Towards Bridging the Cross-modal Semantic Gap for Multi-modal Recommendation.
Xinglong WuAnfeng HuangHongwei YangHui HeYu TaiWeizhe ZhangPublished in: CoRR (2024)
Keyphrases
- multi modal
- cross modal
- semantic gap
- semantic concepts
- image annotation
- video retrieval
- low level
- low level features
- multimedia databases
- automatic image annotation
- visual content
- high dimensional
- image content
- semantic information
- visual features
- visual concepts
- image search
- multimedia data
- visual information
- web images
- feature vectors
- high level
- multiple modalities