{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T19:02:00Z","timestamp":1772823720322,"version":"3.50.1"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"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":["62271143"],"award-info":[{"award-number":["62271143"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Frontier Technologies Research and Development Program of Jiangsu","award":["BF2024060"],"award-info":[{"award-number":["BF2024060"]}]},{"name":"Shenzhen Science and Technology Program","award":["JCYJ20220530160415035"],"award-info":[{"award-number":["JCYJ20220530160415035"]}]},{"name":"Shenzhen Science and Technology Program","award":["JCYJ20240813161801002"],"award-info":[{"award-number":["JCYJ20240813161801002"]}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2025A1515011943"],"award-info":[{"award-number":["2025A1515011943"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Foundation of National Key Laboratory of Complex System Control and Intelligent Agent Cooperation","award":["2024-002"],"award-info":[{"award-number":["2024-002"]}]},{"name":"Postgraduate Research and Practice Innovation Program of Jiangsu Province","award":["SJCX25_0081"],"award-info":[{"award-number":["SJCX25_0081"]}]},{"DOI":"10.13039\/501100017703","name":"SEU Innovation Capability Enhancement Plan for Doctoral Students","doi-asserted-by":"publisher","award":["CXJH_SEU 25128"],"award-info":[{"award-number":["CXJH_SEU 25128"]}],"id":[{"id":"10.13039\/501100017703","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1109\/tcsvt.2025.3576772","type":"journal-article","created":{"date-parts":[[2025,6,5]],"date-time":"2025-06-05T13:38:57Z","timestamp":1749130737000},"page":"10875-10890","source":"Crossref","is-referenced-by-count":1,"title":["Tex2Sem: Learning From Textures to Semantics for Robust Semantic Correspondence"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0803-6206","authenticated-orcid":false,"given":"Zenghui","family":"Wang","sequence":"first","affiliation":[{"name":"School of Automation, Southeast University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4937-2713","authenticated-orcid":false,"given":"Songlin","family":"Du","sequence":"additional","affiliation":[{"name":"School of Automation, Southeast University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1933-732X","authenticated-orcid":false,"given":"Yaping","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Southeast University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2928-8100","authenticated-orcid":false,"given":"Guobao","family":"Xiao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7707-7538","authenticated-orcid":false,"given":"Xiaobo","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Automation, Southeast University, Nanjing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3248510"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3015279"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01113"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3208919"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3218727"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref9","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref10","first-page":"1363","article-title":"Emergent correspondence from image diffusion","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tang"},{"key":"ref11","first-page":"47500","article-title":"Diffusion hyperfeatures: Searching through time and space for semantic correspondence","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Luo"},{"key":"ref12","first-page":"45533","article-title":"A tale of two features: Stable diffusion complements DINO for zero-shot semantic correspondence","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02602"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00297"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref16","first-page":"10041","article-title":"Transformers are SSMs: Generalized models and efficient algorithms through structured state space duality","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"235","author":"Dao"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.147"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i7.16760"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9411961"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3177320"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73383-3_7"},{"key":"ref22","first-page":"9011","article-title":"CATs: Cost aggregation transformers for visual correspondence","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cho"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01706"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_8"},{"key":"ref25","first-page":"8266","article-title":"Unsupervised semantic correspondence using stable diffusion","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hedlin"},{"key":"ref26","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01846"},{"key":"ref29","first-page":"1","article-title":"Efficiently modeling long sequences with structured state spaces","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Gu"},{"key":"ref30","first-page":"35971","article-title":"On the parameterization and initialization of diagonal state space models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gu"},{"key":"ref31","first-page":"1","article-title":"Simplified state space layers for sequence modeling","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Smith"},{"key":"ref32","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv:2312.00752"},{"key":"ref33","first-page":"103031","article-title":"VMamba: Visual state space model","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3508058"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_9"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3530090"},{"key":"ref37","article-title":"Dimba: Transformer-mamba diffusion models","author":"Fei","year":"2024","journal-title":"arXiv:2406.01159"},{"key":"ref38","article-title":"MambaVision: A hybrid mamba-transformer vision backbone","author":"Hatamizadeh","year":"2024","journal-title":"arXiv:2407.08083"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00881"},{"key":"ref41","first-page":"1","article-title":"Root mean square layer normalization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref42","first-page":"5156","article-title":"Transformers are RNNs: Fast autoregressive transformers with linear attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Katharopoulos"},{"key":"ref43","article-title":"Fast and accurate deep network learning by exponential linear units (ELUs)","author":"Clevert","year":"2015","journal-title":"arXiv:1511.07289"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00382"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01859"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_16"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01295"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00452"},{"key":"ref49","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00238"},{"key":"ref51","article-title":"SPair-71k: A large-scale benchmark for semantic correspondence","author":"Min","year":"2019","journal-title":"arXiv:1908.10543"},{"key":"ref52","first-page":"1","article-title":"AP-10k: A benchmark for animal pose estimation in the wild","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Yu"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2724510"},{"key":"ref54","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Loshchilov"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1117\/12.2520589"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3213677"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.261"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01613"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00218"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72949-2_22"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01492"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11223720\/11025852.pdf?arnumber=11025852","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T18:47:13Z","timestamp":1762195633000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11025852\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":62,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3576772","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11]]}}}