Representing Videos As Discriminative Sub-Graphs for Action Recognition.
Dong LiZhaofan QiuYingwei PanTing YaoHouqiang LiTao MeiPublished in: CVPR (2021)
Keyphrases
- action recognition
- action classification
- human actions
- recognizing actions
- recognition of human actions
- video dataset
- mid level features
- ucf sports
- bag of words
- recognizing human actions
- mid level
- spatio temporal interest points
- static images
- human activities
- action detection
- view invariant
- spatial temporal
- computer vision
- motion features
- max margin
- activity recognition
- human detection
- motion history images
- bag of features
- action recognition in videos
- body parts
- space time interest points
- deformable part models
- human object interactions
- depth sensors
- human pose
- global features
- feature extraction
- motion capture data
- machine learning