{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T14:34:53Z","timestamp":1785249293532,"version":"3.55.0"},"reference-count":67,"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":["12326618,62206316"],"award-info":[{"award-number":["12326618,62206316"]}],"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\/iccv51701.2025.02147","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"23124-23134","source":"Crossref","is-referenced-by-count":1,"title":["Training-Free Class Purification for Open-Vocabulary Semantic Segmentation"],"prefix":"10.1109","author":[{"given":"Qi","family":"Chen","sequence":"first","affiliation":[{"name":"Sun Yat-sen University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lingxiao","family":"Yang","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yun","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Surrey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nailong","family":"Zhao","sequence":"additional","affiliation":[{"name":"Alibaba Cloud Computing"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianhuang","family":"Lai","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Shao","sequence":"additional","affiliation":[{"name":"ByteDance Intelligent Creation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohua","family":"Xie","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00523"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00431"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00354"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00367"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00132"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00116"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01074"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00356"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00071"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00425"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref15","author":"Chiang","year":"2023","journal-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90* chatgpt quality"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00394"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01129"},{"key":"ref19","first-page":"8090","article-title":"Openvocabulary universal image segmentation with maskclip","author":"Ding","year":"2023","journal-title":"Int. Conf. Mach. Learn."},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3242819"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref23","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Int. Conf. Mach. Learn.","author":"Jia","year":"2021"},{"key":"ref24","article-title":"Plug-and-play, dense-label-free extraction of open-vocabulary semantic segmentation from visionlanguage models","author":"Jiayun","year":"2024","journal-title":"IEEE Conf. Comput. Vis. Pattern Recog."},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72940-9_9"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_18"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_9"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73113-6_5"},{"key":"ref30","article-title":"Language-driven semantic segmentation","author":"Li","year":"2022","journal-title":"Int. Conf. Learn. Represent."},{"key":"ref31","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022","journal-title":"Int. Conf. Mach. Learn."},{"key":"ref32","article-title":"Clip surgery for better explainability with enhancement in openvocabulary tasks","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01469"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_16"},{"key":"ref35","first-page":"23033","article-title":"Segclip: Patch aggregation with learnable centers for open-vocabulary semantic segmentation","volume-title":"Int. Conf. Mach. Learn.","author":"Luo","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref37","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref38","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00513"},{"key":"ref40","article-title":"Viewco: Discovering text-supervised segmentation masks via multi-view semantic consistency","author":"Ren","year":"2023","journal-title":"Int. Conf. Learn. Represent."},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00113"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01634"},{"key":"ref44","article-title":"Explore the potential of clip for training-free open vocabulary semantic segmentation","author":"Shao","year":"2024","journal-title":"Eur. Conf. Comput. Vis."},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2446"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01251"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_18"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00379"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02530"},{"key":"ref50","article-title":"Clipself: Vision transformer distills itself for open-vocabulary dense prediction","author":"Wu","year":"2024","journal-title":"Int. Conf. Learn. Represent."},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73030-6_18"},{"key":"ref52","first-page":"12077","article-title":"Segformer: Simple and efficient design for semantic segmentation with transformers","author":"Xie","year":"2021","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"ref53","article-title":"Rewrite caption semantics: Bridging semantic gaps for language-supervised semantic segmentation","author":"Xing","year":"2024","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00287"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_42"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00683"},{"key":"ref60","article-title":"Convolutions die hard: Open-vocabulary segmentation with single frozen convolutional clip","author":"Yu","year":"2024","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"ref61","article-title":"Uncovering prototypical knowledge for weakly openvocabulary semantic segmentation","author":"Zhang","year":"2024","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"ref62","article-title":"Formulating discrete probability flow through optimal transport","author":"Zhang","year":"2023","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02270"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"}],"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\/11444485.pdf?arnumber=11444485","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:29:35Z","timestamp":1777613375000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444485\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02147","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}