{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T19:51:53Z","timestamp":1779306713470,"version":"3.51.4"},"reference-count":50,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02025","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"21812-21821","source":"Crossref","is-referenced-by-count":2,"title":["VideoAds for Fast-Paced Video Understanding"],"prefix":"10.1109","author":[{"given":"Zheyuan","family":"Zhang","sequence":"first","affiliation":[{"name":"Northwestern University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wanying","family":"Dou","sequence":"additional","affiliation":[{"name":"Northwestern University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linkai","family":"Peng","sequence":"additional","affiliation":[{"name":"Northwestern University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongyi","family":"Pan","sequence":"additional","affiliation":[{"name":"Northwestern University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ulas","family":"Bagci","sequence":"additional","affiliation":[{"name":"Northwestern University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Boqing","family":"Gong","sequence":"additional","affiliation":[{"name":"Boston University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","author":"Bai","year":"2025","journal-title":"Qwen2. 5-vl technical report"},{"key":"ref2","article-title":"Language models are few-shot learners","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020","author":"Brown","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73113-6_11"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.11"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.51644\/9781771120920-031"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02245"},{"key":"ref8","author":"Fu","year":"2024","journal-title":"Mme-survey: A comprehensive survey on evaluation of multimodal 11 ms"},{"key":"ref9","author":"Ho","year":"2022","journal-title":"Large language models are reasoning teachers"},{"key":"ref10","author":"Hu","year":"2025","journal-title":"Video-mmmu: Evaluating knowledge acquisition from multi-discipline professional videos"},{"key":"ref11","author":"Hurst","year":"2024","journal-title":"Gpt-4o system card"},{"key":"ref12","author":"Hurst","year":"2024","journal-title":"Gpt-4o system card"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.56345\/ijrdv6n107"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"ref15","author":"Li","year":"2024","journal-title":"Llava-onevision: Easy visual task transfer"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02095"},{"key":"ref17","author":"Liu","year":"2023","journal-title":"Mmbench: Is your multi-modal model an all-around player?"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.517"},{"key":"ref19","author":"Maaz","year":"2024","journal-title":"Videogpt+: Integrating image and video encoders for enhanced video understanding"},{"key":"ref20","article-title":"Egoschema: A diagnostic benchmark for very longform video language understanding","volume-title":"NeurIPS","author":"Mangalam","year":"2024"},{"key":"ref21","author":"Ning","year":"2023","journal-title":"Video-bench: A comprehensive benchmark and toolkit for evaluating video-based large language models"},{"key":"ref22","year":"2023","journal-title":"GPT-4V(ision) system card"},{"key":"ref23","author":"Oquab","year":"2023","journal-title":"Dinov2: Learning robust visual features without supervision"},{"key":"ref24","author":"Ormazabal","year":"2024","journal-title":"Reka core, flash, and edge: A series of powerful multimodal language models"},{"key":"ref25","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref26","first-page":"28492","article-title":"Robust speech recog-nition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2023"},{"key":"ref27","author":"Reid","year":"2024","journal-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context"},{"key":"ref28","author":"Reid","year":"2024","journal-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context"},{"key":"ref29","article-title":"How to Write for Television 6th Edition: A guide to writing and selling successful TV Scripts","author":"Smethurst","year":"2009","journal-title":"How To Books"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3566695"},{"key":"ref31","author":"Team","year":"2023","journal-title":"Gemini: a family of highly capable multimodal models"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00914"},{"key":"ref33","author":"Wang","year":"2024","journal-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73013-9_23"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref36","first-page":"2482424837","article-title":"Chain-ofthought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref37","year":"2024","journal-title":"Wikipedia contributors. No. 5 the film - Wikipedia, the free encyclopedia"},{"key":"ref38","article-title":"Star: A benchmark for situated reasoning in real-world videos","volume-title":"NeurIPS","author":"Wu","year":"2024"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref41","author":"Yan","year":"2021","journal-title":"Videogpt: Video generation using vq-vae and transformers"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1108\/K-03-2016-0038"},{"key":"ref43","author":"Yao","year":"2024","journal-title":"Minicpm-v: A gpt-4v level mllm on your phone"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.738"},{"key":"ref46","author":"Zhang","year":"2024","journal-title":"Lmmseval: Reality check on the evaluation of large multimodal models"},{"key":"ref47","author":"Zhang","year":"2024","journal-title":"Long context transfer from language to vision"},{"key":"ref48","author":"Zhang","year":"2024","journal-title":"Llavanext: A strong zero-shot video understanding model"},{"key":"ref49","author":"Zhang","year":"2024","journal-title":"Video instruction tuning with synthetic data"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"}],"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\/11445293.pdf?arnumber=11445293","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:12:03Z","timestamp":1777612323000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445293\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02025","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}