CANet: Comprehensive Attention Network for video-based action recognition.
Xiong GaoZhaobin ChangXingcheng RanYonggang LuPublished in: Knowl. Based Syst. (2024)
Keyphrases
- action recognition
- human actions
- human detection
- activity recognition
- bag of words
- computer vision
- recognizing human actions
- action classification
- recognition of human actions
- spatial temporal
- video dataset
- view invariant
- human activities
- action detection
- human pose
- body parts
- static images
- action recognition in videos
- independent subspace analysis
- depth cameras
- mid level
- image classification
- spatio temporal
- image sequences