A new framework of action recognition with discriminative parts, spatio-temporal and causal interaction descriptors.
Ming TongYiran ChenMengao ZhaoWeijuan TianPublished in: J. Vis. Commun. Image Represent. (2018)
Keyphrases
- action recognition
- action recognition in videos
- human actions
- spatio temporal
- action classification
- spatial temporal
- bag of words
- video dataset
- recognition of human actions
- bag of features
- mid level features
- human computer interaction
- human activities
- computer vision
- recognizing actions
- mid level
- deformable part models
- bayesian networks
- spatio temporal interest points
- view invariant
- max margin
- human detection
- activity recognition
- bag of visual words
- independent component analysis
- video data