AMMD: Attentive maximum mean discrepancy for few-shot image classification.
Ji WuShipeng WangJian SunPublished in: Pattern Recognit. (2024)
Keyphrases
- image classification
- visual features
- bag of words
- image representation
- video sequences
- image features
- feature extraction
- bag of features
- class specific
- sparse representation
- sparse coding
- visual attention
- video data
- key frames
- visual information
- video shots
- focus of attention
- visual motion
- data sets
- video segmentation
- video content
- feature selection