Learnable Sampling 3D Convolution for Video Enhancement and Action Recognition.
Shuyang GuJianmin BaoDong ChenPublished in: ICME (2021)
Keyphrases
- action recognition
- human actions
- action classification
- video dataset
- spatial temporal
- action detection
- recognizing human actions
- motion features
- recognition of human actions
- static images
- bag of words
- activity recognition
- human detection
- image processing
- human activities
- space time interest points
- computer vision
- mid level
- body parts
- video streams
- view invariant
- motion history images
- video data
- action recognition in videos
- recognizing actions
- spatio temporal
- video sequences
- action primitives
- view invariant action recognition
- motion capture data
- human pose
- video surveillance
- video content
- object detection