MCEN: Bridging Cross-Modal Gap between Cooking Recipes and Dish Images with Latent Variable Model.
Han FuRui WuChenghao LiuJianling SunPublished in: CVPR (2020)
Keyphrases
- cross modal
- image data
- image database
- image retrieval
- latent variable models
- visual data
- image regions
- image classification
- multi modal
- image collections
- visual similarity
- image features
- object recognition
- test images
- learning tasks
- latent variables
- image annotation
- content based retrieval
- visual concepts
- multimedia retrieval