Finding beans in burgers: Deep semantic-visual embedding with localization.
Martin EngilbergeLouis ChevallierPatrick PérezMatthieu CordPublished in: CoRR (2018)
Keyphrases
- high level
- semantic web
- semantic space
- visual concepts
- semantic content
- visual information
- vector space
- semantic information
- low level
- natural language
- visual features
- semantic network
- image retrieval
- semantic knowledge
- image quality
- web applications
- domain specific
- semantic annotation
- semantic similarity
- visual perception
- object localization
- semantic description
- face recognition