{"total":37,"rows":[{"id":"2103.16107","title":"Large Scale Visual Food Recognition","created":"2021-03-30","cited_by_count":75,"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":"2109.05743","title":"Explain Me the Painting: Multi-Topic Knowledgeable Art Description Generation","created":"2021-09-13","cited_by_count":30,"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":"2206.01843","title":"Visual Clues: Bridging Vision and Language Foundations for Image Paragraph Captioning","created":"2022-06-03","cited_by_count":21,"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":"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":"2408.16889","title":"LLaVA-Chef: A Multi-modal Generative Model for Food Recipes","created":"2024-08-29","cited_by_count":14,"area":null},{"id":"2409.12010","title":"ChefFusion: Multimodal Foundation Model Integrating Recipe and Food Image Generation","created":"2024-09-18","cited_by_count":11,"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":"2312.08592","title":"Dietary Assessment with Multimodal ChatGPT: A Systematic Analysis","created":"2023-12-14","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":"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":"2302.07960","title":"Learning to Substitute Ingredients in Recipes","created":"2023-02-15","cited_by_count":8,"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":"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":"2305.17542","title":"Non-Sequential Graph Script Induction via Multimedia Grounding","created":"2023-05-27","cited_by_count":4,"area":null},{"id":"2203.06721","title":"Food Recipe Recommendation Based on Ingredients Detection Using Deep Learning","created":"2022-03-13","cited_by_count":2,"area":null},{"id":"2205.02454","title":"Assistive Recipe Editing through Critiquing","created":"2022-05-05","cited_by_count":2,"area":null},{"id":"2209.10134","title":"Recipe Generation from Unsegmented Cooking Videos","created":"2022-09-21","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":"2204.09432","title":"A Mobile Food Recognition System for Dietary Assessment","created":"2022-04-20","cited_by_count":1,"area":null},{"id":"2209.12774","title":"Towards Fine-Dining Recipe Generation with Generative Pre-trained Transformers","created":"2022-09-26","cited_by_count":1,"area":null},{"id":"2503.13821","title":"Stitch-a-Demo: Video Demonstrations from Multistep Descriptions","created":"2025-03-18","cited_by_count":1,"area":null},{"id":"2504.18727","title":"World Food Atlas Project","created":"2025-04-25","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":"2112.09839","title":"Calorie Aware Automatic Meal Kit Generation from an Image","created":"2021-12-18","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":"2407.00911","title":"Deep Image-to-Recipe Translation","created":"2024-07-01","cited_by_count":0,"area":null},{"id":"2508.14718","title":"The Digital Sous Chef -- A Comparative Study on Fine-Tuning Language Models for Recipe Generation","created":"2025-08-20","cited_by_count":0,"area":null},{"id":"2509.24792","title":"Evaluating Spatiotemporal Consistency in Automatically Generated Sewing Instructions","created":"2025-09-29","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":"2604.11913","title":"V-Nutri: Dish-Level Nutrition Estimation from Egocentric Cooking Videos","created":"2026-04-13","cited_by_count":0,"area":null}],"next_cursor":null}