{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T03:24:37Z","timestamp":1782789877441,"version":"3.54.5"},"reference-count":93,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022ZD0160603,62306162"],"award-info":[{"award-number":["2022ZD0160603,62306162"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02172","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"01-12","source":"Crossref","is-referenced-by-count":2,"title":["AdsQA: Towards Advertisement Video Understanding"],"prefix":"10.1109","author":[{"given":"Xinwei","family":"Long","sequence":"first","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Tian","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Xu","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guoli","family":"Jia","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingxuan","family":"Li","sequence":"additional","affiliation":[{"name":"Independent Researcher"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sa","family":"Yang","sequence":"additional","affiliation":[{"name":"Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yihua","family":"Shao","sequence":"additional","affiliation":[{"name":"CASIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaiyan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Che","family":"Jiang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Xu","sequence":"additional","affiliation":[{"name":"Harvard University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Independent Researcher"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaheng","family":"Ma","sequence":"additional","affiliation":[{"name":"Independent Researcher"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bowen","family":"Zhou","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref2","first-page":"15","article-title":"Gpt-4 technical report","volume":"6","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02222"},{"issue":"6","key":"ref4","first-page":"7","article-title":"Qwen2. 5-vl technical report","volume":"3","author":"Bai","year":"2025","journal-title":"arXiv preprint"},{"key":"ref5","first-page":"16","article-title":"Temporalbench: Benchmarking fine-grained temporal understanding for multimodal video models","volume":"abs\/2410.10818","author":"Cai","year":"2024","journal-title":"CoRR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i2.32214"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73113-6_11"},{"key":"ref9","article-title":"Videollama 2: Advancing spatial-temporal modeling and audio understanding in videollms","volume":"abs\/2406.07476","author":"Cheng","year":"2024","journal-title":"CoRR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.870"},{"key":"ref11","first-page":"15","article-title":"Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities","volume":"7","author":"Comanici","year":"2025","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01229"},{"key":"ref13","first-page":"1","article-title":"Automating exploratory pro-teomics research via language models","author":"Ding","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_5"},{"issue":"6","key":"ref15","first-page":"7","article-title":"Video-of-thought: Step-by-step video reasoning from perception to cognition","volume":"3","author":"Fei","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02245"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01419"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i22.34565"},{"issue":"6","key":"ref19","first-page":"16","article-title":"Short film dataset (SFD): A benchmark for storylevel video understanding","volume":"abs\/2406.10221","author":"Ghermi","year":"2024","journal-title":"CoRR"},{"key":"ref20","first-page":"6","article-title":"Deepseek-coder: When the large language model meets programming-the rise of code intelligence","volume":"1","author":"Guo","year":"2024","journal-title":"arXiv preprint"},{"issue":"3","key":"ref21","first-page":"5","article-title":"Deepseek-r1: Incentivizing reasoning capability in 11 ms via reinforcement learning","volume":"1","author":"Guo","year":"2025","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Cos: Chain-of-shot prompting for long video understanding","author":"Hu","year":"2025","journal-title":"arXiv preprint"},{"issue":"6","key":"ref23","first-page":"7","article-title":"Gpt-4o system card","volume":"4","author":"Hurst","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.123"},{"key":"ref25","first-page":"3","article-title":"Openai o1 system card","volume":"1","author":"Jaech","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01279"},{"key":"ref28","first-page":"3","article-title":"Kafa: Rethinking image ad understanding with knowledgeaugmented feature adaptation of vision-language models","author":"Jia","year":"2023","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6767"},{"key":"ref30","first-page":"3","article-title":"Preference optimization for reasoning with pseudo feedback","author":"Jiao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25076"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1167"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"issue":"6","key":"ref34","first-page":"7","article-title":"Llava-onevision: Easy visual task transfer","volume":"3","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018658"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72992-8_12"},{"key":"ref39","first-page":"3","article-title":"Video-llava: Learning united visual representation by alignment before projection","volume":"abs\/2311.10122","author":"Lin","year":"2023","journal-title":"CoRR"},{"key":"ref40","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref41","first-page":"3","author":"Liu","year":"2024","journal-title":"Llava-next: Improved reasoning, ocr, and world knowledge"},{"key":"ref42","first-page":"3","article-title":"Visualrft: Visual reinforcement fine-tuning","author":"Liu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i23.34653"},{"key":"ref44","first-page":"3","article-title":"Reft: Reasoning with reinforced fine-tuning","author":"Quoc