{"total":118,"rows":[{"id":"2103.16107","title":"Large Scale Visual Food Recognition","created":"2021-03-30","cited_by_count":75,"area":null},{"id":"2212.12672","title":"Real or Fake Text?: Investigating Human Ability to Detect Boundaries Between Human-Written and Machine-Generated Text","created":"2022-12-24","cited_by_count":63,"area":null},{"id":"2103.03375","title":"Nutrition5k: Towards Automatic Nutritional Understanding of Generic Food","created":"2021-03-04","cited_by_count":58,"area":null},{"id":"2105.05409","title":"A Large-Scale Benchmark for Food Image Segmentation","created":"2021-05-12","cited_by_count":45,"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":"2109.04711","title":"Pre-train or Annotate? Domain Adaptation with a Constrained Budget","created":"2021-09-10","cited_by_count":27,"area":null},{"id":"2103.07562","title":"Towards Learning Food Portion From Monocular Images With Cross-Domain Feature Adaptation","created":"2021-03-12","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":"2412.08847","title":"MOPI-HFRS: A Multi-objective Personalized Health-aware Food Recommendation System with LLM-enhanced Interpretation","created":"2024-12-12","cited_by_count":18,"area":null},{"id":"2101.01775","title":"Personalized Food Recommendation as Constrained Question Answering over a Large-scale Food Knowledge Graph","created":"2021-01-05","cited_by_count":17,"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":"2203.16071","title":"Learning Program Representations for Food Images and Cooking Recipes","created":"2022-03-30","cited_by_count":16,"area":null},{"id":"2105.08185","title":"SHARE: a System for Hierarchical Assistive Recipe Editing","created":"2021-05-17","cited_by_count":15,"area":null},{"id":"2106.08408","title":"Seeing Through Clouds in Satellite Images","created":"2021-06-15","cited_by_count":13,"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":"2103.01910","title":"MultiSubs: A Large-scale Multimodal and Multilingual Dataset","created":"2021-03-02","cited_by_count":10,"area":null},{"id":"2104.06806","title":"Continual learning in cross-modal retrieval","created":"2021-04-14","cited_by_count":10,"area":null},{"id":"2106.03158","title":"Transferring Knowledge from Text to Video: Zero-Shot Anticipation for Procedural Actions","created":"2021-06-06","cited_by_count":10,"area":null},{"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":"2312.08592","title":"Dietary Assessment with Multimodal ChatGPT: A Systematic Analysis","created":"2023-12-14","cited_by_count":10,"area":null},{"id":"2405.16996","title":"Mitigating Noisy Correspondence by Geometrical Structure Consistency Learning","created":"2024-05-27","cited_by_count":10,"area":null},{"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":"2605.27295","title":"Gemini Embedding 2: A Native Multimodal Embedding Model from Gemini","created":"2026-05-26","cited_by_count":10,"area":null},{"id":"2309.09181","title":"From Cooking Recipes to Robot Task Trees -- Improving Planning Correctness and Task Efficiency by Leveraging LLMs with a Knowledge Network","created":"2023-09-17","cited_by_count":9,"area":null},{"id":"2310.08312","title":"GePSAn: Generative Procedure Step Anticipation in Cooking Videos","created":"2023-10-12","cited_by_count":9,"area":null},{"id":"2410.14045","title":"Human Action Anticipation: A Survey","created":"2024-10-17","cited_by_count":9,"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":"2110.11592","title":"Learning Text-Image Joint Embedding for Efficient Cross-Modal Retrieval with Deep Feature Engineering","created":"2021-10-22","cited_by_count":8,"area":null},{"id":"2302.07960","title":"Learning to Substitute Ingredients in Recipes","created":"2023-02-15","cited_by_count":8,"area":null},{"id":"2504.09277","title":"SynthTRIPs: A Knowledge-Grounded Framework for Benchmark Query Generation for Personalized Tourism Recommenders","created":"2025-04-12","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":"2107.00372","title":"Egocentric Image Captioning for Privacy-Preserved Passive Dietary Intake Monitoring","created":"2021-07-01","cited_by_count":7,"area":null},{"id":"2204.01061","title":"Task2Dial: A Novel Task and Dataset for Commonsense enhanced Task-based Dialogue Grounded in Documents","created":"2022-04-03","cited_by_count":7,"area":null},{"id":"2310.17353","title":"Cultural Adaptation of Recipes","created":"2023-10-26","cited_by_count":7,"area":null},{"id":"2402.10175","title":"Unlocking Structure Measuring: Introducing PDD, an Automatic Metric for Positional Discourse Coherence","created":"2024-02-15","cited_by_count":7,"area":null},{"id":"2505.09777","title":"A Survey on Large Language Models in Multimodal Recommender Systems","created":"2025-05-14","cited_by_count":7,"area":null},{"id":"2601.18106","title":"GLEN-Bench: