SCD-Net: Spatiotemporal Clues Disentanglement Network for Self-Supervised Skeleton-Based Action Recognition.
Cong WuXiao-Jun WuJosef KittlerTianyang XuSara AhmedMuhammad AwaisZhenhua FengPublished in: AAAI (2024)
Keyphrases
- action recognition
- human actions
- bag of words
- spatial temporal
- activity recognition
- computer vision
- recognition of human actions
- action classification
- human detection
- body parts
- static images
- recognizing human actions
- machine learning
- human pose
- recognizing actions
- view invariant
- action recognition in videos
- action detection
- spatial and temporal
- bag of features
- view invariant action recognition
- object detection
- depth sensors
- three dimensional
- multiscale
- spatio temporal
- low level