DCMA-Net: dual cross-modal attention for fine-grained few-shot recognition.
Yan ZhouXiao RenJianxun LiYin YangHaibin ZhouPublished in: Multim. Tools Appl. (2024)
Keyphrases
- fine grained
- cross modal
- visual recognition
- multi modal
- coarse grained
- multimedia retrieval
- access control
- object recognition
- image retrieval
- action recognition
- multimedia databases
- visual data
- video sequences
- feature extraction
- information retrieval
- visual similarity
- data lineage
- multimedia information retrieval
- activity recognition
- co occurrence