Beyond Frame-level CNN: Saliency-Aware 3-D CNN With LSTM for Video Action Recognition.
Xuanhan WangLianli GaoJingkuan SongHeng Tao ShenPublished in: IEEE Signal Process. Lett. (2017)
Keyphrases
- action recognition
- human actions
- action classification
- video dataset
- spatial temporal
- action detection
- video frames
- recognizing human actions
- recognition of human actions
- human activities
- motion features
- activity recognition
- static images
- human detection
- computer vision
- bag of words
- space time interest points
- key frames
- body parts
- mid level
- video sequences
- bag of features
- multimedia
- recognizing actions
- depth sensors
- saliency map
- visual attention
- video streams
- view invariant
- video data
- video images
- video search
- video analysis
- human pose
- video retrieval
- visual words
- atomic actions
- motion history images
- visual features
- human motion