{"total":15,"rows":[{"id":"2301.04883","title":"SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images","created":"2023-01-12","cited_by_count":179,"area":null},{"id":"2112.08359","title":"3D Question Answering","created":"2021-12-15","cited_by_count":41,"area":null},{"id":"2203.15867","title":"Image Retrieval from Contextual Descriptions","created":"2022-03-29","cited_by_count":26,"area":null},{"id":"2311.00308","title":"From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities","created":"2023-11-01","cited_by_count":25,"area":null},{"id":"2103.05187","title":"Iterative Shrinking for Referring Expression Grounding Using Deep Reinforcement Learning","created":"2021-03-09","cited_by_count":20,"area":null},{"id":"2212.10278","title":"Fully and Weakly Supervised Referring Expression Segmentation with End-to-End Learning","created":"2022-12-17","cited_by_count":14,"area":null},{"id":"2404.16222","title":"Step Differences in Instructional Video","created":"2024-04-24","cited_by_count":11,"area":null},{"id":"2306.16713","title":"Answer Mining from a Pool of Images: Towards Retrieval-Based Visual Question Answering","created":"2023-06-29","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":"2104.00107","title":"Analysis on Image Set Visual Question Answering","created":"2021-03-31","cited_by_count":1,"area":null},{"id":"2412.20619","title":"Audiopedia: Audio QA with Knowledge","created":"2024-12-29","cited_by_count":1,"area":null},{"id":"2502.13034","title":"Natural Language Generation from Visual Events: State-of-the-Art and Key Open Questions","created":"2025-02-18","cited_by_count":1,"area":null},{"id":"2506.01275","title":"Contra4: Evaluating Contrastive Cross-Modal Reasoning in Audio, Video, Image, and 3D","created":"2025-06-02","cited_by_count":0,"area":null},{"id":"2601.16333","title":"Where is the multimodal goal post? On the Ability of Foundation Models to Recognize Highlights in Videos","created":"2026-01-22","cited_by_count":0,"area":null},{"id":"2605.11439","title":"Instruct-ICL: Instruction-Guided In-Context Learning for Post-Disaster Damage Assessment","created":"2026-05-12","cited_by_count":0,"area":null}],"next_cursor":null}