End-to-end Video-level Representation Learning for Action Recognition.
Jiagang ZhuZheng ZhuWei ZouPublished in: ICPR (2018)
Keyphrases
- end to end
- action recognition
- recognition of human actions
- recognizing human actions
- human actions
- spatial temporal
- action classification
- action detection
- real time
- static images
- spatio temporal interest points
- view invariant
- motion features
- video data
- bag of features
- human detection
- bag of words
- video sequences
- reinforcement learning
- multimedia
- human activities
- video streams
- spatio temporal
- action recognition in videos
- computer vision