{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T20:18:16Z","timestamp":1783455496001,"version":"3.55.0"},"reference-count":105,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2022ZD0160400"],"award-info":[{"award-number":["2022ZD0160400"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62271346"],"award-info":[{"award-number":["62271346"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206031"],"award-info":[{"award-number":["62206031"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1109\/tpami.2026.3681368","type":"journal-article","created":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T19:56:01Z","timestamp":1775505361000},"page":"9765-9781","source":"Crossref","is-referenced-by-count":1,"title":["iSeg: An Iterative Refinement-Based Framework for Training-Free Segmentation"],"prefix":"10.1109","volume":"48","author":[{"given":"Lin","family":"Sun","sequence":"first","affiliation":[{"name":"Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5160-6841","authenticated-orcid":false,"given":"Jiale","family":"Cao","sequence":"additional","affiliation":[{"name":"Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6978-8834","authenticated-orcid":false,"given":"Jin","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Big Data and Software Engineering, Chongqing University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4263-3143","authenticated-orcid":false,"given":"Fahad Shahbaz","family":"Khan","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6670-3727","authenticated-orcid":false,"given":"Yanwei","family":"Pang","sequence":"additional","affiliation":[{"name":"Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00231"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00523"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"ref4","first-page":"1","article-title":"Label-efficient semantic segmentation with diffusion models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Baranchuk","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00149"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00354"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2001.937505"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01074"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref13","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref16","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Cheng","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01652"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref19","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dhariwal","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01129"},{"key":"ref21","first-page":"1","article-title":"An image is worth 16 x 16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01178"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540073"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00069"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72890-7_15"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00544"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00996"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01987"},{"key":"ref32","article-title":"Segment anything is a good pseudo-label generator for weakly supervised semantic segmentation","author":"Jiang","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3103"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_18"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3456442"},{"key":"ref36","first-page":"1","article-title":"SLiMe: Segment like me","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Khani","year":"2024"},{"key":"ref37","first-page":"1","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2014"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01317"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01844"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2019.04.006"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00406"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref43","first-page":"1","article-title":"Language-driven semantic segmentation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2022"},{"key":"ref44","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","year":"2022"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00692"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3132068"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00705"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00539"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01469"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28139"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02037"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.l007\/978-3-319-46448-0_2"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"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","year":"2023"},{"key":"ref57","first-page":"1","article-title":"Unsupervised semantic segmentation by distilling feature correspondences","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mark","year":"2022"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3359"},{"key":"ref60","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol","year":"2022"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.203"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00149"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298780"},{"key":"ref64","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":"ref65","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00513"},{"key":"ref67","first-page":"1","article-title":"ViewCo: Discovering text-supervised segmentation masks via multi-view semantic consistency","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ren","year":"2023"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00302"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2446"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01251"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02224"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3554410"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00341"},{"key":"ref78","article-title":"Harnessing diffusion models for visual perception with meta prompts","author":"Wan","year":"2023"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_18"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00367"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00542"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3551648"},{"key":"ref83","first-page":"1336","article-title":"Diffusion models for implicit image segmentation ensembles","volume-title":"Proc. Int. Conf. Med. Imag. with Deep Learn.","author":"Wolleb","year":"2022"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00117"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/171"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73030-6_18"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128437"},{"key":"ref88","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Xie","year":"2021"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00444"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00287"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3404422"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00427"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_42"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00058"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00346"},{"key":"ref98","first-page":"7281","article-title":"HRFormer: High-resolution transformer for dense prediction","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yuan","year":"2021"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01465-9"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01919-2"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00315"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00527"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2026.3678362"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11595778\/11475541.pdf?arnumber=11475541","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T19:45:06Z","timestamp":1783453506000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11475541\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":105,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3681368","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":[[2026,8]]}}}