{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T15:27:50Z","timestamp":1780500470751,"version":"3.54.1"},"reference-count":142,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"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":["62306251"],"award-info":[{"award-number":["62306251"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Hong Kong Research Grants Council - Early Career Scheme","award":["27208022"],"award-info":[{"award-number":["27208022"]}]},{"name":"Hong Kong Research Grants Council - General Research Fund","award":["17211024"],"award-info":[{"award-number":["17211024"]}]},{"name":"HKU Seed Fund for Basic Research"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/tpami.2025.3640429","type":"journal-article","created":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T18:37:06Z","timestamp":1764873426000},"page":"3911-3930","source":"Crossref","is-referenced-by-count":3,"title":["Semantic Correspondence: Unified Benchmarking and a Strong Baseline"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-3359-4649","authenticated-orcid":false,"given":"Kaiyan","family":"Zhang","sequence":"first","affiliation":[{"name":"University of Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3797-5082","authenticated-orcid":false,"given":"Xinghui","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Engineering, University of Oxford, Oxford, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1373-231X","authenticated-orcid":false,"given":"Jingyi","family":"Lu","sequence":"additional","affiliation":[{"name":"University of Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7995-9999","authenticated-orcid":false,"given":"Kai","family":"Han","sequence":"additional","affiliation":[{"name":"University of Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00238"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3013620"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.147"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00584"},{"key":"ref5","first-page":"20637","article-title":"TokenFlow: Consistent diffusion features for consistent video editing","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Geyer","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_14"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01859"},{"key":"ref8","first-page":"8098","article-title":"DragonDiffusion: Enabling drag-style manipulation on diffusion models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mou","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298724"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.203"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.73"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00349"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_21"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00210"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00021"},{"key":"ref17","first-page":"1658","article-title":"Neighbourhood consensus networks","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Rocco","year":"2018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00296"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01295"},{"key":"ref21","first-page":"9011","article-title":"CATS: Cost aggregation transformers for visual correspondence","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cho","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3218727"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00850"},{"key":"ref24","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref26","first-page":"1363","article-title":"Emergent correspondence from image diffusion","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tang","year":"2023"},{"key":"ref27","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","year":"2023"},{"key":"ref28","article-title":"Dinov 3","author":"Sim\u00e9oni","year":"2025"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02602"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00297"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00658"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00114"},{"key":"ref33","article-title":"Jamais VU: Exposing the generalization gap in supervised semantic correspondence","volume-title":"Proc. 39th Annu. Conf. Neural Inf. Process. Syst.","author":"Mariotti","year":"2025"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01081"},{"key":"ref35","article-title":"Towards robust semantic correspondence: A benchmark and insights","author":"Chong","year":"2025"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511811685"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01359-2"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1098\/rspb.1979.0029"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(81)90024-2"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1023\/b:visi.0000029664.99615.94"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2005.10"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383149"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2007.09.014"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126544"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.299"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.435"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.77"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.378"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2724510"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126445"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247701"},{"key":"ref52","first-page":"2414","article-title":"Universal correspondence network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Choy","year":"2016"},{"key":"ref53","first-page":"1601","article-title":"Do convnets learn correspondence?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Long","year":"2014"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298642"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00334"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.125476"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01613"},{"key":"ref58","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","year":"2023"},{"key":"ref59","article-title":"Simsc: A simple framework for semantic correspondence with temperature learning","author":"Li","year":"2023"},{"key":"ref60","first-page":"8266","article-title":"Unsupervised semantic correspondence using stable diffusion","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hedlin","year":"2024"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72667-5_7"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(77)90026-1"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref64","first-page":"611","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gal","year":"2021"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00020"},{"key":"ref66","article-title":"Unleashing diffusion transformers for visual correspondence by modulating massive activations","volume-title":"Proc. 39th Annu. Conf. Neural Inf. Process. Syst.","author":"Gan","year":"2025"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_16"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00629"},{"key":"ref69","article-title":"Deep VIT features as dense visual descriptors","author":"Amir","year":"2022","journal-title":"ECCVW What is Motion For?"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.628"},{"key":"ref71","article-title":"Integrative feature and cost aggregation with transformers for dense correspondence","author":"Hong","year":"2022"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01018"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3316770"},{"key":"ref74","first-page":"17346","article-title":"Dual-resolution correspondence networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li","year":"2020"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01706"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_38"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01908"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_16"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01262"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72920-1_9"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3233884"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00723"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.485"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.302"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459459"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45479-9_20"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.5244\/C.25.14"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref89","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref91","first-page":"894","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu","year":"2021"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00881"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_7"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref95","first-page":"13512","article-title":"Neural matching fields: Implicit representation of matching fields for visual correspondence","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hong","year":"2022"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.12"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_22"},{"key":"ref98","first-page":"6129","article-title":"Recurrent transformer networks for semantic correspondence","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kim","year":"2018"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_22"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_35"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01489"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298723"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00118"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20893-6_22"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00100"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00851"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.20"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00742"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.4135\/9781071810118"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-0960-4_28"},{"key":"ref113","first-page":"5834","article-title":"Do it yourself: Learning semantic correspondence from pseudo-labels","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"D\u00fcnkel","year":"2025"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.79"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.254"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.460"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10593-2_31"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.253"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref122","article-title":"Caltech-256 object category dataset","author":"Griffin","year":"2007","journal-title":"California Inst. Technol."},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.11"},{"key":"ref124","article-title":"SPair-71k: A large-scale benchmark for semantic correspondence","author":"Min","year":"2019"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2014.6836101"},{"key":"ref126","article-title":"Ap-10k: A benchmark for animal pose estimation in the wild","volume-title":"Proc. Neural Inf. Process. Syst. Track Datasets Benchmarks","volume":"1","author":"Yu","year":"2021"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2857768"},{"key":"ref128","article-title":"African wildlife","author":"Ferreira","year":"2021"},{"key":"ref129","article-title":"Wild cats","author":"\u0160ahovi\u0107","year":"2020"},{"key":"ref130","article-title":"Animals 5","author":"Trivedi","year":"2020"},{"key":"ref131","article-title":"Animal image dataset (dog, cat and panda)","author":"Saxena","year":"2019"},{"key":"ref132","article-title":"Animals 10","author":"Alessio","year":"2019"},{"key":"ref133","article-title":"IUCN animals dataset","year":"2021"},{"key":"ref134","article-title":"Endangered animals","author":"Jamil","year":"2020"},{"key":"ref135","first-page":"4732","article-title":"Unifying feature and cost aggregation with transformers for semantic and visual correspondence","author":"Hong","year":"2024"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_8"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00382"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00452"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref141","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref142","article-title":"IBOT: Image BERT pre-training with online Tokenizer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhou","year":"2022"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11372200\/11277385.pdf?arnumber=11277385","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:05:17Z","timestamp":1770671117000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11277385\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":142,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3640429","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}