{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,20]],"date-time":"2025-08-20T12:45:46Z","timestamp":1755693946128,"version":"3.37.3"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10448330","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"4310-4314","source":"Crossref","is-referenced-by-count":2,"title":["Bridging the Gap: Sketch to Color Diffusion Model with Semantic Prompt Learning"],"prefix":"10.1109","author":[{"given":"Ning","family":"Wang","sequence":"first","affiliation":[{"name":"Dalian University of Technology"}]},{"given":"Yifei","family":"She","sequence":"additional","affiliation":[{"name":"Dalian University of Technology"}]},{"given":"Rui","family":"Xu","sequence":"additional","affiliation":[{"name":"Dalian University of Technology"}]},{"given":"Bin","family":"Liu","sequence":"additional","affiliation":[{"name":"Dalian University of Technology"}]},{"given":"Haojie","family":"Li","sequence":"additional","affiliation":[{"name":"Dalian University of Technology"}]},{"given":"Zhiyong","family":"Wang","sequence":"additional","affiliation":[{"name":"The University of Sydney"}]},{"given":"Zhihui","family":"Wang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology"}]}],"member":"263","reference":[{"article-title":"Large scale GAN training for high fidelity natural image synthesis","volume-title":"7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019","author":"Brock","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683686"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3117061"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275090"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240661"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3104190"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01464"},{"key":"ref9","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref10","article-title":"Generating diverse high-fidelity images with vq-vae-2","volume":"32","author":"Razavi","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref11","first-page":"16784","article-title":"GLIDE: towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"International Conference on Machine Learning, ICML 2022","volume":"162","author":"Nichol"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261988"},{"article-title":"Pretraining is all you need for image-to-image translation","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Wang","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref15","article-title":"T2i-adapter: Learning adapters to dig out more controllable ability for text-to-image diffusion models","author":"Mou","year":"2023","journal-title":"CoRR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.23940\/ijpe.19.03.p20.910918"},{"article-title":"Danbooru2020: A large-scale crowdsourced and tagged anime illustration dataset","year":"2021","author":"Community","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2012.03.004"},{"article-title":"Deepdanbooru","year":"2019","author":"Kim","key":"ref19"},{"key":"ref20","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"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10448330.pdf?arnumber=10448330","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,3]],"date-time":"2024-08-03T04:52:25Z","timestamp":1722660745000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448330\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448330","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}