{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T22:41:09Z","timestamp":1769640069957,"version":"3.49.0"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62003286"],"award-info":[{"award-number":["62003286"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Lab","award":["2021NL0AB01"],"award-info":[{"award-number":["2021NL0AB01"]}]},{"name":"CCF-Baidu Open Fund","award":["182215PCK04183"],"award-info":[{"award-number":["182215PCK04183"]}]},{"name":"HK PolyU","award":["P0034801"],"award-info":[{"award-number":["P0034801"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1109\/tcsvt.2023.3288370","type":"journal-article","created":{"date-parts":[[2023,6,23]],"date-time":"2023-06-23T21:41:19Z","timestamp":1687556479000},"page":"897-910","source":"Crossref","is-referenced-by-count":3,"title":["Learning Semantic Alignment Using Global Features and Multi-Scale Confidence"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2017-5484","authenticated-orcid":false,"given":"Huaiyuan","family":"Xu","sequence":"first","affiliation":[{"name":"Department of Mechanical Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7014-5377","authenticated-orcid":false,"given":"Jing","family":"Liao","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Kowloon, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4042-6044","authenticated-orcid":false,"given":"Huaping","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Institute for Artificial Intelligence, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7704-0559","authenticated-orcid":false,"given":"Yuxiang","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3133353"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3102109"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3135440"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3130281"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073683"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3001536"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00817"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201365"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.12"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_22"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00210"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00452"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_21"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01295"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00742"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00334"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00519"},{"key":"ref20","first-page":"1601","article-title":"Do convnets learn correspondence?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Long"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.20"},{"key":"ref22","first-page":"1658","article-title":"Neighbourhood consensus networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Rocco"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15558-1_3"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00238"},{"key":"ref25","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref26","first-page":"1","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics, Hum. Lang. Technol.","author":"Devlin"},{"key":"ref27","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref30","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3181490"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2724510"},{"key":"ref34","article-title":"SPair-71k: A large-scale benchmark for semantic correspondence","author":"Min","year":"2019","journal-title":"arXiv:1908.10543"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01029"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20893-6_22"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00349"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00851"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_8"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00296"},{"key":"ref42","first-page":"9011","article-title":"CATs: Cost aggregation transformers for visual correspondence","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Cho"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01908"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00850"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.261"},{"key":"ref46","first-page":"2414","article-title":"Universal correspondence network","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Choy"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.378"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.79"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.460"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206536"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.136"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10422872\/10159138.pdf?arnumber=10159138","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T20:37:51Z","timestamp":1736368671000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10159138\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2]]},"references-count":52,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3288370","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2]]}}}