Semantic-aware Video Representation for Few-shot Action Recognition.
Yutao TangBenjamín BéjarRené VidalPublished in: CoRR (2023)
Keyphrases
- video representation
- action recognition
- video database
- key frames
- video shots
- video content
- human actions
- video data
- spatio temporal
- bag of words
- video analysis
- video sequences
- video streams
- activity recognition
- video retrieval
- computer vision
- video clips
- body parts
- space time
- low level features
- feature vectors
- video objects
- visual features
- video frames
- visual content
- generative model
- mid level
- visual words
- temporal information
- bag of features
- human activities
- image features
- low level
- object recognition