{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/question-answering-dense-video-events","title":"Question-Answering Dense Video Events","arxiv_id":"2409.04388","date":"2024-09-06","proceeding":null,"authors":["Hangyu Qin","Junbin Xiao","Angela Yao"],"abstract":"This paper presents question-answering on dense video events, a novel task that answers and grounds dense-event questions in long videos, thus challenging MLLMs to faithfully comprehend and reason about multiple events over extended periods of time. To facilitate the study, we construct DeVE-QA -- a dataset featuring 78K questions about 26K events on 10.6K long videos. Our benchmarking shows that state-of-the-art MLLMs struggle on DeVE-QA. For improvement, we propose DeVi, a novel training-free MLLM approach that highlights a hierarchical captioning module, a temporal event memory module, and a self-consistency checking module to respectively detect, contextualize and memorize, and ground dense-events in long videos for question answering. Extensive experiments show that DeVi is superior at answering dense-event questions and grounding relevant video moments. Compared with existing MLLMs, it achieves a notable increase of 4.8% and 2.1% for G(round)QA accuracy on DeVE-QA and NExT-GQA, respectively. Data and code are available at https://github.com/QHUni/DeVE-QA.","url_abs":"https://arxiv.org/abs/2409.04388v5","url_pdf":"https://arxiv.org/pdf/2409.04388v5.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"question-answering-dense-video-events","repo_url":"https://github.com/qhuni/deve-qa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"zeroshot-video-question-answer","task_name":"Zero-Shot Video Question Answer"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/zero-shot-video-question-answer-on-next-gqa","task":"Zero-Shot Video Question Answer","dataset":"NExT-GQA","model":"DeVi (Gemini 2.0)","rank_in_archive_order":1,"of":9,"metrics":{"Acc@GQA":"28.9"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-video-question-answer-on-next-gqa","task":"Zero-Shot Video Question Answer","dataset":"NExT-GQA","model":"DeVi (GPT-4)","rank_in_archive_order":3,"of":9,"metrics":{"Acc@GQA":"28.0"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2409.04388","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}