{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T21:03:54Z","timestamp":1776978234972,"version":"3.51.4"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272337"],"award-info":[{"award-number":["62272337"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006606","name":"Natural Science Foundation of Tianjin","doi-asserted-by":"publisher","award":["23JCQNJC01520"],"award-info":[{"award-number":["23JCQNJC01520"]}],"id":[{"id":"10.13039\/501100006606","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3684826","type":"journal-article","created":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T19:54:13Z","timestamp":1776369253000},"page":"59095-59108","source":"Crossref","is-referenced-by-count":0,"title":["Causal Inference and Text-Assisted Localization for Medical Video Localization"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-0105-5684","authenticated-orcid":false,"given":"Shikai","family":"Zhou","sequence":"first","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tingting","family":"Bo","sequence":"additional","affiliation":[{"name":"Medical Operations Department, Tianjin TEDA Hospital, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0160-2545","authenticated-orcid":false,"given":"Zibo","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Microelectronics, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bingyang","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Tianjin Chest Hospital, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaopeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Cardiothoracic Surgery Department, Tianjin Chest Hospital, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI48211.2021.9433921"},{"key":"ref2","article-title":"Artificial intelligence in gastrointestinal bleeding analysis for video capsule endoscopy: Insights, innovations, and prospects (2008\u20132023)","author":"Singh","year":"2024","journal-title":"arXiv:2409.00639"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/app13116582"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics12010043"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3077313"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.327"},{"key":"ref8","article-title":"MS-DETR: Natural language video localization with sampling moment-moment interaction","author":"Wang","year":"2023","journal-title":"arXiv:2305.18969"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16406"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01253"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.4018\/IJSWIS.332768"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00360"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00042"},{"key":"ref14","volume-title":"Counterfactuals and Causal Inference: Methods and Principles for Social Research","author":"Antonakis","year":"2011"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9781139025751"},{"key":"ref16","volume-title":"Elements of Causal Inference: Foundations and Learning Algorithms","author":"Peters","year":"2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1017\/S0266466603004109"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3058954"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1093\/ectj\/utad008"},{"key":"ref20","first-page":"6446","article-title":"Causal effect inference with deep latent-variable models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Louizos"},{"key":"ref21","volume-title":"Causal Inference","author":"Hern\u00e1n","year":"2010"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.386"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref25","article-title":"Bottom-up and top-down attention for image captioning and visual question answering","author":"Anderson","year":"2017","journal-title":"arXiv:1707.07998"},{"key":"ref26","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01188-y"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210003"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1015"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00032"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019062"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018199"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00134"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018393"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018175"},{"key":"ref37","first-page":"1984","article-title":"ExCL: Extractive clip localization using natural language descriptions","volume-title":"Proc. Conf. North American Chapter Assoc. Comput. Linguistics, Human Lang. Technol.","author":"Ghosh"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019159"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1518"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00207"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33718-5_11"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240549"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1168"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-023-02036-y"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-021-00920-z"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-022-02433-7"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2025.3575554"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2025.3591094"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/HRI61500.2025.10973826"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2941820"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2025.3569584"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2025.103150"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.327"},{"key":"ref58","first-page":"1230","article-title":"MS-DETR: Multi-scale detr for natural language video localization","volume-title":"Proc. 61st Annu. Meeting Assoc. Comput. Linguistics","author":"Jing"},{"key":"ref59","first-page":"18874","article-title":"UnLoc: A unified framework for video localization tasks","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis. (ICCV)","author":"Fernando"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11482438.pdf?arnumber=11482438","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T20:00:00Z","timestamp":1776974400000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11482438\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3684826","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}