CLIP-based fusion-modal reconstructing hashing for large-scale unsupervised cross-modal retrieval.
Mingyong LiYewen LiMingyuan GeLongfei MaPublished in: Int. J. Multim. Inf. Retr. (2023)
Keyphrases
- cross modal
- multi modal
- multimedia retrieval
- image retrieval
- multimedia databases
- visual similarity
- similarity search
- data structure
- text retrieval
- content based retrieval
- visual data
- visual recognition
- semi supervised
- image understanding
- low level features
- video clips
- image database
- visual content
- supervised learning
- multimedia