Unsupervised multi-perspective fusing semantic alignment for cross-modal hashing retrieval.
Yongfeng ChenJunpeng TanZhijing YangYukai ShiJinghui QinPublished in: Multim. Tools Appl. (2024)
Keyphrases
- cross modal
- multi perspective
- multi modal
- multimedia retrieval
- visual similarity
- semantic concepts
- image retrieval
- multimedia databases
- d scene
- visual recognition
- semantic similarity
- visual data
- semi supervised
- semantic content
- image annotation
- content based retrieval
- text retrieval
- data structure
- web pages
- low level features
- document retrieval
- similarity search
- relevance feedback
- image sequences