{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:17:26Z","timestamp":1778080646851,"version":"3.51.4"},"reference-count":87,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100019014","name":"Shenzhen Science and Technology Program","doi-asserted-by":"publisher","award":["CJGJZD20220517142402006"],"award-info":[{"award-number":["CJGJZD20220517142402006"]}],"id":[{"id":"10.13039\/501100019014","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206153"],"award-info":[{"award-number":["62206153"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2025.3639996","type":"journal-article","created":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T18:34:53Z","timestamp":1765391693000},"page":"8271-8284","source":"Crossref","is-referenced-by-count":12,"title":["Self-Calibrated CLIP for Training-Free Open-Vocabulary Segmentation"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-3259-9081","authenticated-orcid":false,"given":"Sule","family":"Bai","sequence":"first","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3078-1598","authenticated-orcid":false,"given":"Yong","family":"Liu","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifei","family":"Han","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6132-5417","authenticated-orcid":false,"given":"Haoji","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1534-4549","authenticated-orcid":false,"given":"Yansong","family":"Tang","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7701-234X","authenticated-orcid":false,"given":"Jie","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6121-5529","authenticated-orcid":false,"given":"Jiwen","family":"Lu","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_18"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00367"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111409"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_9"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00495"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72940-9_9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73016-0_9"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73113-6_5"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73030-6_18"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"issue":"4","key":"ref16","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1002\/wics.101","article-title":"Principal component analysis","volume":"2","author":"Wold","year":"2010","journal-title":"Wiley Interdiscipl. Reviews, Comput. Statist."},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/335191.335388"},{"key":"ref18","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia"},{"key":"ref19","article-title":"CoCa: Contrastive captioners are image-text foundation models","volume":"2022","author":"Yu","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref20","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.5040\/9798881817916.ch-004"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_38"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.378"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3361862"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3567828"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3485518"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3371348"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3459589"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_24"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00332"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3554410"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3434373"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3205207"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3551648"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_42"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01129"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00335"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00080"},{"key":"ref44","first-page":"32215","article-title":"Convolutions die hard: Open-vocabulary segmentation with single frozen convolutional CLIP","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Yu"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00329"},{"key":"ref46","article-title":"Language-driven semantic segmentation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00394"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00088"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01863"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3562930"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02640"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01860"},{"key":"ref53","article-title":"ViewCo: Discovering text-supervised segmentation masks via multi-view semantic consistency","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ren"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01074"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref56","first-page":"23033","article-title":"SegCLIP: Patch aggregation with learnable centers for open-vocabulary semantic segmentation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Luo"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00287"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01078"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3359041"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00354"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00143"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28139"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01251"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref65","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":"ref66","article-title":"Vision transformers need registers","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Darcet"},{"key":"ref67","article-title":"Efficient streaming language models with attention sinks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Xiao"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref70","first-page":"28243","article-title":"Cascade-CLIP: Cascaded vision-language embeddings alignment for zero-shot semantic segmentation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref71","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Xie"},{"key":"ref72","first-page":"1140","article-title":"SegNeXt: Rethinking convolutional attention design for semantic segmentation","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Guo"},{"issue":"1","key":"ref73","first-page":"5","article-title":"The Pascal visual object classes challenge 2012 (voc2012) development kit","volume":"2007","author":"Everingham","year":"2012","journal-title":"Pattern Anal. Stat. Model. Comput. Learn., Tech. Rep"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref76","first-page":"33754","article-title":"ReCo: Retrieve and co-segment for zero-shot transfer","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Shin"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01414"},{"key":"ref78","first-page":"73299","article-title":"What a MESS: Multi-domain evaluation of zero-shot semantic segmentation","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Blumenstiel"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.365"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref81","first-page":"68367","article-title":"OpenMask3D: Open-vocabulary 3D instance segmentation","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Takmaz"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_10"},{"key":"ref83","first-page":"71862","article-title":"CoDA: Collaborative novel box discovery and cross-modal alignment for open-vocabulary 3D object detection","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Cao"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_22"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/11291123.pdf?arnumber=11291123","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T18:44:35Z","timestamp":1766429075000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11291123\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":87,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3639996","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}