AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Learning Program Representations for Food Images and Cooking Recipes

Dim P. Papadopoulos, Enrique Mora, Nadiia Chepurko, Kuan Wei Huang, Ferda Ofli, Antonio Torralba

CVPR 2022 · Vision-language and multimodal › Human and embodied modeling · approach: Scene graph generation · 38 citations (OpenAlex)

Check your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (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 changedWhereMeasuredEffect
Add program prediction losses to joint image-recipe training (ablation)Image-recipe retrieval model · Recipe1M test, image-to-recipeR@1: 53.5 -> 58.6Improved
Increase encoder depth from 8 to 12 layers (ablation)Full recipe retrieval model · Recipe1M test, image-to-recipeR@1: 58.6 -> 66.9Improved
Use average-pooled ViT features instead of the CLS token (ablation)Image-recipe retrieval model · Recipe1M test, image-to-recipeR@1: 56.1 -> 58.6Improved
Increase program-loss weights from 0.1 to 1 (ablation)Image-recipe retrieval model · Recipe1M test, image-to-recipeR@1: 58.6 -> 58.0Hurt
Increase program-loss weights from 0.1 to 10 (ablation)Image-recipe retrieval model · Recipe1M test, image-to-recipeR@1: 58.6 -> 56.4Hurt
Add ingredients to the title representation (ablation)Recipe retrieval model · Recipe1M test, image-to-recipeR@1: 24.0 -> 43.6Improved
Use the full recipe rather than title and ingredients (ablation)Recipe retrieval model · Recipe1M test, image-to-recipeR@1: 43.6 -> 53.5Improved
Generate cooking programs instead of raw instruction textFood image-conditioned prediction · Food image program predictionIngredients F1: 28.5 -> 53.5Improved
Generate cooking programs instead of raw instruction textRecipe-conditioned prediction · Cooking recipe program predictionIngredients F1: 41.6 -> 75.5Improved
Use minimum cross-entropy over valid program sequences instead of standard cross-entropy (ablation)Image-conditioned program decoder · Food image program predictionFull graph GED: 72.1 -> 67.2Improved
Use minimum cross-entropy over valid program sequences instead of standard cross-entropy (ablation)Recipe-conditioned program decoder · Cooking recipe program predictionFull graph GED: 19.1 -> 16.8Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy