TFRS: A task-level feature rectification and separation method for few-shot video action recognition.
Yanfei QinBaolin LiuPublished in: Neural Networks (2024)
Keyphrases
- action recognition
- motion features
- spatio temporal interest points
- human detection
- human actions
- action classification
- computer vision
- video data
- key frames
- video database
- spatial temporal
- multimedia
- action detection
- bag of words
- machine learning
- video shots
- visual features
- video sequences
- independent subspace analysis