{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:51:16Z","timestamp":1777654276413,"version":"3.51.4"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3418210","type":"journal-article","created":{"date-parts":[[2024,6,24]],"date-time":"2024-06-24T20:08:16Z","timestamp":1719259696000},"page":"88322-88331","source":"Crossref","is-referenced-by-count":4,"title":["TAG: Guidance-Free Open-Vocabulary Semantic Segmentation"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2252-1910","authenticated-orcid":false,"given":"Yasufumi","family":"Kawano","sequence":"first","affiliation":[{"name":"Graduate School of Integrated Design Engineering, Keio University, Kanagawa, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7361-0027","authenticated-orcid":false,"given":"Yoshimitsu","family":"Aoki","sequence":"additional","affiliation":[{"name":"Graduate School of Integrated Design Engineering, Keio University, Kanagawa, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01652"},{"key":"ref2","article-title":"Unsupervised semantic segmentation by distilling feature correspondences","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hamilton"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01872"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref5","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv:2304.07193"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"ref10","article-title":"Open-vocabulary universal image segmentation with MaskCLIP","author":"Ding","year":"2022","journal-title":"arXiv:2208.08984"},{"key":"ref11","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017","journal-title":"arXiv:1706.05587"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref13","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":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00113"},{"issue":"8","key":"ref15","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref16","article-title":"Auto-vocabulary semantic segmentation","author":"\u00dclger","year":"2023","journal-title":"arXiv:2312.04539"},{"key":"ref17","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":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01451"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"ref21","volume-title":"FreebSD. Web2 Dictionary (Revision 326913)","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref23","article-title":"Vocabulary-free image classification","author":"Conti","year":"2023","journal-title":"arXiv:2306.00917"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref26","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00996"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00695"},{"key":"ref29","first-page":"33754","article-title":"ReCo: Retrieve and co-segment for zero-shot transfer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Shin"},{"key":"ref30","article-title":"Zero-shot semantic segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Bucher"},{"key":"ref31","article-title":"Segment everything everywhere all at once","author":"Zou","year":"2023","journal-title":"arXiv:2304.06718"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00845"},{"key":"ref33","article-title":"Language-driven semantic segmentation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00111"},{"key":"ref35","article-title":"Grounding everything: Emerging localization properties in vision-language transformers","author":"Bousselham","year":"2023","journal-title":"arXiv:2312.00878"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01739"},{"key":"ref37","first-page":"2206","article-title":"Improving language models by retrieving from trillions of tokens","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","volume":"162","author":"Borgeaud"},{"key":"ref38","first-page":"3929","article-title":"Retrieval augmented language model pre-training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Guu"},{"key":"ref39","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Lewis"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00683"},{"key":"ref41","volume-title":"NLP Library Flair","year":"2024"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10568947.pdf?arnumber=10568947","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,28]],"date-time":"2024-06-28T18:44:01Z","timestamp":1719600241000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10568947\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3418210","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}