Token Embeddings Alignment for Cross-Modal Retrieval.
Chen-Wei XieJianmin WuYun ZhengPan PanXian-Sheng HuaPublished in: ACM Multimedia (2022)
Keyphrases
- cross modal
- multi modal
- multimedia retrieval
- image retrieval
- multimedia databases
- visual similarity
- visual recognition
- visual data
- perceptual information
- text retrieval
- semantic similarity
- multimedia information retrieval
- multimedia
- high dimensional data
- visual features
- query expansion
- high dimensional
- feature space