A 3-dimensional sift descriptor and its application to action recognition.
Paul ScovannerSaad AliMubarak ShahPublished in: ACM Multimedia (2007)
Keyphrases
- action recognition
- sift descriptors
- bag of features
- bag of words
- visual words
- discriminative power
- human actions
- keypoints
- activity recognition
- computer vision
- action classification
- image matching
- projective invariants
- image features
- feature representation
- scale invariant feature transform
- object recognition
- human activities
- maximum likelihood
- multi view
- image segmentation