Luong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref46","first-page":"3","article-title":"Videogpt+: Integrating image and video encoders for enhanced video understanding","author":"Maaz","year":"2024","journal-title":"arxiv"},{"key":"ref47","first-page":"16","article-title":"Egoschema: A diagnostic benchmark for very longform video language understanding","volume":"3","author":"Mangalam","year":"2023","journal-title":"NeurIPS"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01257"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.1025"},{"key":"ref50","first-page":"16","article-title":"Video-bench: A comprehensive benchmark and toolkit for evaluating video-based large language models","volume":"abs\/2311.16103","author":"Ning","year":"2023","journal-title":"CoRR"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref52","first-page":"1","article-title":"Large language models as biomedical hypothesis generators: a comprehensive evaluation","volume-title":"arXiv preprint","author":"Qi","year":"2024"},{"key":"ref53","first-page":"arXiv-2406","article-title":"Seeing the unseen: Visual metaphor captioning for videos","author":"Rajakumar Kalarani","year":"2024","journal-title":"arXiv e-prints"},{"key":"ref54","article-title":"How2: a large-scale dataset for multimodal language understanding","author":"Sanabria","year":"2018","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01660"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3754500"},{"key":"ref57","first-page":"3","article-title":"Unlocking video-llm via agent-of-thoughts distillation","author":"Shi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref58","first-page":"3","article-title":"Moviechat+: Question-aware sparse memory for long video question answering","author":"Song","year":"2024","journal-title":"arXiv preprint"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.501"},{"issue":"7","key":"ref60","first-page":"15","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","volume":"3","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72989-8_4"},{"key":"ref62","first-page":"3","article-title":"Internvideo2: Scaling video foundation models for multimodal video understanding","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref63","first-page":"3","article-title":"Videocot: A video chain-ofthought dataset with active annotation tool","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01254"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_3"},{"key":"ref68","first-page":"3","article-title":"Streaming video understanding and multi-round interaction with memoryenhanced knowledge","author":"Xiong","year":"2025","journal-title":"arXiv preprint"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref70","article-title":"Pllava: Parameter-free llava extension from images to videos for video dense captioning","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.6"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.513"},{"key":"ref73","first-page":"3","article-title":"Doraemongpt: Toward understanding dynamic scenes with large language models (exemplified as a video agent)","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref74","article-title":"Lens: Multi-level evaluation of multimodal reasoning with large language models","author":"Yao","year":"2025","journal-title":"arXiv preprint"},{"key":"ref75","first-page":"15","article-title":"Minicpm-v: A gpt-4v level mllm on your phone","volume":"7","author":"Yao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2947440"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019127"},{"issue":"6","key":"ref78","first-page":"7","article-title":"Evoagent: Towards automatic multiagent generation via evolutionary algorithms","volume":"4","author":"Yuan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/s10660-023-09676-7"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.340"},{"key":"ref81","first-page":"3","article-title":"Futuresightdrive: Thinking visually with spatio-temporal cot for autonomous driving","author":"Zeng","year":"2025","journal-title":"arXiv preprint"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.249"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.409"},{"issue":"6","key":"ref84","first-page":"7","article-title":"Accessing gpt-4 level mathematical olympiad solutions via monte carlo tree self-refine with llama-3 8b","volume":"1","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"issue":"7","key":"ref85","first-page":"15","article-title":"Internlm-xcomposer-2.5: A versatile large vision language model supporting long-contextual input and output","volume":"3","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref86","first-page":"3","author":"Zhang","year":"2024","journal-title":"Llavanext: A strong zero-shot video understanding model"},{"key":"ref87","first-page":"7","article-title":"Video instruction tuning with synthetic data","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref88","first-page":"15","author":"Zhang","year":"2024","journal-title":"Video instruction tuning with synthetic data"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3661350"},{"key":"ref90","first-page":"8","article-title":"Open-ended longform video question answering via adaptive hierarchical reinforced networks","author":"Zhao","year":"2018","journal-title":"IJCAI"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01258"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"ref93","first-page":"1","article-title":"Medxpertqa: Benchmarking expert-level medical reasoning and understanding","author":"Zuo","year":"2025","journal-title":"arXiv preprint"},{"key":"ref94","first-page":"3","article-title":"Ttrl: Test-time reinforcement learning","author":"Zuo","year":"2025","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444190.pdf?arnumber=11444190","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T19:45:06Z","timestamp":1777578306000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444190\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":93,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02172","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}