Look, Imagine and Match: Improving Textual-Visual Cross-Modal Retrieval With Generative Models.
Jiuxiang GuJianfei CaiShafiq R. JotyLi NiuGang WangPublished in: CVPR (2018)
Keyphrases
- cross modal
- generative model
- multi modal
- visual similarity
- image retrieval
- multimedia retrieval
- probabilistic model
- multimedia databases
- prior knowledge
- visual content
- semi supervised
- multimedia
- object categories
- em algorithm
- visual data
- keywords
- visual features
- web images
- image search
- semantic similarity
- image content
- expectation maximization