Self-Attentive CLIP Hashing for Unsupervised Cross-Modal Retrieval.
Heng YuShuyan DingLunbo LiJiexin WuPublished in: MMAsia (2022)
Keyphrases
- cross modal
- multi modal
- multimedia retrieval
- multimedia databases
- image retrieval
- visual similarity
- similarity search
- multimedia
- visual data
- visual recognition
- supervised learning
- data structure
- information retrieval systems
- multimedia information retrieval
- semi supervised
- image database
- retrieval systems
- low level features
- object recognition