{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T02:51:40Z","timestamp":1784429500346,"version":"3.55.0"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100004405","name":"Japan Society for the Promotion of Science (JSPS) KAKENHI","doi-asserted-by":"publisher","award":["23K28164"],"award-info":[{"award-number":["23K28164"]}],"id":[{"id":"10.13039\/501100004405","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004405","name":"Japan Science and Technology Agency","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004405","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004405","name":"Core Research for Evolutionary Science and Technology","doi-asserted-by":"publisher","award":["JPMJCR22D1"],"award-info":[{"award-number":["JPMJCR22D1"]}],"id":[{"id":"10.13039\/501100004405","id-type":"DOI","asserted-by":"publisher"}]},{"name":"JST CREST","award":["JPMJCR22D1"],"award-info":[{"award-number":["JPMJCR22D1"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/tcsvt.2025.3616588","type":"journal-article","created":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T17:40:45Z","timestamp":1759340445000},"page":"3665-3678","source":"Crossref","is-referenced-by-count":4,"title":["CLIP-to-Seg Distillation for Zero-Shot Semantic Segmentation"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-0654-4281","authenticated-orcid":false,"given":"Jialei","family":"Chen","sequence":"first","affiliation":[{"name":"Graduate School of Informatics, Nagoya University, Nagoya, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenzhen","family":"Quan","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Shandong University, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7258-272X","authenticated-orcid":false,"given":"Chenkai","family":"Zhang","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Nagoya University, Nagoya, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4008-8951","authenticated-orcid":false,"given":"Xu","family":"Zheng","sequence":"additional","affiliation":[{"name":"AI Thrust, The Hong Kong University of Science and Technology, Guangzhou Campus (HKUST-GZ), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0603-8790","authenticated-orcid":false,"given":"Daisuke","family":"Deguchi","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Nagoya University, Nagoya, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8103-9294","authenticated-orcid":false,"given":"Hiroshi","family":"Murase","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Nagoya University, Nagoya, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110431"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.111029"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3536086"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01129"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01075"},{"key":"ref6","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3524784"},{"key":"ref8","first-page":"1","article-title":"CLIPSelf: Vision transformer distills itself for open-vocabulary dense prediction","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Wu"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00106"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00315"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3504816"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_42"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00080"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00623"},{"key":"ref16","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xie"},{"key":"ref17","first-page":"1140","article-title":"SegNeXt: Rethinking convolutional attention design for semantic segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Guo"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref22","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref25","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume-title":"Proc. NIPS","author":"Cheng"},{"key":"ref26","first-page":"1","article-title":"FROSTER: Frozen CLIP is a strong teacher for open-vocabulary action recognition","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Huang"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01576"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3375789"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3255832"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.111095"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01081"},{"key":"ref33","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Jia"},{"key":"ref34","article-title":"Recognize anything: A strong image tagging model","author":"Zhang","year":"2023","journal-title":"arXiv:2306.03514"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01820"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413593"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref38","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref39","first-page":"1","article-title":"Language-driven semantic segmentation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"ref42","article-title":"Open-vocabulary universal image segmentation with MaskCLIP","author":"Ding","year":"2022","journal-title":"arXiv:2208.08984"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01863"},{"key":"ref44","first-page":"1","article-title":"Convolutions die hard: Open-vocabulary segmentation with single frozen convolutional CLIP","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Yu"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1549"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02640"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72940-9_9"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3361862"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_27"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_24"},{"key":"ref52","first-page":"1","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Gu"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_16"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3520734"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3364764"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00845"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref61","first-page":"1","article-title":"Zero-shot semantic segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bucher"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00942"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00940"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_12"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00145"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_20"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01368"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11424237\/11187310.pdf?arnumber=11187310","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T20:00:51Z","timestamp":1773086451000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11187310\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":71,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3616588","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}