STSD: spatial-temporal semantic decomposition transformer for skeleton-based action recognition.
Hu CuiTessai HayamaPublished in: Multim. Syst. (2024)
Keyphrases
- spatial temporal
- action recognition
- human actions
- bag of words
- activity recognition
- computer vision
- action classification
- human activities
- recognizing actions
- recognizing human actions
- video database
- bag of features
- view invariant
- recognition of human actions
- semantic information
- search engine
- space time interest points
- action recognition in videos
- semantic concepts
- high level
- temporal information
- multiscale
- multi modal