{"total":59,"rows":[{"id":"2103.16107","title":"Large Scale Visual Food Recognition","created":"2021-03-30","cited_by_count":75,"area":null},{"id":"2103.13061","title":"Revamping Cross-Modal Recipe Retrieval with Hierarchical Transformers and Self-supervised Learning","created":"2021-03-24","cited_by_count":28,"area":null},{"id":"2402.15761","title":"Res-VMamba: Fine-Grained Food Category Visual Classification Using Selective State Space Models with Deep Residual Learning","created":"2024-02-24","cited_by_count":22,"area":"ssm"},{"id":"2307.00183","title":"Long-Tailed Continual Learning For Visual Food Recognition","created":"2023-07-01","cited_by_count":20,"area":null},{"id":"2308.14391","title":"FIRE: Food Image to REcipe generation","created":"2023-08-28","cited_by_count":18,"area":null},{"id":"2110.01209","title":"Learning Structural Representations for Recipe Generation and Food Retrieval","created":"2021-10-04","cited_by_count":17,"area":null},{"id":"2407.12843","title":"NutriBench: A Dataset for Evaluating Large Language Models on Nutrition Estimation from Meal Descriptions","created":"2024-07-04","cited_by_count":17,"area":null},{"id":"2107.06538","title":"Transformer with Peak Suppression and Knowledge Guidance for Fine-grained Image Recognition","created":"2021-07-14","cited_by_count":12,"area":null},{"id":"2205.12396","title":"Recipe2Vec: Multi-modal Recipe Representation Learning with Graph Neural Networks","created":"2022-05-24","cited_by_count":12,"area":null},{"id":"2407.12730","title":"RoDE: Linear Rectified Mixture of Diverse Experts for Food Large Multi-Modal Models","created":"2024-07-17","cited_by_count":11,"area":"mllm"},{"id":"2308.03151","title":"Food-500 Cap: A Fine-Grained Food Caption Benchmark for Evaluating Vision-Language Models","created":"2023-08-06","cited_by_count":10,"area":"mllm"},{"id":"2406.10261","title":"FoodSky: A Food-oriented Large Language Model that Passes the Chef and Dietetic Examination","created":"2024-06-11","cited_by_count":10,"area":null},{"id":"2108.02947","title":"A review on vision-based analysis for automatic dietary assessment","created":"2021-08-06","cited_by_count":9,"area":null},{"id":"2108.04644","title":"FoodLogoDet-1500: A Dataset for Large-Scale Food Logo Detection via Multi-Scale Feature Decoupling Network","created":"2021-08-10","cited_by_count":9,"area":null},{"id":"2110.12183","title":"Attend and Guide (AG-Net): A Keypoints-driven Attention-based Deep Network for Image Recognition","created":"2021-10-23","cited_by_count":9,"area":null},{"id":"2106.11776","title":"A Comprehensive Survey of Image-Based Food Recognition and Volume Estimation Methods for Dietary Assessment","created":"2021-06-21","cited_by_count":8,"area":null},{"id":"2107.05869","title":"Applications of knowledge graphs for food science and industry","created":"2021-07-13","cited_by_count":8,"area":null},{"id":"2203.05187","title":"Cluttered Food Grasping with Adaptive Fingers and Synthetic-Data Trained Object Detection","created":"2022-03-10","cited_by_count":8,"area":null},{"id":"2102.02547","title":"CHEF: Cross-modal Hierarchical Embeddings for Food Domain Retrieval","created":"2021-02-04","cited_by_count":7,"area":null},{"id":"2504.06925","title":"Are Vision-Language Models Ready for Dietary Assessment? Exploring the Next Frontier in AI-Powered Food Image Recognition","created":"2025-04-09","cited_by_count":7,"area":"mllm"},{"id":"2302.09079","title":"Advances in Automatically Rating the Trustworthiness of Text Processing Services","created":"2023-02-04","cited_by_count":6,"area":null},{"id":"2310.04689","title":"SeeDS: Semantic Separable Diffusion Synthesizer for Zero-shot Food Detection","created":"2023-10-07","cited_by_count":6,"area":"diffusion"},{"id":"2404.01409","title":"OVFoodSeg: Elevating Open-Vocabulary Food Image Segmentation via Image-Informed Textual Representation","created":"2024-04-01","cited_by_count":5,"area":null},{"id":"2505.08747","title":"Advancing Food Nutrition Estimation via Visual-Ingredient Feature Fusion","created":"2025-05-13","cited_by_count":5,"area":null},{"id":"2211.07440","title":"Leveraging Automatic Personalised Nutrition: Food Image Recognition Benchmark and Dataset based on Nutrition Taxonomy","created":"2022-11-14","cited_by_count":4,"area":null},{"id":"2501.09042","title":"CookingDiffusion: Cooking Procedural Image Generation with Stable Diffusion","created":"2025-01-15","cited_by_count":4,"area":"diffusion"},{"id":"2204.07775","title":"TASTEset -- Recipe Dataset and Food Entities Recognition Benchmark","created":"2022-04-16","cited_by_count":3,"area":null},{"id":"2309.06308","title":"AI4Food-NutritionFW: A Novel Framework for the Automatic Synthesis and Analysis of Eating Behaviours","created":"2023-09-12","cited_by_count":3,"area":null},{"id":"2402.09242","title":"Synthesizing Knowledge-enhanced Features for Real-world Zero-shot Food Detection","created":"2024-02-14","cited_by_count":3,"area":null},{"id":"2411.08715","title":"Retrieval