DTG-Net: Differentiated Teachers Guided Self-Supervised Video Action Recognition.
Ziming LiuGuangyu GaoA. Kai QinJinyang LiPublished in: CoRR (2020)
Keyphrases
- action recognition
- human actions
- action classification
- video dataset
- spatial temporal
- action detection
- recognizing human actions
- recognition of human actions
- motion features
- static images
- human activities
- space time interest points
- activity recognition
- video sequences
- motion history images
- video frames
- video data
- spatio temporal
- computer vision
- atomic actions
- space time
- multiscale
- action recognition in videos
- human motion
- linear filters
- visual features
- natural images
- image features
- image sequences