Transformer-Based Discriminative and Strong Representation Deep Hashing for Cross-Modal Retrieval.
Suqing ZhouYu HanNing ChenSiyu HuangKostromitin Konstantin IgorevichJia LuoPeiying ZhangPublished in: IEEE Access (2023)
Keyphrases
- cross modal
- multi modal
- perceptual information
- multimedia retrieval
- image retrieval
- visual similarity
- multimedia databases
- visual data
- information retrieval
- visual recognition
- image representation
- content based retrieval
- multimedia information retrieval
- visual features
- action recognition
- semantic information
- visual content
- information retrieval systems
- image database