Saliency-based selection of sparse descriptors for action recognition.
Eleonora VigMichael DorrDavid D. CoxPublished in: ICIP (2012)
Keyphrases
- action recognition
- action recognition in videos
- bag of features
- human actions
- activity recognition
- bag of words
- human detection
- action classification
- mid level features
- computer vision
- recognizing human actions
- depth sensors
- recognition of human actions
- video dataset
- static images
- body parts
- recognizing actions
- spatial temporal
- dictionary learning
- human pose
- action detection
- shape descriptors
- visual attention
- human activities
- keypoints
- low level descriptors
- sift descriptors
- saliency map
- image representation
- visual features
- object recognition
- three dimensional