AFE-CNN: 3D Skeleton-based Action Recognition with Action Feature Enhancement.
Shannan GuanHaiyan LuLinchao ZhuGengfa FangPublished in: CoRR (2022)
Keyphrases
- action recognition
- human actions
- action classification
- recognizing human actions
- recognizing actions
- spatio temporal interest points
- recognition of human actions
- action primitives
- view invariant
- motion features
- activity recognition
- bag of words
- action detection
- computer vision
- spatial temporal
- body parts
- human detection
- mid level features
- space time interest points
- global features
- human pose
- mid level
- static images
- feature vectors
- human motion
- video dataset
- human activities
- atomic actions
- motion recognition
- space time
- motion history images
- spatio temporal
- view invariant action recognition
- action recognition in videos
- bag of features
- human computer interaction
- low level
- viewpoint