{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:31:14Z","timestamp":1777865474176,"version":"3.51.4"},"reference-count":59,"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":["62471405,62331003,62301451,62301613"],"award-info":[{"award-number":["62471405,62331003,62301451,62301613"]}],"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\/iccv51701.2025.01887","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"20291-20300","source":"Crossref","is-referenced-by-count":0,"title":["Feature Purification Matters: Suppressing Outlier Propagation for Training-Free Open-Vocabulary Semantic Segmentation"],"prefix":"10.1109","author":[{"given":"Shuo","family":"Jin","sequence":"first","affiliation":[{"name":"Xi'an Jiaotong-Liverpool University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siyue","family":"Yu","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong-Liverpool University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bingfeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"China University of Petroleum (East China)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingjie","family":"Sun","sequence":"additional","affiliation":[{"name":"Soochow University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Dong","sequence":"additional","affiliation":[{"name":"University of Liverpool"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jimin","family":"Xiao","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong-Liverpool University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00431"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2025.3639996"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00367"},{"key":"ref4","first-page":"468","article-title":"Zero-shot semantic segmentation","author":"Bucher","year":"2019","journal-title":"NeurIPS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01496"},{"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","first-page":"1","article-title":"Vision transformers need registers","author":"Darcet","year":"2024","journal-title":"ICLR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref14","article-title":"Openvocabulary panoptic segmentation with maskclip","author":"Ding","year":"2022","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00495"},{"key":"ref17","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"Jia","year":"2021","journal-title":"ICML"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1549"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72940-9_9"},{"key":"ref20","first-page":"299","article-title":"Diffusion models for zero-shot open-vocabulary segmentation","author":"Karazija","year":"2024","journal-title":"ECCV"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1137\/060659624"},{"key":"ref23","first-page":"109","article-title":"Efficient inference in fully connected crfs with gaussian edge potentials","author":"Kr\u00e4henb\u00fchl","year":"2011","journal-title":"NeurIPS"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_9"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73113-6_5"},{"key":"ref26","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022","journal-title":"ICML"},{"key":"ref27","first-page":"28243","article-title":"Cascade-clip: Cascaded vision-language embeddings alignment for zero-shot semantic segmentation","author":"Li","year":"2024","journal-title":"ICML"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111409"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00335"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref32","first-page":"23033","article-title":"Segclip: Patch aggregation with learnable centers for open-vocabulary semantic segmentation","author":"Luo","year":"2023","journal-title":"ICML"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00386"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref35","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01398"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00430"},{"key":"ref38","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref39","first-page":"25278","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","author":"Schuhmann","year":"2022","journal-title":"NeurIPS"},{"key":"ref40","first-page":"139","article-title":"Explore the potential of clip for training-free open vocabulary semantic segmentation","author":"Shao","year":"2024","journal-title":"ECCV"},{"key":"ref41","first-page":"33754","article-title":"Reco: Retrieve and co-segment for zero-shot transfer","author":"Shin","year":"2022","journal-title":"NeurIPS"},{"key":"ref42","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","author":"Sohl-Dickstein","year":"2015","journal-title":"ICML"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01251"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_18"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00367"},{"key":"ref47","first-page":"320","article-title":"Clip-dinoiser: Teaching clip a few dino tricks","author":"Wysocza\u0144ska","year":"2024","journal-title":"ECCV"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00329"},{"key":"ref49","first-page":"12077","article-title":"Segformer: Simple and efficient design for semantic segmentation with transformers","author":"Xie","year":"2021","journal-title":"NeurIPS"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00287"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3186512"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611951"},{"key":"ref55","article-title":"Automatically identify and rectify: Robust deep contrastive multiview clustering in noisy scenarios","author":"Yang","year":"2025","journal-title":"ICML. PMLR"},{"key":"ref56","first-page":"32215","article-title":"Convolutions die hard: Open-vocabulary segmentation with single frozen convolutional clip","author":"Yu","year":"2023","journal-title":"NeurIPS"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01075"}],"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\/11445443.pdf?arnumber=11445443","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:38:03Z","timestamp":1777531083000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445443\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01887","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}