{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:28:52Z","timestamp":1761895732992,"version":"build-2065373602"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209790","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Optimization of Multimodal Inputs Based on Diffusion Models: Zero-Shot Semantic Image Generation"],"prefix":"10.1109","author":[{"given":"Leilei","family":"Wang","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Renjie","family":"Lu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fengzhao","family":"Sun","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunxiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Yu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingsong","family":"Liu","sequence":"additional","affiliation":[{"name":"Unisound AI Technology Co., Ltd.,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sun","family":"Jianqing","sequence":"additional","affiliation":[{"name":"Unisound AI Technology Co., Ltd.,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Jiaen","sequence":"additional","affiliation":[{"name":"Unisound AI Technology Co., Ltd.,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00187"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref3","first-page":"16331","article-title":"Editgan: High-precision semantic image editing","volume":"34","author":"Ling","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01253"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"article-title":"Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models","year":"2023","author":"Ye","key":"ref10"},{"article-title":"Auto-encoding variational bayes","year":"2013","author":"Kingma","key":"ref11"},{"key":"ref12","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref13","first-page":"12888","article-title":"Blip: Bootstrapping language-image pretraining for unified vision-language understanding and generation","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01370"},{"key":"ref15","article-title":"Freemask: Synthetic images with dense annotations make stronger segmentation models","volume":"36","author":"Yang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref18","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00917"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00244"},{"key":"ref21","article-title":"Learning to predict layout-to-image conditional convolutions for semantic image synthesis","volume":"32","author":"Liu","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00789"},{"article-title":"You only need adversarial supervision for semantic image synthesis","year":"2021","author":"Sch\u00f6nfeld","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01349"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01093"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01094"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3298721"},{"article-title":"Semantic image synthesis via diffusion models","year":"2022","author":"Wang","key":"ref28"},{"article-title":"Pretraining is all you need for image-to-image translation","year":"2022","author":"Wang","key":"ref29"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209790.pdf?arnumber=11209790","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:58:12Z","timestamp":1761890292000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209790\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209790","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}