Task-Specific Alignment and Multiple Level Transformer for Few-Shot Action Recognition.
Fei GuoLi ZhuYiWang WangPublished in: CoRR (2023)
Keyphrases
- action recognition
- human actions
- action classification
- bag of words
- computer vision
- human detection
- spatial temporal
- activity recognition
- body parts
- video sequences
- mid level
- recognition of human actions
- recognizing human actions
- bag of features
- independent subspace analysis
- depth sensors
- action detection
- view invariant action recognition
- recognizing actions
- video shots
- visual features
- three dimensional
- view invariant
- static images
- high level