CAS-YNU Multi-modal Cross-view Human Action Dataset.
Qingsong ZhaoJun ChengDapeng TaoXiaopeng JiLei WangPublished in: ICIA (2018)
Keyphrases
- multi modal
- human actions
- cross view
- action recognition
- spatio temporal
- space time
- human motion
- video sequences
- similarity search
- activity recognition
- human activities
- visual features
- high dimensional
- graph embedding
- bag of words
- visual data
- machine learning
- graph cuts
- pairwise
- three dimensional
- computer vision
- learning algorithm