Augmenting bag-of-words: a robust contextual representation of spatiotemporal interest points for action recognition.
Yang LiJunyong YeTongqing WangShijian HuangPublished in: Vis. Comput. (2015)
Keyphrases
- action recognition
- bag of words
- view invariant
- recognizing human actions
- fisher kernel
- visual words
- recognition of human actions
- action recognition in videos
- human actions
- image representation
- bag of features
- action classification
- computer vision
- human detection
- spatial pyramid matching
- activity recognition
- body parts
- pascal voc
- image classification
- text classification
- object retrieval
- space time
- mid level
- static images
- human pose
- moving objects
- pairwise