Cross-Modal Food Retrieval: Learning a Joint Embedding of Food Images and Recipes With Semantic Consistency and Attention Mechanism.
Hao WangDoyen SahooChenghao LiuKe ShuPalakorn AchananuparpEe-Peng LimSteven C. H. HoiPublished in: IEEE Trans. Multim. (2022)
Keyphrases
- cross modal
- perceptual information
- image retrieval
- image database
- visual similarity
- image data
- multi modal
- active learning
- image features
- object recognition
- input image
- visual recognition
- content based retrieval
- multimedia retrieval
- information retrieval
- image classification
- attention mechanism
- semantic information
- visual concepts
- multimedia databases
- image collections
- test collection
- similarity measure