{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T20:07:02Z","timestamp":1780949222966,"version":"3.54.1"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2022ZD0160101"],"award-info":[{"award-number":["2022ZD0160101"]}]},{"name":"Ningbo Science and the National Natural Science Foundation of China","award":["62206244"],"award-info":[{"award-number":["62206244"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/tcsvt.2026.3662405","type":"journal-article","created":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:09:48Z","timestamp":1770671388000},"page":"8845-8858","source":"Crossref","is-referenced-by-count":0,"title":["Zippo: RGB-Alpha Joint Modeling With a Unified Diffusion Model"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-1048-1274","authenticated-orcid":false,"given":"Kangyang","family":"Xie","sequence":"first","affiliation":[{"name":"State Key Lab of CAD and CG, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2143-2836","authenticated-orcid":false,"given":"Binbin","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Sun Yat-Sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenchen","family":"Jing","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7006-1728","authenticated-orcid":false,"given":"Cheng","family":"Peng","sequence":"additional","affiliation":[{"name":"State Key Lab of CAD and CG, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng","family":"Wang","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4527-7535","authenticated-orcid":false,"given":"Cheng","family":"Zou","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1691-6817","authenticated-orcid":false,"given":"Ming","family":"Yang","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0963-0311","authenticated-orcid":false,"given":"Heqian","family":"Qiu","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7481-095X","authenticated-orcid":false,"given":"Hongliang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4417-614X","authenticated-orcid":false,"given":"Hao","family":"Chen","sequence":"additional","affiliation":[{"name":"State Key Lab of CAD and CG, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73113-6_23"},{"key":"ref2","article-title":"Text2Layer: Layered image generation using latent diffusion model","author":"Zhang","year":"2023","journal-title":"arXiv:2307.09781"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00321"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3658150"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2537"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102091"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.41"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3132461"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01140"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00336"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3452512"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3234983"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19999"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00411"},{"key":"ref15","article-title":"PP-matting: High-accuracy natural image matting","author":"Chen","year":"2022","journal-title":"arXiv:2204.09433"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3585899"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3504838"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3306400"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.32"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1177"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995495"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3260025"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383006"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3300731"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3361181"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3387451"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3231964"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01987"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"ref31","article-title":"Matcher: Segment anything with one shot using all-purpose feature matching","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Liu"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3195"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"ref34","article-title":"Harnessing diffusion models for visual perception with meta prompts","author":"Wan","year":"2023","journal-title":"arXiv:2312.14733"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_5"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00603"},{"key":"ref37","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref40","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv:2207.12598"},{"key":"ref41","first-page":"25278","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Schuhmann"},{"key":"ref42","article-title":"Qwen2.5-VL technical report","volume-title":"arXiv:2502.13923","author":"Bai","year":"2025"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475512"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/111"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01541-0"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00371"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref48","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref49","first-page":"6626","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Heusel"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01797-8"},{"key":"ref51","article-title":"Adversarially-guided portrait matting","author":"Chicherin","year":"2023","journal-title":"arXiv:2305.02981"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00765"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01369"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240610"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00865"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00684"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107404"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11552944\/11381991.pdf?arnumber=11381991","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T19:54:50Z","timestamp":1780948490000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11381991\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":58,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3662405","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}