Multi-head attention-based two-stream EfficientNet for action recognition.
Aihua ZhouYujun MaWanting JiMing ZongPei YangMin WuMingzhe LiuPublished in: Multim. Syst. (2023)
Keyphrases
- action recognition
- bag of words
- human actions
- action classification
- computer vision
- body parts
- activity recognition
- human detection
- data streams
- spatial temporal
- real time
- recognition of human actions
- recognizing human actions
- recognizing actions
- static images
- video dataset
- human pose
- action detection
- bag of features
- view invariant
- independent subspace analysis
- view invariant action recognition
- motion capture data
- depth information