{"total":61,"rows":[{"id":"2203.14371","title":"MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answering","created":"2022-03-27","cited_by_count":543,"area":null},{"id":"2104.12756","title":"InfographicVQA","created":"2021-04-26","cited_by_count":437,"area":null},{"id":"2101.11272","title":"VisualMRC: Machine Reading Comprehension on Document Images","created":"2021-01-27","cited_by_count":151,"area":null},{"id":"2109.00590","title":"WebQA: Multihop and Multimodal QA","created":"2021-09-01","cited_by_count":109,"area":null},{"id":"2101.09465","title":"WebSRC: A Dataset for Web-Based Structural Reading Comprehension","created":"2021-01-23","cited_by_count":100,"area":null},{"id":"2209.04355","title":"MIntRec: A New Dataset for Multimodal Intent Recognition","created":"2022-09-09","cited_by_count":41,"area":null},{"id":"2108.13327","title":"N24News: A New Dataset for Multimodal News Classification","created":"2021-08-30","cited_by_count":40,"area":null},{"id":"2305.01795","title":"Multimodal Procedural Planning via Dual Text-Image Prompting","created":"2023-05-02","cited_by_count":40,"area":null},{"id":"2107.13189","title":"Goal-Oriented Script Construction","created":"2021-07-28","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":"2204.13243","title":"HybriDialogue: An Information-Seeking Dialogue Dataset Grounded on Tabular and Textual Data","created":"2022-04-28","cited_by_count":28,"area":null},{"id":"2411.04075","title":"M3SciQA: A Multi-Modal Multi-Document Scientific QA Benchmark for Evaluating Foundation Models","created":"2024-11-06","cited_by_count":27,"area":null},{"id":"2101.10421","title":"English Machine Reading Comprehension Datasets: A Survey","created":"2021-01-25","cited_by_count":26,"area":null},{"id":"2402.01512","title":"Distractor Generation in Multiple-Choice Tasks: A Survey of Methods, Datasets, and Evaluation","created":"2024-02-02","cited_by_count":25,"area":null},{"id":"2406.11030","title":"FoodieQA: A Multimodal Dataset for Fine-Grained Understanding of Chinese Food Culture","created":"2024-06-16","cited_by_count":25,"area":null},{"id":"2206.15030","title":"Modern Question Answering Datasets and Benchmarks: A Survey","created":"2022-06-30","cited_by_count":23,"area":null},{"id":"2104.07635","title":"Time-Stamped Language Model: Teaching Language Models to Understand the Flow of Events","created":"2021-04-15","cited_by_count":22,"area":null},{"id":"2111.05547","title":"ICDAR 2021 Competition on Document VisualQuestion Answering","created":"2021-11-10","cited_by_count":19,"area":null},{"id":"2104.08066","title":"Effect of Visual Extensions on Natural Language Understanding in Vision-and-Language Models","created":"2021-04-16","cited_by_count":18,"area":null},{"id":"2110.08486","title":"Understanding Multimodal Procedural Knowledge by Sequencing Multimodal Instructional Manuals","created":"2021-10-16","cited_by_count":18,"area":null},{"id":"2206.13349","title":"Process Knowledge-Infused AI: Towards User-level Explainability, Interpretability, and Safety","created":"2022-06-09","cited_by_count":18,"area":null},{"id":"2207.07568","title":"Reasoning about Actions over Visual and Linguistic Modalities: A Survey","created":"2022-07-15","cited_by_count":10,"area":null},{"id":"2301.10165","title":"Lexi: Self-Supervised Learning of the UI Language","created":"2023-01-23","cited_by_count":10,"area":null},{"id":"2403.19454","title":"JDocQA: Japanese Document Question Answering Dataset for Generative Language Models","created":"2024-03-28","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":"2209.05840","title":"Visual Recipe Flow: A Dataset for Learning Visual State Changes of Objects with Recipe Flows","created":"2022-09-13","cited_by_count":8,"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":"2209.02508","title":"\"Mama Always Had a Way of Explaining Things So I Could Understand'': A Dialogue Corpus for Learning to Construct Explanations","created":"2022-09-06","cited_by_count":6,"area":null},{"id":"2109.11047","title":"Cross-Modal Coherence for Text-to-Image Retrieval","created":"2021-09-22","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":"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":"2302.06829","title":"The Role of Semantic Parsing in Understanding Procedural Text","created":"2023-02-14","cited_by_count":4,"area":null},{"id":"2503.13500","title":"Long-horizon