{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:00:53Z","timestamp":1777888853617,"version":"3.51.4"},"reference-count":74,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":["U24B20151"],"award-info":[{"award-number":["U24B20151"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02288","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"24677-24687","source":"Crossref","is-referenced-by-count":1,"title":["CorrCLIP: Reconstructing Patch Correlations in CLIP for Open-Vocabulary Semantic Segmentation"],"prefix":"10.1109","author":[{"given":"Dengke","family":"Zhang","sequence":"first","affiliation":[{"name":"South China University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fagui","family":"Liu","sequence":"additional","affiliation":[{"name":"South China University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quan","family":"Tang","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2025.3639996"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00354"},{"key":"ref3","article-title":"\u201cWindow attention is bugged: How not to interpolate position embeddings.\u201d","author":"Bolya","year":"2023","journal-title":"ICLR"},{"key":"ref4","article-title":"\u201cZero-shot semantic segmentation.\u201d","author":"Bucher","year":"2019","journal-title":"NeurIPS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01074"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00394"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref12","article-title":"\u201cVision transformers need registers.\u201d","author":"Darcet","year":"2024","journal-title":"ICLR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref14","article-title":"\u201cAn image is worth 16x16 words: Transformers for image recognition at scale.\u201d","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref15","first-page":"226","article-title":"\u201cA density-based algorithm for discovering clusters in large spatial databases with noise.\u201d","author":"Ester","year":"1996","journal-title":"KDD"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref17","article-title":"\u201cData filtering networks.\u201d","author":"Fang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00495"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref21","article-title":"\u201cHrsam: Efficiently segment anything in high-resolution images.\u201d","author":"Huang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref22","first-page":"4904","article-title":"\u201cScaling up visual and vision-language representation learning with noisy text supervision.\u201d","author":"Jia","year":"2021","journal-title":"ICML"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72940-9_9"},{"key":"ref24","article-title":"\u201cSegment anything in high quality.\u201d","author":"Ke","year":"2024","journal-title":"NeurIPS"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01400"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_9"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73113-6_5"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02429"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref32","article-title":"\u201cClip surgery for better explainability with enhancement in openvocabulary tasks.\u201d","author":"Li","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00335"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref36","article-title":"\u201cVilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks.\u201d","author":"Lu","year":"2019","journal-title":"NeurIPS"},{"key":"ref37","first-page":"23033","article-title":"\u201cSegclip: Patch aggregation with learnable centers for open-vocabulary semantic segmentation.\u201d","author":"Luo","year":"2023","journal-title":"ICML"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02489"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref40","article-title":"\u201cDinov2: Learning robust visual features without supervision.\u201d","author":"Oquab","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref41","first-page":"8748","article-title":"\u201cLearning transferable visual models from natural language supervision.\u201d","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref42","article-title":"\u201cSam 2: Segment anything in images and videos.\u201d","author":"Ravi","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref43","first-page":"29441","article-title":"\u201cHiera: A hierarchical vision transformer without the bells-andwhistles.\u201d","author":"Ryali","year":"2023","journal-title":"ICML"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73016-0_9"},{"key":"ref45","article-title":"\u201cHarnessing vision foundation models for high-performance, training-free open vocabulary segmentation.\u201d","author":"Shi","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref46","first-page":"33754","article-title":"\u201cReco: Retrieve and co-segment for zero-shot transfer.\u201d","author":"Shin","year":"2022","journal-title":"NeurIPS"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.365"},{"key":"ref48","article-title":"\u201cCliper: Hierarchically improving spatial representation of clip for open-vocabulary semantic segmentation.\u201d","author":"Sun","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01251"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3534532"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_18"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00401"},{"key":"ref53","first-page":"26794","article-title":"\u201cImage-text codecomposition for text-supervised semantic segmentation.\u201d","author":"Wu","year":"2024","journal-title":"CVPR"},{"key":"ref54","article-title":"\u201cClip-dinoiser: Teaching clip a few dino tricks.\u201d","author":"Wysocza\u0144ska","year":"2024","journal-title":"ECCV"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00845"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00329"},{"key":"ref57","article-title":"\u201cRewrite caption semantics: Bridging semantic gaps for language-supervised semantic segmentation.\u201d","author":"Xing","year":"2023","journal-title":"NeurIPS"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01525"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1075"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.5040\/9798881817916.ch-004"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02789"},{"key":"ref63","first-page":"32215","article-title":"\u201cConvolutions die hard: Open-vocabulary segmentation with single frozen convolutional clip.\u201d","author":"Yu","year":"2023","journal-title":"NeurIPS"},{"key":"ref64","article-title":"\u201cFlorence: A new foundation model for computer vision.\u201d","author":"Yuan","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref66","article-title":"\u201cFaster segment anything: Towards lightweight sam for mobile applications.\u201d","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref67","article-title":"\u201cUncovering prototypical knowledge for weakly openvocabulary semantic segmentation.\u201d","author":"Zhang","year":"2023","journal-title":"NeurIPS"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00782"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.221"},{"key":"ref70","article-title":"\u201cFast segment anything.\u201d","author":"Zhao","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"ref73","article-title":"\u201cEdgesam: Prompt-in-the-loop distillation for on-device deployment of sam.\u201d","author":"Zhou","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref74","article-title":"\u201cibot: Image bert pre-training with online tokenizer.\u201d","author":"Zhou","year":"2022","journal-title":"ICLR"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444983.pdf?arnumber=11444983","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:59:59Z","timestamp":1777611599000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444983\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02288","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}