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: CoRR (2020)
Keyphrases
- cross modal
- perceptual information
- image database
- multi modal
- image retrieval
- image data
- visual similarity
- visual recognition
- object recognition
- input image
- multimedia retrieval
- image classification
- content based retrieval
- high level
- attention mechanism
- multimedia databases
- image regions
- image features
- semantic gap
- image annotation
- visual concepts
- image content
- active learning
- multimedia