Learnable Sampling 3D Convolution for Video Enhancement and Action Recognition.
Shuyang GuJianmin BaoDong ChenPublished in: CoRR (2020)
Keyphrases
- action recognition
- human actions
- action classification
- spatial temporal
- video dataset
- action detection
- recognizing human actions
- image processing
- motion features
- static images
- recognition of human actions
- bag of words
- human activities
- human detection
- space time interest points
- activity recognition
- computer vision
- mid level
- body parts
- spatio temporal
- recognizing actions
- action recognition in videos
- bag of features
- video data
- video content
- depth sensors
- motion history images
- video sequences
- human pose
- motion capture data
- action primitives
- image sequences
- video images
- space time
- video frames
- video streams
- event detection
- video shots
- video analysis
- video clips
- video retrieval
- video surveillance