Look, Imagine and Match: Improving Textual-Visual Cross-Modal Retrieval with Generative Models.
Jiuxiang GuJianfei CaiShafiq R. JotyLi NiuGang WangPublished in: CoRR (2017)
Keyphrases
- cross modal
- generative model
- multi modal
- multimedia retrieval
- visual similarity
- probabilistic model
- image retrieval
- multimedia databases
- visual data
- em algorithm
- prior knowledge
- visual features
- multimedia
- keywords
- semi supervised
- visual content
- multimedia data
- object categories
- computer vision
- text retrieval
- expectation maximization
- information retrieval
- image database
- relevance feedback
- high dimensional
- object recognition