{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T07:13:08Z","timestamp":1779347588766,"version":"3.51.4"},"reference-count":17,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T00:00:00Z","timestamp":1775606400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T00:00:00Z","timestamp":1775606400000},"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":[[2026,4,8]]},"DOI":"10.1109\/isbi61048.2026.11515743","type":"proceedings-article","created":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T19:48:46Z","timestamp":1779306526000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Evidence-Grounded Temporal Reasoning in Operating Room Long Video Understanding"],"prefix":"10.1109","author":[{"given":"Yaoqian","family":"Li","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Computer Science and Engineering,Hong Kong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinpeng","family":"Li","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Computer Science and Engineering,Hong Kong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pheng-Ann","family":"Heng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Computer Science and Engineering,Hong Kong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2026.104083"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16449-1_45"},{"key":"ref3","article-title":"Surgpub-video: A comprehensive surgical video dataset for enhanced surgical intelligence in visionlanguage model","author":"Li","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-032-05114-1_40"},{"key":"ref5","article-title":"Orqa: A benchmark and foundation model for holistic operating room modeling","author":"\u00d6zsoy","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01805"},{"key":"ref7","article-title":"Spatial-ormllm: Improve spatial relation understanding in the operating room with multimodal large language model","author":"He","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-025-03393-2"},{"key":"ref9","article-title":"Qwen2-vl: Enhancing visionlanguage model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref10","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02131"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73414-4_26"},{"key":"ref13","volume-title":"Introducing gpt-5","year":"2025"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref15","article-title":"Qwen3 technical report","author":"Yang","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref16","article-title":"Video-r1: Reinforcing video reasoning in mllms","author":"Feng","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"}],"event":{"name":"2026 IEEE 23rd International Symposium on Biomedical Imaging (ISBI)","location":"London, United Kingdom","start":{"date-parts":[[2026,4,8]]},"end":{"date-parts":[[2026,4,11]]}},"container-title":["2026 IEEE 23rd International Symposium on Biomedical Imaging (ISBI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11515282\/11515297\/11515743.pdf?arnumber=11515743","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T06:44:05Z","timestamp":1779345845000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11515743\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,8]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/isbi61048.2026.11515743","relation":{},"subject":[],"published":{"date-parts":[[2026,4,8]]}}}