Joint Image-Text Representation by Gaussian Visual-Semantic Embedding.
Zhou RenHailin JinZhe L. LinChen FangAlan L. YuillePublished in: ACM Multimedia (2016)
Keyphrases
- text representation
- low level
- image classification
- image features
- multiscale
- image representation
- image content
- image retrieval
- text documents
- concept learning
- domain knowledge
- vector space
- similarity measure
- image segmentation
- visual features
- information retrieval
- word sense disambiguation
- vector space model
- machine learning
- language model
- data mining
- data analysis
- natural language
- high level
- computer vision