Action recognition in video using a spatial-temporal graph-based feature representation.
Iveel JargalsaikhanSuzanne LittleRémi TrichetNoel E. O'ConnorPublished in: AVSS (2015)
Keyphrases
- spatial temporal
- action recognition
- feature representation
- human actions
- action classification
- bag of words
- activity recognition
- feature extraction
- video database
- computer vision
- face recognition
- human activities
- low dimensional
- feature set
- space time interest points
- bag of features
- feature descriptors
- spatio temporal
- sparse representation
- semi supervised
- viewpoint
- image processing
- spatial and temporal
- signal processing
- video shots
- image retrieval
- feature space
- high level