Learning discriminative motion feature for enhancing multi-modal action recognition.
Jianyu YangYao HuangZhanpeng ShaoChunping LiuPublished in: J. Vis. Commun. Image Represent. (2021)
Keyphrases
- multi modal
- action recognition
- recognizing human actions
- mid level
- recognition of human actions
- motion features
- action classification
- static images
- humanoid robot
- computer vision
- max margin
- human detection
- human actions
- human movements
- activity recognition
- action primitives
- action recognition in videos
- view invariant
- cross modal
- object recognition
- keywords
- feature extraction
- image sequences