graph convolutional networks for skeleton-based action recognition.
Yinghui KongLi LiKe ZhangQiang NiJungong HanPublished in: J. Electronic Imaging (2019)
Keyphrases
- spatial temporal
- action recognition
- human actions
- bag of words
- activity recognition
- computer vision
- recognition of human actions
- recognizing human actions
- action recognition in videos
- action classification
- human activities
- graph structure
- bag of features
- space time interest points
- video shots
- video database
- spatial and temporal
- video frames
- spatial information
- low level
- feature extraction