{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T16:53:41Z","timestamp":1792515221049,"version":"4.5.0"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888502","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:56:59Z","timestamp":1741787819000},"page":"1-5","source":"Crossref","is-referenced-by-count":4,"title":["Seg-diffusion: Text-to-Image Diffusion Model for Open-Vocabulary Semantic Segmentation"],"prefix":"10.1109","author":[{"given":"Shuo","family":"Zhang","sequence":"first","affiliation":[{"name":"East China Normal University,Shanghai Key Laboratory of Trustworthy Computing,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaming","family":"Huang","sequence":"additional","affiliation":[{"name":"Huolala,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Wu","sequence":"additional","affiliation":[{"name":"Huolala,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Hu","sequence":"additional","affiliation":[{"name":"Huolala,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenbing","family":"Tang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,College of Computing and Data Science,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Liu","sequence":"additional","affiliation":[{"name":"East China Normal University,Shanghai Key Laboratory of Trustworthy Computing,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00292"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00207"},{"key":"ref3","first-page":"468","article-title":"Zero-shot semantic segmentation","volume":"32","author":"Bucher","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref4","article-title":"Open-vocabulary semantic segmentation via attribute decomposition-aggregation","volume":"36","author":"Ma","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref5","article-title":"Convolutions die hard: Open-vocabulary segmentation with single frozen convolutional clip","volume":"36","author":"Yu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3361862"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3413013"},{"key":"ref8","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref9","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"International conference on machine learning","author":"Jia"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.357"},{"issue":"2","key":"ref11","first-page":"3","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022"},{"key":"ref12","article-title":"ediff-i: Text-to-image diffusion models with an ensemble of expert denoisers","author":"Balaji","year":"2022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01738"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00705"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00117"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref19","article-title":"Swift sampler: Efficient learning of sampler by 10 parameters","author":"Yao","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680807"},{"key":"ref21","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref23","first-page":"25 278","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","volume":"35","author":"Schuhmann","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref24","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00394"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref30","article-title":"Progressive distillation for fast sampling of diffusion models","volume-title":"International Conference on Learning Representations","author":"Salimans"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00845"},{"key":"ref32","first-page":"1","article-title":"Language-driven semantic segmentation","volume-title":"International Conference on Learning Representations","author":"Li"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00080"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01129"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_42"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00106"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01860"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00329"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888502.pdf?arnumber=10888502","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:40Z","timestamp":1774416220000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888502\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888502","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}