Self-Supervised Video Pose Representation Learning for Occlusion- Robust Action Recognition.
Di YangYaohui WangAntitza DantchevaLorenzo GarattoniGianpiero FrancescaFrançois BrémondPublished in: FG (2021)
Keyphrases
- action recognition
- human actions
- human pose
- recognition of human actions
- recognizing human actions
- view invariant
- spatial temporal
- action classification
- action detection
- video dataset
- bag of features
- computer vision
- human detection
- three dimensional
- body parts
- video content
- bag of words
- static images
- partial occlusion
- event detection
- activity recognition
- sensor data
- action recognition in videos