Semantic parts based top-down pyramid for action recognition.
Zhichen ZhaoHuimin MaXiaozhi ChenPublished in: Pattern Recognit. Lett. (2016)
Keyphrases
- action recognition
- deformable part models
- human actions
- bag of words
- computer vision
- action classification
- high level
- human detection
- spatial temporal
- activity recognition
- recognizing actions
- body parts
- view invariant
- recognizing human actions
- depth sensors
- semantic information
- recognition of human actions
- independent subspace analysis
- video dataset
- view invariant action recognition
- action recognition in videos
- static images
- mid level
- bag of features
- semantic similarity
- multiscale
- action detection
- action primitives
- visual words
- scale space
- input image
- low level
- image retrieval