Hugs Are Better Than Handshakes: Unsupervised Cross-Modal Transformer Hashing with Multi-granularity Alignment.
Jinpeng WangZiyun ZengBin ChenYuting WangDongliang LiaoGongfu LiYiru WangShu-Tao XiaPublished in: BMVC (2022)
Keyphrases
- cross modal
- multi granularity
- multi modal
- multi user
- dynamic integration
- multimedia retrieval
- visual recognition
- location aware
- privacy protection
- semi supervised
- multimedia databases
- supervised learning
- visual similarity
- data structure
- similarity search
- visual data
- image classification
- data sets
- multimedia data
- seamless integration
- learning algorithm