Visual Instruction Generation with Logic and Attribute Self-reflection","created":"2025-03-12","cited_by_count":4,"area":null},{"id":"2601.12318","title":"Beyond Human Annotation: Recent Advances in Data Generation Methods for Document Intelligence","created":"2026-01-18","cited_by_count":4,"area":null},{"id":"2311.08329","title":"KTRL+F: Knowledge-Augmented In-Document Search","created":"2023-11-14","cited_by_count":3,"area":null},{"id":"2401.13594","title":"Graph Guided Question Answer Generation for Procedural Question-Answering","created":"2024-01-24","cited_by_count":3,"area":null},{"id":"2101.04727","title":"Latent Alignment of Procedural Concepts in Multimodal Recipes","created":"2021-01-12","cited_by_count":2,"area":null},{"id":"2104.10139","title":"Towards Solving Multimodal Comprehension","created":"2021-04-20","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":"2204.02566","title":"Modeling Temporal-Modal Entity Graph for Procedural Multimodal Machine Comprehension","created":"2022-04-06","cited_by_count":2,"area":null},{"id":"2303.16778","title":"Assorted, Archetypal and Annotated Two Million (3A2M) Cooking Recipes Dataset based on Active Learning","created":"2023-03-27","cited_by_count":2,"area":null},{"id":"2305.14815","title":"Machine Reading Comprehension using Case-based Reasoning","created":"2023-05-24","cited_by_count":2,"area":null},{"id":"2403.00662","title":"Modeling the Quality of Dialogical Explanations","created":"2024-03-01","cited_by_count":2,"area":null},{"id":"2410.13662","title":"ActionCOMET: A Zero-shot Approach to Learn Image-specific Commonsense Concepts about Actions","created":"2024-10-17","cited_by_count":2,"area":null},{"id":"2506.11380","title":"Enhance Multimodal Consistency and Coherence for Text-Image Plan Generation","created":"2025-06-13","cited_by_count":2,"area":null},{"id":"2110.11899","title":"Challenges in Procedural Multimodal Machine Comprehension:A Novel Way To Benchmark","created":"2021-10-22","cited_by_count":1,"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":"2306.00887","title":"OpenPI-C: A Better Benchmark and Stronger Baseline for Open-Vocabulary State Tracking","created":"2023-06-01","cited_by_count":1,"area":null},{"id":"2309.10945","title":"Benchmarks for Pir\\'a 2.0, a Reading Comprehension Dataset about the Ocean, the Brazilian Coast, and Climate Change","created":"2023-09-19","cited_by_count":1,"area":null},{"id":"2404.01182","title":"A Neuro-Symbolic Approach to Monitoring Salt Content in Food","created":"2024-04-01","cited_by_count":1,"area":null},{"id":"2405.18682","title":"Can GPT Redefine Medical Understanding? Evaluating GPT on Biomedical Machine Reading Comprehension","created":"2024-05-29","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":"2309.14165","title":"Towards End-User Development for IoT: A Case Study on Semantic Parsing of Cooking Recipes for Programming Kitchen Devices","created":"2023-09-25","cited_by_count":0,"area":null},{"id":"2402.03957","title":"Sparse Graph Representations for Procedural Instructional Documents","created":"2024-02-06","cited_by_count":0,"area":null},{"id":"2406.13714","title":"BEACON: Balancing Convenience and Nutrition in Meals With Long-Term Group Recommendations and Reasoning on Multimodal Recipes","created":"2024-06-19","cited_by_count":0,"area":null},{"id":"2408.02114","title":"Recent Advances in Multi-Choice Machine Reading Comprehension: A Survey on Methods and Datasets","created":"2024-08-04","cited_by_count":0,"area":null},{"id":"2411.01996","title":"Culinary Class Wars: Evaluating LLMs using ASH in Cuisine Transfer Task","created":"2024-11-04","cited_by_count":0,"area":null},{"id":"2412.18327","title":"HAUR: Human Annotation Understanding and Recognition Through Text-Heavy Images","created":"2024-12-24","cited_by_count":0,"area":null},{"id":"2507.17232","title":"A Highly Clean Recipe Dataset with Ingredient States Annotation for State Probing Task","created":"2025-07-23","cited_by_count":0,"area":null},{"id":"2604.26565","title":"DenseStep2M: A Scalable, Training-Free Pipeline for Dense Instructional Video Annotation","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2608.14505","title":"RecipeNet: A Hierarchical Transformer for Recipe Data","created":"2026-08-14","cited_by_count":0,"area":null}],"next_cursor":null}