Research map / Vision-language and multimodal / Cross-modal learning
MCEN: Bridging Cross-Modal Gap between Cooking Recipes and Dish Images with Latent Variable Model
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 latent-variable cross-modal modeling on both modalities (ablation) | MCEN · Recipe1M 1K image-to-recipe | R@1: 44.5 -> 48.2 | Helped |
| Add latent-variable cross-modal modeling on both modalities (ablation) | MCEN · Recipe1M 1K recipe-to-image | R@1: 44.9 -> 48.4 | Helped |
| Use latent variables on the image side only rather than the recipe side only (ablation) | MCEN · Recipe1M 1K image-to-recipe | R@1: 45.8 -> 47.6 | Helped |
| Use latent variables on the image side only rather than the recipe side only (ablation) | MCEN · Recipe1M 1K recipe-to-image | R@1: 46.1 -> 47.8 | Helped |
| Add the cross-modal reconstruction component (ablation) | MCEN · Recipe1M 1K image-to-recipe | R@1: 46.4 -> 48.2 | Helped |
| Add the cross-modal reconstruction component (ablation) | MCEN · Recipe1M 1K recipe-to-image | R@1: 47.8 -> 48.4 | Helped |
| Use MCEN rather than ACME | Recipe1M 10K image-to-recipe · Recipe1M 10K | MedR: 10.0 -> 7.2 | Helped |
| Use MCEN rather than ACME | Recipe1M 10K recipe-to-image · Recipe1M 10K | MedR: 9.2 -> 6.6 | Helped |
Closest papers by meaning
- Pic2Prep: A Multimodal Conversational Agent for Cooking Assistance (AAAI 2025 · similarity 0.85)
- Guiding Cross-Modal Representations with MLLM Priors via Preference Alignment (NeurIPS 2025 · similarity 0.85)
- OVFoodSeg: Elevating Open-Vocabulary Food Image Segmentation via Image-Informed Textual Representation (CVPR 2024 · similarity 0.84)
- Same Concept, Different Directions: Cross-Modal Feature Heterogeneity in Sparse Autoencoders (NeurIPS 2026 · similarity 0.84)
- Adaptive Prompt-Based Semantic Embedding with Inspire Potential of Implicit Knowledge for Cross-Modal Retrieval (AAAI 2025 · similarity 0.84)
- Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion (ICLR 2025 · similarity 0.84)
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.