Cross-Modal Retrieval in the Cooking Context: Learning Semantic Text-Image Embeddings.
Micael CarvalhoRémi CadèneDavid PicardLaure SoulierNicolas ThomeMatthieu CordPublished in: SIGIR (2018)
Keyphrases
- cross modal
- image retrieval
- visual similarity
- perceptual information
- image classification
- image representation
- image features
- semantic content
- visual recognition
- image content
- image database
- image data
- visual concepts
- high level
- information retrieval
- low level features
- visual data
- contextual information
- retrieval systems
- vector space
- web images
- information retrieval systems
- multimedia retrieval
- feature extraction