Research map / Vision-language and multimodal / Cross-modal learning
Learning Cross-Modal Embeddings for Cooking Recipes and Food Images
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add semantic regularization to the joint embedding (ablation) | ResNet-50 joint embedding · im2recipe test | medR: 7.2 to 5.2 | Helped |
| add semantic regularization to the joint embedding (ablation) | ResNet-50 joint embedding · recipe2im test | medR: 6.9 to 5.1 | Helped |
| replace CCA with the learned joint neural embedding | im2recipe retrieval · im2recipe test | medR: 15.7 -> 5.2 | Helped |
| replace CCA with the learned joint neural embedding | recipe2im retrieval · recipe2im test | medR: 24.8 -> 5.1 | Helped |
| finetune the vision network rather than keep it fixed (ablation) | ResNet-50 joint embedding · im2recipe, 1K retrieval | medR-1K: 7.9 -> 7.2 | Helped |
| finetune the vision network rather than keep it fixed (ablation) | ResNet-50 joint embedding · recipe2im, 1K retrieval | medR-1K: 9.3 -> 6.9 | Helped |
| add semantic regularization (ablation) | ResNet-50 finetuned joint embedding · im2recipe, 1K retrieval | medR-1K: 7.2 -> 5.2 | Helped |
| add semantic regularization (ablation) | ResNet-50 finetuned joint embedding · recipe2im, 1K retrieval | medR-1K: 6.9 -> 5.1 | Helped |
| replace VGG-16 image features with ResNet-50 features (ablation) | joint embedding with fixed vision · im2recipe, 1K retrieval | medR-1K: 15.3 -> 7.9 | Helped |
| replace VGG-16 image features with ResNet-50 features (ablation) | joint embedding with fixed vision · recipe2im, 1K retrieval | medR-1K: 16.4 -> 9.3 | Helped |
| add semantic regularization (ablation) | VGG-16 finetuned joint embedding · im2recipe, 1K retrieval | medR-1K: 12.1 -> 8.2 | Helped |
| add semantic regularization (ablation) | VGG-16 finetuned joint embedding · recipe2im, 1K retrieval | medR-1K: 10.5 -> 7.3 | Helped |
Closest papers by meaning
- CHEF: Cross-modal Hierarchical Embeddings for Food Domain Retrieval (AAAI 2021 · similarity 0.94)
- Revamping Cross-Modal Recipe Retrieval With Hierarchical Transformers and Self-Supervised Learning (CVPR 2021 · similarity 0.94)
- Learning Cross-Modal Embeddings With Adversarial Networks for Cooking Recipes and Food Images (CVPR 2019 · similarity 0.92)
- MCEN: Bridging Cross-Modal Gap between Cooking Recipes and Dish Images with Latent Variable Model (CVPR 2020 · similarity 0.92)
- OVFoodSeg: Elevating Open-Vocabulary Food Image Segmentation via Image-Informed Textual Representation (CVPR 2024 · similarity 0.88)
- Pic2Prep: A Multimodal Conversational Agent for Cooking Assistance (AAAI 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.