Cross-modal Recipe Retrieval with Hierarchical Transformers and Pretrained Food Image Encoder.
Hanyan QinXiankun ZhangChen SongPublished in: ICIC (LNAI 5) (2024)
Keyphrases
- cross modal
- image retrieval
- visual similarity
- image content
- image data
- multi modal
- visual data
- image features
- image representation
- image collections
- image database
- image segmentation
- multimedia retrieval
- image classification
- multiscale
- perceptual information
- relevance feedback
- spatial information
- multimedia databases
- information retrieval systems
- information retrieval
- document retrieval
- image regions
- similarity measure
- feature space
- key frames
- image annotation
- keywords
- content based retrieval
- visual content
- high level
- test collection
- visual features