Collaborative Spatio-temporal Feature Learning for Video Action Recognition.
Chao LiQiaoyong ZhongDi XieShiliang PuPublished in: CoRR (2019)
Keyphrases
- action recognition
- human actions
- spatio temporal interest points
- spatio temporal
- spatial temporal
- action classification
- motion features
- computer vision
- human activities
- recognition of human actions
- space time
- human detection
- video dataset
- mid level
- video sequences
- activity recognition
- bag of words
- spatial and temporal
- static images
- recognizing actions
- video data
- three dimensional
- low level features
- max margin
- image sequences
- view invariant
- depth sensors
- image representation