Deformable patch embedding-based shift module-enhanced transformer for panoramic action recognition.
Xiaoyan ZhangYujie CuiYongkai HuoPublished in: Vis. Comput. (2023)
Keyphrases
- action recognition
- deformable part models
- bag of words
- human actions
- activity recognition
- human detection
- action classification
- computer vision
- recognizing actions
- body parts
- spatial temporal
- image patches
- action detection
- field of view
- recognizing human actions
- view invariant
- video dataset
- bag of features
- stereo vision
- human pose
- depth sensors
- recognition of human actions
- action recognition in videos
- independent subspace analysis
- panoramic images
- static images
- d scene
- human activities
- machine learning