{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T10:26:12Z","timestamp":1780395972477,"version":"3.54.1"},"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.2024.3456442","type":"journal-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:52:26Z","timestamp":1725904346000},"page":"127283-127293","source":"Crossref","is-referenced-by-count":12,"title":["MaskDiffusion: Exploiting Pre-Trained Diffusion Models for 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":[{"vocabulary":"crossref","role":"author"}]},{"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":[{"vocabulary":"crossref","role":"author"}]}],"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","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"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.","author":"Radford"},{"key":"ref14","article-title":"Diffuse, attend, and segment: Unsupervised zero-shot segmentation using stable diffusion","author":"Tian","year":"2023","journal-title":"arXiv:2308.12469"},{"key":"ref15","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho"},{"key":"ref16","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Saharia"},{"key":"ref17","article-title":"Label-efficient semantic segmentation with diffusion models","author":"Baranchuk","year":"2021","journal-title":"arXiv:2112.03126"},{"key":"ref18","article-title":"SegDiff: Image segmentation with diffusion probabilistic models","author":"Amit","year":"2021","journal-title":"arXiv:2112.00390"},{"key":"ref19","article-title":"Grounding everything: Emerging localization properties in vision-language transformers","author":"Bousselham","year":"2023","journal-title":"arXiv:2312.00878"},{"key":"ref20","first-page":"58921","article-title":"Text-to-image diffusion models are zero shot classifiers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Clark"},{"key":"ref21","first-page":"1","article-title":"On spectral clustering: Analysis and an algorithm","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ng"},{"key":"ref22","volume-title":"ISPRS, 2D Semantic Labeling Contest"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref26","article-title":"LAION-400M: Open dataset of CLIP-filtered 400 million image-text pairs","author":"Schuhmann","year":"2021","journal-title":"arXiv:2111.02114"},{"key":"ref27","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017","journal-title":"arXiv:1706.05587"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00996"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00695"},{"key":"ref32","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":"ref33","first-page":"1","article-title":"Zero-shot semantic segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bucher"},{"key":"ref34","article-title":"Segment everything everywhere all at once","author":"Zou","year":"2023","journal-title":"arXiv:2304.06718"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02260"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00445"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref39","article-title":"Semantic segmentation by improved generative adversarial networks","author":"Zhaoa","year":"2021","journal-title":"arXiv:2104.09917"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00820"},{"key":"ref41","article-title":"A tale of two features: Stable diffusion complements DINO for zero-shot semantic correspondence","author":"Zhang","year":"2023","journal-title":"arXiv:2305.15347"},{"key":"ref42","article-title":"DifFSS: Diffusion model for few-shot semantic segmentation","author":"Tan","year":"2023","journal-title":"arXiv:2307.00773"},{"key":"ref43","first-page":"1336","article-title":"Diffusion models for implicit image segmentation ensembles","volume-title":"Proc. Int. Conf. Med. Imag. With Deep Learn.","author":"Wolleb"},{"key":"ref44","first-page":"1","article-title":"DifNet: Semantic segmentation by diffusion networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Jiang"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00117"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10669545.pdf?arnumber=10669545","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,18]],"date-time":"2024-09-18T06:34:36Z","timestamp":1726641276000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10669545\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3456442","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}