Research map / Vision-language and multimodal / Cross-modal learning
Multi-Modal Multi-Task Learning for Automatic Dietary Assessment
Read the paperCheck 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 meal rating task to BRNN (BRNN+mr) | BRNN · test | ROUGE-1: 0.247 -> 0.258 | Helped |
| add meal rating task to SAT (SAT+mr) | SAT · test | ROUGE-1: 0.263 -> 0.274 | Helped |
| add description and user features to BRNN+mr (BRNN+all) | BRNN+mr · test | MAE: 0.473 -> 0.458 | Helped |
| add description and user features to SAT+mr (SAT+all) | SAT+mr · test | MAE: 0.462 -> 0.442 | Helped |
| replace BRNN with attention (SAT) | BRNN · test | ROUGE-1: 0.247 -> 0.263 | Helped |
| add attention over images and texts (MMDA-mem vs MMDA-att-mem) (ablation) | MMDA · test | MAE: 0.452 -> 0.424 | Helped |
| add attention over images and texts (MMDA-mem vs MMDA-att-mem) (ablation) | MMDA · test | ROUGE-1: 0.265 -> 0.285 | Helped |
| add memory network over historical meals (MMDA vs MMDA-mem) (ablation) | MMDA · test | MAE: 0.424 -> 0.387 | Helped |
| add memory network over historical meals (MMDA vs MMDA-mem) (ablation) | MMDA · test | ROUGE-1: 0.285 -> 0.335 | Helped |
| add comment prediction task (MMDA vs MMDA-mc) (ablation) | MMDA · test | MAE: 0.403 -> 0.387 | Helped |
| add rating prediction task (MMDA vs MMDA-mr) (ablation) | MMDA · test | ROUGE-1: 0.317 -> 0.335 | Helped |
| increase loss weight lambda from small values up to 0.1 (ablation) | MMDA · dev | MAE | Helped |
Closest papers by meaning
- CHEF: Cross-modal Hierarchical Embeddings for Food Domain Retrieval (AAAI 2021 · similarity 0.87)
- Learning Cross-Modal Embeddings for Cooking Recipes and Food Images (CVPR 2017 · similarity 0.87)
- Pic2Prep: A Multimodal Conversational Agent for Cooking Assistance (AAAI 2025 · similarity 0.87)
- OVFoodSeg: Elevating Open-Vocabulary Food Image Segmentation via Image-Informed Textual Representation (CVPR 2024 · similarity 0.83)
- NutriBench: A Dataset for Evaluating Large Language Models in Nutrition Estimation from Meal Descriptions (ICLR 2025 · similarity 0.83)
- L-Man: A Large Multi-modal Model Unifying Human-centric Tasks (AAAI 2025 · similarity 0.81)
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.