{"total":32,"rows":[{"id":"2101.09465","title":"WebSRC: A Dataset for Web-Based Structural Reading Comprehension","created":"2021-01-23","cited_by_count":100,"area":null},{"id":"2210.05815","title":"Underspecification in Scene Description-to-Depiction Tasks","created":"2022-10-11","cited_by_count":30,"area":null},{"id":"2407.03550","title":"CoMix: A Comprehensive Benchmark for Multi-Task Comic Understanding","created":"2024-07-04","cited_by_count":16,"area":null},{"id":"2207.04675","title":"COO: Comic Onomatopoeia Dataset for Recognizing Arbitrary or Truncated Texts","created":"2022-07-11","cited_by_count":13,"area":null},{"id":"2204.04621","title":"Unsupervised Manga Character Re-identification via Face-body and Spatial-temporal Associated Clustering","created":"2022-04-10","cited_by_count":9,"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":"2506.02011","title":"OASIS: Online Sample Selection for Continual Visual Instruction Tuning","created":"2025-05-27","cited_by_count":9,"area":null},{"id":"2203.05711","title":"Synopses of Movie Narratives: a Video-Language Dataset for Story Understanding","created":"2022-03-11","cited_by_count":8,"area":null},{"id":"2308.09096","title":"Identity-Aware Semi-Supervised Learning for Comic Character Re-Identification","created":"2023-08-17","cited_by_count":8,"area":null},{"id":"2407.03540","title":"Comics Datasets Framework: Mix of Comics datasets for detection benchmarking","created":"2024-07-03","cited_by_count":7,"area":null},{"id":"2505.20298","title":"MangaVQA and MangaLMM: A Benchmark and Specialized Model for Multimodal Manga Understanding","created":"2025-05-26","cited_by_count":7,"area":null},{"id":"2204.14034","title":"A Challenging Benchmark of Anime Style Recognition","created":"2022-04-29","cited_by_count":6,"area":null},{"id":"2509.23724","title":"Video Panels for Long Video Understanding","created":"2025-09-28","cited_by_count":6,"area":null},{"id":"2403.03719","title":"Multimodal Transformer for Comics Text-Cloze","created":"2024-03-06","cited_by_count":5,"area":null},{"id":"2212.14674","title":"A Comprehensive Gold Standard and Benchmark for Comics Text Detection and Recognition","created":"2022-12-27","cited_by_count":4,"area":null},{"id":"2401.02863","title":"A Customizable Generator for Comic-Style Visual Narrative","created":"2023-12-14","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":"2409.16159","title":"ComiCap: A VLMs pipeline for dense captioning of Comic Panels","created":"2024-09-24","cited_by_count":3,"area":null},{"id":"2104.10139","title":"Towards Solving Multimodal Comprehension","created":"2021-04-20","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":"2407.08248","title":"Toward accessible comics for blind and low vision readers","created":"2024-07-11","cited_by_count":2,"area":null},{"id":"2507.10053","title":"CoSMo: A Multimodal Transformer for Page Stream Segmentation in Comic Books","created":"2025-07-14","cited_by_count":2,"area":null},{"id":"2105.10131","title":"Visual representation of negation: Real world data analysis on comic image design","created":"2021-05-21","cited_by_count":1,"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":"2211.10641","title":"Domain-Adaptive Self-Supervised Pre-Training for Face & Body Detection in Drawings","created":"2022-11-19","cited_by_count":1,"area":null},{"id":"2312.08720","title":"Panel Transitions for Genre Analysis in Visual Narratives","created":"2023-12-14","cited_by_count":1,"area":null},{"id":"2410.20459","title":"Unlocking Comics: The AI4VA Dataset for Visual Understanding","created":"2024-10-27","cited_by_count":1,"area":null},{"id":"2508.16190","title":"ComicScene154: A Scene Dataset for Comic Analysis","created":"2025-08-22","cited_by_count":1,"area":null},{"id":"2512.01686","title":"DreamingComics: A Story Visualization Pipeline via Subject and Layout Customized Generation using Video Models","created":"2025-12-01","cited_by_count":1,"area":null},{"id":"2312.08695","title":"CPST: Comprehension-Preserving Style Transfer for Multi-Modal Narratives","created":"2023-12-14","cited_by_count":0,"area":null},{"id":"2504.16136","title":"Active Learning Methods for Efficient Data Utilization and Model Performance Enhancement","created":"2025-04-21","cited_by_count":0,"area":null},{"id":"2610.13840","title":"Studying Comics at Scale with Artificial Intelligence: The PAGE Framework and Three Studies of American Comics and Japanese Manga","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}