MV2Flow: Learning Motion Representation for Fast Compressed Video Action Recognition.
Hezhen HuWengang ZhouXingze LiNing YanHouqiang LiPublished in: ACM Trans. Multim. Comput. Commun. Appl. (2020)
Keyphrases
- action recognition
- recognizing human actions
- recognition of human actions
- action recognition in videos
- compressed video
- view invariant
- human actions
- computer vision
- action classification
- human detection
- kalman filter
- image representation
- multiscale
- activity recognition
- human activities
- video content
- body parts
- video analysis
- video quality
- motion model
- image sequences