GeoDeformer: Geometric Deformable Transformer for Action Recognition.
Jinhui YeJiaming ZhouHui XiongJunwei LiangPublished in: CoRR (2023)
Keyphrases
- action recognition
- deformable part models
- human actions
- activity recognition
- bag of words
- human detection
- spatial temporal
- computer vision
- recognition of human actions
- body parts
- action classification
- action primitives
- geometric structure
- mid level
- view invariant
- bag of features
- recognizing actions
- video dataset
- static images
- human activities
- action detection
- view invariant action recognition
- depth sensors
- visual words
- recognizing human actions