{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T21:24:10Z","timestamp":1791408250672,"version":"4.3.3"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2023YFC2705700"],"award-info":[{"award-number":["2023YFC2705700"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U23B2048"],"award-info":[{"award-number":["U23B2048"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Innovative Research Group Project of Hubei Province","award":["2024AFA017"],"award-info":[{"award-number":["2024AFA017"]}]},{"name":"Science and Technology Major Project of Hubei Province","award":["2024BAB046"],"award-info":[{"award-number":["2024BAB046"]}]},{"name":"Wuhan University (WHU)-Kingsoft Joint Laboratory."}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1109\/tcsvt.2026.3688478","type":"journal-article","created":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T19:49:51Z","timestamp":1777405791000},"page":"14283-14297","source":"Crossref","is-referenced-by-count":3,"title":["GoMatching++: Parameter- and Data-Efficient Arbitrary-Shaped Video Text Spotting and Benchmarking"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-2004-150X","authenticated-orcid":false,"given":"Haibin","family":"He","sequence":"first","affiliation":[{"name":"Wuhan University","place":["Wuhan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6595-7661","authenticated-orcid":false,"given":"Jing","family":"Zhang","sequence":"additional","affiliation":[{"name":"Wuhan University","place":["Wuhan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4180-1096","authenticated-orcid":false,"given":"Maoyuan","family":"Ye","sequence":"additional","affiliation":[{"name":"Wuhan University","place":["Wuhan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3907-8820","authenticated-orcid":false,"given":"Juhua","family":"Liu","sequence":"additional","affiliation":[{"name":"Wuhan University","place":["Wuhan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0059-8458","authenticated-orcid":false,"given":"Bo","family":"Du","sequence":"additional","affiliation":[{"name":"Wuhan University","place":["Wuhan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-5449","authenticated-orcid":false,"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[{"name":"Nanyang Technological University","place":["Nanyang Ave, Singapore"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"843","article-title":"Unsupervised learning of video representations using LSTMs","volume-title":"Proc. 32nd Int. Conf. Int. Conf. Mach. Learn.","volume":"37","author":"Srivastava"},{"key":"ref2","first-page":"35549","article-title":"Towards video text visual question answering: Benchmark and baseline","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dai"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-41731-3_9"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3059295"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3116216"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01657-x"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01369-0"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01388-x"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3312285"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00930"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01854"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01786"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_32"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3455551"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3361076"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.207"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351093"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3038520"},{"key":"ref19","article-title":"A bilingual, OpenWorld video text dataset and end-to-end video text spotter with transformer","volume-title":"arXiv:2112.04888","author":"Wu"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3454331"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02063-1"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02112"},{"key":"ref24","article-title":"MOTRv3: Release-fetch supervision for end-to-end multi-object tracking","author":"Yu","year":"2023","journal-title":"arXiv:2305.14298"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_38"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref27","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"arXiv:2010.04159","author":"Zhu"},{"key":"ref28","article-title":"ICDAR 2023 video text reading competition for dense and small text","author":"Wu","year":"2023","journal-title":"arXiv:2304.04376"},{"key":"ref29","first-page":"25663","article-title":"GoMatching: A simple baseline for video text spotting via long and short term matching","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Du"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_41"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3077555"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3107437"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3068133"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3431993"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00857"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.02.002"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1155\/2008\/246309"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_2"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.221"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"ref43","article-title":"Decoupled weight decay regularization","volume-title":"arXiv:1711.05101","author":"Loshchilov"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6812"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2956516"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_11"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_1"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref49","article-title":"BoT-SORT: Robust associations multi-pedestrian tracking","author":"Aharon","year":"2022","journal-title":"arXiv:2206.14651"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3124313"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11679504\/11498383.pdf?arnumber=11498383","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T19:02:56Z","timestamp":1788807776000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11498383\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":50,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3688478","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9]]}}}