Parameter-efficient tuning of cross-modal retrieval for a specific database via trainable textual and visual prompts.
Huaying ZhangRintaro YanagiRen TogoTakahiro OgawaMiki HaseyamaPublished in: Int. J. Multim. Inf. Retr. (2024)
Keyphrases
- cross modal
- database
- multi modal
- multimedia retrieval
- visual similarity
- image retrieval
- multimedia databases
- visual recognition
- perceptual information
- indexing structure
- databases
- visual data
- database management systems
- database systems
- indexing techniques
- multimedia
- text retrieval
- multimedia data
- visual information
- image content
- metadata