Task-Specific Alignment and Multiple-level Transformer for few-shot action recognition.
Fei GuoLi ZhuYikang WangJing SunPublished in: Neurocomputing (2024)
Keyphrases
- action recognition
- human actions
- bag of words
- activity recognition
- computer vision
- human detection
- action classification
- spatial temporal
- recognizing human actions
- human activities
- body parts
- recognition of human actions
- action detection
- video sequences
- human pose
- view invariant
- recognizing actions
- independent subspace analysis
- video dataset
- bag of features
- visual words
- multi view
- text classification
- three dimensional