Multi-modal feature fusion for action recognition in RGB-D sequences.
Amir ShahroudyGang WangTian-Tsong NgPublished in: ISCCSP (2014)
Keyphrases
- multi modal
- action recognition
- feature fusion
- bag of words
- human actions
- depth cameras
- multiple features
- feature extraction
- activity recognition
- computer vision
- high dimensional
- video search
- human activities
- depth information
- image processing
- infrared
- data fusion
- higher level
- multi class
- image annotation
- video sequences
- depth data
- data mining