{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T08:54:40Z","timestamp":1771923280768,"version":"3.50.1"},"reference-count":65,"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\/501100020963","name":"JST Moonshot R&D Program","doi-asserted-by":"publisher","award":["JPMJMS2236"],"award-info":[{"award-number":["JPMJMS2236"]}],"id":[{"id":"10.13039\/501100020963","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\/iccvw69036.2025.00135","type":"proceedings-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:44:02Z","timestamp":1771879442000},"page":"1265-1275","source":"Crossref","is-referenced-by-count":0,"title":["PMC-Vid: A Large-Scale Biomedical Video Captioning Dataset"],"prefix":"10.1109","author":[{"given":"Yosuke","family":"Yamagishi","sequence":"first","affiliation":[{"name":"The University of Tokyo"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kuniaki","family":"Saito","sequence":"additional","affiliation":[{"name":"OMRON SINIC X Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Atsushi","family":"Hashimoto","sequence":"additional","affiliation":[{"name":"OMRON SINIC X Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoshitaka","family":"Ushiku","sequence":"additional","affiliation":[{"name":"OMRON SINIC X Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.tria.2020.100083"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-41299-9_37"},{"key":"ref4","article-title":"Qwen2. 5-v1 technical report","author":"Bai","year":"2025","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612156"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0614"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43996-4_3"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref9","article-title":"Videollama 2: Advancing spatial-temporal modeling and audio understanding in video-llms","author":"Cheng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.5946\/ce.2014.47.6.490"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02245"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.06.096"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.337"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.6028\/nist.sp.1329.overview.medvidqa-coordinators"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-023-02036-y"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72390-2_45"},{"key":"ref17","article-title":"Shot2story20k: A new benchmark for comprehensive understanding of multi-shot videos","author":"Han","year":"2023","journal-title":"arXiv preprint"},{"key":"ref18","volume-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"ref19","article-title":"Video-mmmu: Evaluating knowledge acquisition from multi-discipline professional videos","author":"Hu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.aacl-main.48"},{"key":"ref21","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1005927"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1023\/A:1020346032608"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v27i1.8679"},{"key":"ref26","first-page":"28541","article-title":"LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day","volume":"36","author":"Li","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-57426-0"},{"key":"ref28","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International conference on machine learning","author":"Li","year":"2022"},{"key":"ref29","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref31","article-title":"Vlm-eval: a general evaluation on video large language models","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref32","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43993-3_51"},{"key":"ref34","first-page":"34892","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2023","journal-title":"Advances in neural information processing systems"},{"key":"ref35","volume-title":"Llava-next: Improved reasoning, ocr, and world knowledge","author":"Liu","year":"2024"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01837"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-07618-3"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1038\/nature08869"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-821259-2.00003-X"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1006128"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/RBME.2024.3408456"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-03302-1"},{"key":"ref44","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv preprint"},{"key":"ref45","first-page":"1218","article-title":"Integrating language and vision to generate natural language descriptions of videos in the wild","volume-title":"Proceedings of coling 2014, the 25th international conference on computational linguistics: Technical papers","author":"Thomason","year":"2014"},{"key":"ref46","article-title":"Translating videos to natural language using deep recurrent neural networks","author":"Venugopalan","year":"2014","journal-title":"arXiv preprint"},{"key":"ref47","article-title":"Qwen2-v1: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arxiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0195315"},{"key":"ref49","article-title":"Lvbench: An extreme long video understanding benchmark","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00468"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2020.03.001"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-07441-w"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref54","article-title":"Pllava: Parameter-free llava extension from images to videos for video dense captioning","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2867286"},{"key":"ref56","first-page":"49428","article-title":"Vidchapters-7m: Video chapters at scale","author":"Yang","year":"2023","journal-title":"Advances in Neural Information Processing Systems, 36"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01032"},{"key":"ref58","article-title":"Videollama 3: Frontier multimodal foundation models for image and video understanding","author":"Zhang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1056\/AIoa2400640"},{"key":"ref62","article-title":"Bertscore: Evaluating text generation with bert","volume-title":"International Conference on Learning Representations","author":"Zhang"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1038\/s43856-024-00709-2"},{"key":"ref64","volume-title":"Llava-next: A strong zero-shot video understanding model","author":"Zhang","year":"2024"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,20]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11373940\/11374285\/11375300.pdf?arnumber=11375300","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T07:50:14Z","timestamp":1771919414000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11375300\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/iccvw69036.2025.00135","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}