CoVLR: Coordinating Cross-Modal Consistency and Intra-Modal Structure for Vision-Language Retrieval.
Yang YangZhongtian FuXiangyu WuWenjie LiPublished in: CoRR (2023)
Keyphrases
- cross modal
- multi modal
- multimedia retrieval
- image retrieval
- visual recognition
- multimedia databases
- computer vision
- visual similarity
- image database
- test collection
- retrieval systems
- text retrieval
- multimedia information retrieval
- information retrieval
- information retrieval systems
- xml documents
- high dimensional
- indexing structure
- keywords
- multimedia