SMAM: Self and Mutual Adaptive Matching for Skeleton-Based Few-Shot Action Recognition.
Zhiheng LiXuyuan GongRan SongPeng DuanJun LiuWei ZhangPublished in: IEEE Trans. Image Process. (2023)
Keyphrases
- action recognition
- human actions
- human detection
- bag of words
- activity recognition
- computer vision
- action classification
- spatial temporal
- matching algorithm
- body parts
- video sequences
- independent subspace analysis
- static images
- video shots
- human activities
- image matching
- feature points
- view invariant
- depth sensors
- bag of features
- human pose
- mid level
- action primitives
- recognizing actions
- video dataset
- recognizing human actions
- recognition of human actions
- action recognition in videos
- object recognition