Layered Hypernetwork Models for Cross-Modal Associative Text and Image Keyword Generation in Multimodal Information Retrieval.
JungWoo HaByoung-Hee KimBado LeeByoung-Tak ZhangPublished in: PRICAI (2010)
Keyphrases
- cross modal
- information retrieval
- image retrieval
- multi modal
- visual similarity
- multiple modalities
- web images
- image data
- image classification
- text retrieval
- image content
- text mining
- multimedia retrieval
- multiscale
- keywords
- image representation
- visual data
- perceptual information
- low level
- image features
- test images
- search engine
- visual recognition
- image database
- information extraction
- image collections
- spatial relationships
- multimedia databases
- test collection
- visual features
- query expansion
- object detection
- high level
- multimedia