{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:31:54Z","timestamp":1778009514790,"version":"3.51.4"},"reference-count":55,"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\/iccv51701.2025.02255","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"24330-24339","source":"Crossref","is-referenced-by-count":1,"title":["Player-Centric Multimodal Prompt Generation for Large Language Model Based Identity-Aware Basketball Video Captioning"],"prefix":"10.1109","author":[{"given":"Zeyu","family":"Xi","sequence":"first","affiliation":[{"name":"Beijing University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoying","family":"Sun","sequence":"additional","affiliation":[{"name":"Beijing University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaofei","family":"Wu","sequence":"additional","affiliation":[{"name":"Beijing University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junchi","family":"Yan","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoran","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lifang","family":"Wu","sequence":"additional","affiliation":[{"name":"Beijing University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Wang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changwen","family":"Chen","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University"}],"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","first-page":"65","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","volume-title":"Proceedings of Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Banerjee","year":"2005"},{"key":"ref3","first-page":"4","author":"Bertasius","year":"2021","journal-title":"Is space-time attention all you need for video understanding? In ICML"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref6","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"Proceedings of the 49th annual meeting of the association for computational linguistics: human language technologies","author":"Chen","year":"2011"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/d14-1179"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00910"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.340"},{"key":"ref10","article-title":"An image is worth $16 \\times 16$ words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2022.10.125"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref14","article-title":"Gaussian error linear units (gelus)","author":"Hendrycks","year":"2016","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1154"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475301"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3341105.3374063"},{"key":"ref18","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2930041"},{"key":"ref20","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01742"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref23","volume-title":"Llama 3.2 quantized models","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw59228.2023.00536"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548180"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00163"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_22"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615120"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2921655"},{"issue":"8","key":"ref31","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref32","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning (ICML)","author":"Radford","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.99"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00785"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00207"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298940"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01426"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3479207"},{"key":"ref40","volume-title":"Qwen2.5: A party of foundation models","year":"2024"},{"key":"ref41","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01724"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_2"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3349923"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.129177"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.126906"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01741"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00629"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.257"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01753"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681178"},{"key":"ref55","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\/11444849.pdf?arnumber=11444849","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:30:40Z","timestamp":1777613440000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444849\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02255","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}