Multi-dataset Training of Transformers for Robust Action Recognition.
Junwei LiangEnwei ZhangJun ZhangChunhua ShenPublished in: CoRR (2022)
Keyphrases
- action recognition
- human actions
- view invariant
- bag of words
- activity recognition
- ucf sports
- action classification
- human detection
- computer vision
- space time interest points
- recognizing human actions
- body parts
- static images
- action recognition in videos
- video dataset
- recognizing actions
- bag of features
- recognition of human actions
- spatial temporal
- independent subspace analysis
- human activities
- spatio temporal
- training set
- three dimensional
- depth information
- action detection