CAESAR: concept augmentation based semantic representation for cross-modal retrieval.
Lei ZhuJiayu SongXiangxiang WeiHao YuJun LongPublished in: Multim. Tools Appl. (2022)
Keyphrases
- cross modal
- semantic representation
- multi modal
- visual similarity
- semantic representations
- multimedia retrieval
- natural language
- image retrieval
- semantic concepts
- conceptual graphs
- visual recognition
- multimedia databases
- image database
- low level
- multimedia information retrieval
- data mining
- visual concepts
- visual information
- visual data
- visual content
- retrieval model
- document retrieval
- image classification
- relevance feedback
- information extraction
- image data
- high level
- multimedia
- information retrieval