Augmented Recipe Generation","created":"2024-11-13","cited_by_count":3,"area":"mllm"},{"id":"2103.01997","title":"Material Measurement Units for a Circular Economy: Foundations through a Review","created":"2021-03-02","cited_by_count":2,"area":null},{"id":"2106.11359","title":"Photozilla: A Large-Scale Photography Dataset and Visual Embedding for 20 Photography Styles","created":"2021-06-21","cited_by_count":2,"area":null},{"id":"2203.17109","title":"A Rich Recipe Representation as Plan to Support Expressive Multi Modal Queries on Recipe Content and Preparation Process","created":"2022-03-31","cited_by_count":2,"area":null},{"id":"2210.17235","title":"50 Ways to Bake a Cookie: Mapping the Landscape of Procedural Texts","created":"2022-10-31","cited_by_count":2,"area":null},{"id":"2306.01747","title":"UMDFood: Vision-language models boost food composition compilation","created":"2023-05-18","cited_by_count":2,"area":"mllm"},{"id":"2508.09966","title":"January Food Benchmark (JFB): A Public Benchmark Dataset and Evaluation Suite for Multimodal Food Analysis","created":"2025-08-13","cited_by_count":2,"area":null},{"id":"2604.12356","title":"OmniFood8K: Single-Image Nutrition Estimation via Hierarchical Frequency-Aligned Fusion","created":"2026-04-14","cited_by_count":2,"area":null},{"id":"2304.05041","title":"What Food Do We Tweet about on a Rainy Day?","created":"2023-04-11","cited_by_count":1,"area":null},{"id":"2305.11398","title":"Comfort Foods and Community Connectedness: Investigating Diet Change during COVID-19 Using YouTube Videos on Twitter","created":"2023-05-19","cited_by_count":1,"area":null},{"id":"2308.01813","title":"Deep Neural Networks Fused with Textures for Image Classification","created":"2023-08-03","cited_by_count":1,"area":null},{"id":"2309.01812","title":"Into the Single Cell Multiverse: an End-to-End Dataset for Procedural Knowledge Extraction in Biomedical Texts","created":"2023-09-04","cited_by_count":1,"area":null},{"id":"2403.12109","title":"GCAM: Gaussian and causal-attention model of food fine-grained recognition","created":"2024-03-18","cited_by_count":1,"area":null},{"id":"2406.09445","title":"A topological analysis of the space of recipes","created":"2024-06-12","cited_by_count":1,"area":null},{"id":"2503.05228","title":"RecipeGen: A Benchmark for Real-World Recipe Image Generation","created":"2025-03-07","cited_by_count":1,"area":null},{"id":"2510.20393","title":"Mitigating Cross-modal Representation Bias for Multicultural Image-to-Recipe Retrieval","created":"2025-10-23","cited_by_count":1,"area":null},{"id":"2110.07045","title":"Investigating Health-Aware Smart-Nudging with Machine Learning to Help People Pursue Healthier Eating-Habits","created":"2021-10-05","cited_by_count":0,"area":null},{"id":"2409.00830","title":"Building FKG.in: a Knowledge Graph for Indian Food","created":"2024-09-01","cited_by_count":0,"area":null},{"id":"2412.05248","title":"Enhancing FKG.in: automating Indian food composition analysis","created":"2024-12-06","cited_by_count":0,"area":null},{"id":"2506.06733","title":"RecipeGen: A Step-Aligned Multimodal Benchmark for Real-World Recipe Generation","created":"2025-06-07","cited_by_count":0,"area":null},{"id":"2509.03873","title":"SalientFusion: Context-Aware Compositional Zero-Shot Food Recognition","created":"2025-09-04","cited_by_count":0,"area":null},{"id":"2510.14128","title":"Building a Macedonian Recipe Dataset: Collection, Parsing, and Comparative Analysis","created":"2025-10-15","cited_by_count":0,"area":null},{"id":"2511.15201","title":"Towards Unbiased Cross-Modal Representation Learning for Food Image-to-Recipe Retrieval","created":"2025-11-19","cited_by_count":0,"area":null},{"id":"2602.18650","title":"NutriOrion: A Hierarchical Multi-Agent Framework for Personalized Nutrition Intervention Grounded in Clinical Guidelines","created":"2026-02-20","cited_by_count":0,"area":"agents"},{"id":"2607.06148","title":"RFHNet: Relational and Frequency-Aware Hashing Network for Large-Scale Fine-Grained Food Image Retrieval","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2608.03428","title":"OliveGemma: A 3 Billion Visual Language Model for Recognising the Mediterranean & European Diet","created":"2026-08-04","cited_by_count":0,"area":"mllm"},{"id":"2608.06917","title":"ReGraph: Learning to Generate Recipe Graphs from Food Images","created":"2026-08-07","cited_by_count":0,"area":"mllm"},{"id":"2609.03967","title":"Investigating the Ability of Large Language Models to Analyze Recipes for Diabetes","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.22171","title":"Quantifying Hidden Salt for Precision Healthcare: Sodium Assessment via Joint-Factor Retrieval and Chain-of-Thought Inference","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.33076","title":"NutriVision: Ingredient-Conditioned Fusion and Prediction for Single-Image Food Nutrition Estimation","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}