A Graph-Language based Benchmark for Nutritional Health","created":"2026-01-26","cited_by_count":7,"area":null},{"id":"2204.09730","title":"Transformer Decoders with MultiModal Regularization for Cross-Modal Food Retrieval","created":"2022-04-20","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":"2401.07868","title":"Consolidating Trees of Robotic Plans Generated Using Large Language Models to Improve Reliability","created":"2024-01-15","cited_by_count":6,"area":null},{"id":"2212.05093","title":"Plug-and-Play Recipe Generation with Content Planning","created":"2022-12-09","cited_by_count":5,"area":null},{"id":"2304.02016","title":"The Multimodal And Modular Ai Chef: Complex Recipe Generation From Imagery","created":"2023-03-20","cited_by_count":5,"area":null},{"id":"2306.09203","title":"Transferring Knowledge for Food Image Segmentation using Transformers and Convolutions","created":"2023-06-15","cited_by_count":5,"area":null},{"id":"2307.16081","title":"Roll Up Your Sleeves: Working with a Collaborative and Engaging Task-Oriented Dialogue System","created":"2023-07-29","cited_by_count":5,"area":null},{"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":"2407.15239","title":"Benchmark Granularity and Model Robustness for Image-Text Retrieval","created":"2024-07-21","cited_by_count":5,"area":"mllm"},{"id":"2412.04189","title":"HANDI: Hand-Centric Text-and-Image Conditioned Video Generation","created":"2024-12-05","cited_by_count":5,"area":null},{"id":"2108.03788","title":"Learning Joint Embedding with Modality Alignments for Cross-Modal Retrieval of Recipes and Food Images","created":"2021-08-09","cited_by_count":4,"area":null},{"id":"2110.02035","title":"FooDI-ML: a large multi-language dataset of food, drinks and groceries images and descriptions","created":"2021-10-05","cited_by_count":4,"area":null},{"id":"2206.02086","title":"Towards the Creation of a Nutrition and Food Group Based Image Database","created":"2022-06-05","cited_by_count":4,"area":null},{"id":"2206.08267","title":"Ratatouille: A tool for Novel Recipe Generation","created":"2022-05-10","cited_by_count":4,"area":null},{"id":"2210.10628","title":"RecipeMind: Guiding Ingredient Choices from Food Pairing to Recipe Completion using Cascaded Set Transformer","created":"2022-10-14","cited_by_count":4,"area":null},{"id":"2412.09936","title":"CaLoRAify: Calorie Estimation with Visual-Text Pairing and LoRA-Driven Visual Language Models","created":"2024-12-13","cited_by_count":4,"area":"mllm"},{"id":"2204.07775","title":"TASTEset -- Recipe Dataset and Food Entities Recognition Benchmark","created":"2022-04-16","cited_by_count":3,"area":null},{"id":"2211.14451","title":"GLAMI-1M: A Multilingual Image-Text Fashion Dataset","created":"2022-11-17","cited_by_count":3,"area":null},{"id":"2401.05199","title":"Monte Carlo Tree Search for Recipe Generation using GPT-2","created":"2024-01-10","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":"2501.14991","title":"Advances in Set Function Learning: A Survey of Techniques and Applications","created":"2025-01-24","cited_by_count":3,"area":null},{"id":"2502.02067","title":"AdaptBot: Combining LLM with Knowledge Graphs and Human Input for Generic-to-Specific Task Decomposition and Knowledge Refinement","created":"2025-02-04","cited_by_count":3,"area":null},{"id":"2504.20643","title":"Cooking Up Creativity: Enhancing LLM Creativity through Structured Recombination","created":"2025-04-29","cited_by_count":3,"area":null},{"id":"2202.00712","title":"Should I take a walk? Estimating Energy Expenditure from Video Data","created":"2022-02-01","cited_by_count":2,"area":null},{"id":"2203.15778","title":"Text-Driven Video Acceleration: A Weakly-Supervised Reinforcement Learning Method","created":"2022-03-29","cited_by_count":2,"area":null},{"id":"2211.01824","title":"Human in the loop approaches in multi-modal conversational task guidance system development","created":"2022-11-03","cited_by_count":2,"area":null},{"id":"2304.10739","title":"KitchenScale: Learning to predict ingredient quantities from recipe contexts","created":"2023-04-21","cited_by_count":2,"area":null},{"id":"2306.13986","title":"Large Language Models as Sous Chefs: Revising Recipes with GPT-3","created":"2023-06-24","cited_by_count":2,"area":null},{"id":"2309.07704","title":"NutritionVerse: Empirical Study of Various Dietary Intake Estimation Approaches","created":"2023-09-14","cited_by_count":2,"area":null},{"id":"2404.04676","title":"Order-Based Pre-training Strategies for Procedural Text Understanding","created":"2024-04-06","cited_by_count":2,"area":null},{"id":"2405.00523","title":"CookingSense: A Culinary Knowledgebase with Multidisciplinary Assertions","created":"2024-05-01","cited_by_count":2,"area":null},{"id":"2409.18459","title":"FoodMLLM-JP: