MESH: A Flexible Manifold-Embedded Semantic Hashing for Cross-Modal Retrieval.
Fangming ZhongGuangze WangZhikui ChenFeng XiaPublished in: IEEE Access (2020)
Keyphrases
- cross modal
- multi modal
- multimedia retrieval
- visual similarity
- image retrieval
- semantic concepts
- multimedia databases
- visual recognition
- low dimensional
- semantic similarity
- image database
- visual features
- multimedia information retrieval
- information retrieval
- high dimensional
- visual data
- semantic content
- multimedia data
- data structure
- automatic image annotation
- low level features
- semantic gap
- video analysis
- text retrieval
- low level
- high level
- multimedia