MSSPQ: Multiple Semantic Structure-Preserving Quantization for Cross-Modal Retrieval.
Lei ZhuLiewu CaiJiayu SongXinghui ZhuChengyuan ZhangShichao ZhangPublished in: ICMR (2022)
Keyphrases
- cross modal
- structure preserving
- multi modal
- multimedia retrieval
- image retrieval
- visual similarity
- visual recognition
- high level
- information retrieval systems
- text retrieval
- multimedia databases
- semantic concepts
- semantic content
- visual data
- semantic information
- semantic similarity
- image database
- multi label
- retrieval model
- co occurrence
- low level
- query processing
- information retrieval