Leveraging Multimodal Large Language Models for Japanese Recipe Generation","created":"2024-09-27","cited_by_count":2,"area":"mllm"},{"id":"2409.19074","title":"Show and Guide: Instructional-Plan Grounded Vision and Language Model","created":"2024-09-27","cited_by_count":2,"area":null},{"id":"2507.03330","title":"Exploring Object Status Recognition for Recipe Progress Tracking in Non-Visual Cooking","created":"2025-07-04","cited_by_count":2,"area":null},{"id":"2507.04412","title":"SFOOD: A Multimodal Benchmark for Comprehensive Food Attribute Analysis Beyond RGB with Spectral Insights","created":"2025-07-06","cited_by_count":2,"area":null},{"id":"2507.23135","title":"ISO-Bench: Benchmarking Multimodal Causal Reasoning in Visual-Language Models through Procedural Plans","created":"2025-07-30","cited_by_count":2,"area":"lr"},{"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":"2511.09483","title":"CrochetBench: Can Vision-Language Models Move from Describing to Doing in Crochet Domain?","created":"2025-11-12","cited_by_count":2,"area":"mllm"},{"id":"2512.01077","title":"ELR-1000: A Community-Generated Dataset for Endangered Indic Indigenous Languages","created":"2025-11-30","cited_by_count":2,"area":null},{"id":"2601.04491","title":"A Closed-Loop Multi-Agent System Driven by LLMs for Meal-Level Personalized Nutrition Management","created":"2026-01-08","cited_by_count":2,"area":null},{"id":"2604.22776","title":"Epicure: Multidimensional Flavor Structure in Food Ingredient Embeddings","created":"2026-04-02","cited_by_count":2,"area":null},{"id":"2112.02433","title":"Functional Task Tree Generation from a Knowledge Graph to Solve Unseen Problems","created":"2021-12-04","cited_by_count":1,"area":null},{"id":"2210.06618","title":"QMRNet: Quality Metric Regression for EO Image Quality Assessment and Super-Resolution","created":"2022-10-12","cited_by_count":1,"area":null},{"id":"2305.11327","title":"MALM: Mask Augmentation based Local Matching for Food-Recipe Retrieval","created":"2023-05-18","cited_by_count":1,"area":"distill"},{"id":"2312.12299","title":"Instruct-SCTG: Guiding Sequential Controlled Text Generation through Instructions","created":"2023-12-19","cited_by_count":1,"area":null},{"id":"2402.07477","title":"Food Recommendation as Language Processing (F-RLP): A Personalized and Contextual Paradigm","created":"2024-02-12","cited_by_count":1,"area":null},{"id":"2403.17426","title":"Knowledge-Powered Recommendation for an Improved Diet Water Footprint","created":"2024-03-26","cited_by_count":1,"area":null},{"id":"2408.13358","title":"Shape-Preserving Generation of Food Images for Automatic Dietary Assessment","created":"2024-08-23","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":"2505.21068","title":"Predicting Implicit Arguments in Procedural Video Instructions","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2509.06006","title":"Khana: A Comprehensive Indian Cuisine Dataset","created":"2025-09-07","cited_by_count":1,"area":null},{"id":"2511.20525","title":"Mistake Attribution: Fine-Grained Mistake Understanding in Egocentric Videos","created":"2025-11-25","cited_by_count":1,"area":null},{"id":"2512.03540","title":"CookAnything: A Framework for Flexible and Consistent Multi-Step Recipe Image Generation","created":"2025-12-03","cited_by_count":1,"area":null},{"id":"2605.22391","title":"Epicure: Navigating the Emergent Geometry of Food Ingredient Embeddings","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2606.08948","title":"NutriMLLM: Multimodal Large Language Models for Dietary Micronutrient Analysis","created":"2026-06-08","cited_by_count":1,"area":"mllm"},{"id":"2105.04971","title":"Backretrieval: An Image-Pivoted Evaluation Metric for Cross-Lingual Text Representations Without Parallel Corpora","created":"2021-05-11","cited_by_count":0,"area":null},{"id":"2112.09839","title":"Calorie Aware Automatic Meal Kit Generation from an Image","created":"2021-12-18","cited_by_count":0,"area":null},{"id":"2201.00220","title":"Turath-150K: Image Database of Arab Heritage","created":"2022-01-01","cited_by_count":0,"area":null},{"id":"2205.02141","title":"RecipeSnap -- a lightweight image-to-recipe model","created":"2022-05-04","cited_by_count":0,"area":null},{"id":"2211.01745","title":"Task Tree Retrieval for Robotic Cooking","created":"2022-11-03","cited_by_count":0,"area":null},{"id":"2306.15977","title":"A Dimensional Structure based Knowledge Distillation Method for Cross-Modal Learning","created":"2023-06-28","cited_by_count":0,"area":"distill"},{"id":"2308.04579","title":"RECipe: Does a Multi-Modal Recipe Knowledge Graph Fit a Multi-Purpose Recommendation System?","created":"2023-08-08","cited_by_count":0,"area":null}],"next_cursor":"100"}