Cross-Fiber Spatial-Temporal Co-enhanced Networks for Video Action Recognition.
Haoze WuZheng-Jun ZhaXin WenZhenzhong ChenDong LiuXuejin ChenPublished in: ACM Multimedia (2019)
Keyphrases
- spatial temporal
- action recognition
- human actions
- bag of words
- action classification
- activity recognition
- action detection
- video dataset
- computer vision
- video database
- recognizing human actions
- static images
- recognition of human actions
- human activities
- bag of features
- motion features
- space time interest points
- spatial and temporal
- multi modal
- video shots
- three dimensional
- multimedia