Research map / Vision-language and multimodal / Cross-modal learning
Learning Cross-Modal Embeddings With Adversarial Networks 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 hard-sample mining to triplet loss (ablation) | Recipe1M cross-modal retrieval · Recipe1M image-to-recipe | R@1: 25.9 -> 47.5 | Helped |
| add modality alignment (ablation) | TL+HM · Recipe1M image-to-recipe | R@1: 47.5 -> 48.0 | Helped |
| add recipe-to-image translation (ablation) | TL+HM+MA · Recipe1M image-to-recipe | R@1: 48.0 -> 50.0 | Helped |
| add image-to-recipe translation (ablation) | TL+HM+MA · Recipe1M image-to-recipe | R@1: 48.0 -> 49.3 | Helped |
| add modality alignment to the model with both translation components (ablation) | TL+HM+R2I+I2R · Recipe1M image-to-recipe | R@1: 49.5 -> 51.8 | Helped |
| combine hard-sample mining, modality alignment, and cross-modal translation with triplet loss | ACME · Recipe1M 10k image-to-recipe | MedR: 13.2 -> 6.7 | Helped |
| combine hard-sample mining, modality alignment, and cross-modal translation with triplet loss | ACME · Recipe1M 10k recipe-to-image | R@1: 14.8 -> 24.4 | Helped |
| use modality alignment with hard mining and translation objectives (ablation) | ACME · Recipe1M image-to-recipe | R@1: 49.5 -> 51.8 | Helped |
Closest papers by meaning
- CHEF: Cross-modal Hierarchical Embeddings for Food Domain Retrieval (AAAI 2021 · similarity 0.94)
- MCEN: Bridging Cross-Modal Gap between Cooking Recipes and Dish Images with Latent Variable Model (CVPR 2020 · similarity 0.93)
- Learning Cross-Modal Embeddings for Cooking Recipes and Food Images (CVPR 2017 · similarity 0.92)
- Revamping Cross-Modal Recipe Retrieval With Hierarchical Transformers and Self-Supervised Learning (CVPR 2021 · similarity 0.91)
- Pic2Prep: A Multimodal Conversational Agent for Cooking Assistance (AAAI 2025 · similarity 0.86)
- OVFoodSeg: Elevating Open-Vocabulary Food Image Segmentation via Image-Informed Textual Representation (CVPR 2024 · similarity 0.85)
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.