Semantic-aware Video Representation for Few-shot Action Recognition.
Yutao TangBenjamín BéjarRené VidalPublished in: WACV (2024)
Keyphrases
- action recognition
- video representation
- video database
- key frames
- video shots
- video content
- video data
- human actions
- spatio temporal
- video sequences
- space time
- bag of words
- video streams
- video analysis
- activity recognition
- video retrieval
- computer vision
- video clips
- visual features
- video objects
- feature vectors
- video frames
- visual content
- dynamic textures
- mid level
- low level features
- motion patterns
- bag of features
- machine learning
- keywords
- body parts
- multiscale
- generative model