Exploring Rich Semantics for Open-Set Action Recognition.
Yufan HuJunyu GaoJianfeng DongBin FanHongmin LiuPublished in: IEEE Trans. Multim. (2024)
Keyphrases
- action recognition
- human actions
- bag of words
- spatial temporal
- activity recognition
- action classification
- human detection
- body parts
- recognizing human actions
- computer vision
- mid level
- view invariant
- static images
- machine learning
- independent subspace analysis
- view invariant action recognition
- multiple views
- pose estimation
- human pose
- image retrieval
- video dataset
- three dimensional
- recognition of human actions
- action recognition in videos