Multi-Modal Fusion With Observation Points For Skeleton Action Recognition.
Iqbal SinghXiaodan ZhuMichael A. GreenspanPublished in: ICIP (2020)
Keyphrases
- action recognition
- multi modal fusion
- view invariant action recognition
- human actions
- bag of words
- activity recognition
- action classification
- computer vision
- human detection
- depth sensors
- recognizing human actions
- recognizing actions
- spatial temporal
- human pose
- recognition of human actions
- body parts
- video dataset
- view invariant
- bag of features
- human activities
- feature extraction
- three dimensional
- keypoints