MoFAP: A Multi-level Representation for Action Recognition.
Limin WangYu QiaoXiaoou TangPublished in: Int. J. Comput. Vis. (2016)
Keyphrases
- action recognition
- recognizing human actions
- recognition of human actions
- action recognition in videos
- view invariant
- human actions
- bag of words
- bag of features
- activity recognition
- spatial temporal
- action classification
- computer vision
- human detection
- body parts
- mid level
- viewpoint
- depth sensors
- action primitives
- recognizing actions
- static images
- video dataset
- visual words
- spatio temporal
- multiscale
- machine learning
- view invariant action recognition