Improving bag-of-poses with semi-temporal pose descriptors for skeleton-based action recognition.
Saeid AgahianFarhood NeginCemal KösePublished in: Vis. Comput. (2019)
Keyphrases
- action recognition
- human pose
- bag of words
- recognizing actions
- action recognition in videos
- bag of features
- spatial temporal
- human actions
- body parts
- mid level features
- human detection
- static images
- activity recognition
- computer vision
- human pose estimation
- motion history images
- pose estimation
- temporal information
- visual words
- action classification
- action detection
- recognizing human actions
- shape analysis
- human body
- shape descriptors
- spatial and temporal
- view invariant
- depth sensors
- low level descriptors
- space time
- spatio temporal
- visual features
- temporal structure
- body pose
- temporal relations
- image retrieval
- recognition of human actions
- depth images
- feature descriptors
- human computer interaction
- keypoints
- face recognition