Multiscale Matching Driven by Cross-Modal Similarity Consistency for Audio-Text Retrieval.
Qian WangJia-Chen GuZhen-Hua LingPublished in: ICASSP (2024)
Keyphrases
- cross modal
- text retrieval
- multimedia retrieval
- multiscale
- image retrieval
- multi modal
- visual similarity
- multimedia information retrieval
- similarity measure
- image representation
- document retrieval
- visual data
- information retrieval
- query expansion
- keypoints
- retrieval systems
- document collections
- image processing
- retrieval model
- image database
- visual recognition
- visual information
- multimedia databases
- distance measure
- semantic similarity
- automatic image annotation
- keywords
- database systems
- learning algorithm