{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:13:54Z","timestamp":1774419234505,"version":"3.50.1"},"reference-count":48,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888355","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["GoLoColor: Towards Global-Local Semantic Aware Image Colorization"],"prefix":"10.1109","author":[{"given":"Tianai","family":"Yue","sequence":"first","affiliation":[{"name":"Johns Hopkins University,Baltimore,MD,USA"}]},{"given":"Xiangcheng","family":"Du","sequence":"additional","affiliation":[{"name":"Fudan University,Shanghai,China"}]},{"given":"Jing","family":"Liu","sequence":"additional","affiliation":[{"name":"Capital Medical University,Beijing Chest Hospital,Beijing,China"}]},{"given":"Zhongli","family":"Fang","sequence":"additional","affiliation":[{"name":"Fudan University,Shanghai,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00282"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1141911.1142017"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356570"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618180"},{"key":"ref5","article-title":"Improved diffusion-based image colorization via piggybacked models","author":"Liu","year":"2023"},{"key":"ref6","article-title":"Control color: Multimodal diffusion-based interactive image colorization","author":"Liang","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.55"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093389"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3117061"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01411"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_21"},{"key":"ref14","article-title":"Large scale gan training for high fidelity natural image synthesis","volume-title":"ICLR","author":"Brock"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref16","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_2"},{"key":"ref18","first-page":"1","article-title":"Ct2: Colorization transformer via color tokens","volume-title":"ECCV","author":"Weng"},{"key":"ref19","article-title":"L-cad: Language-based colorization with any-level descriptions","author":"Chang","year":"2023","journal-title":"NeurIPS"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00037"},{"key":"ref21","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"ICML","author":"Sohl-Dickstein"},{"key":"ref22","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"NeurIPS"},{"key":"ref23","first-page":"21 696","article-title":"Variational diffusion models","volume":"34","author":"Kingma","year":"2021","journal-title":"NeurIPS"},{"key":"ref24","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021"},{"key":"ref25","first-page":"36 479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia","year":"2022","journal-title":"NeurIPS"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3204461"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01581"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref29","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00965"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01143"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73202-7_25"},{"key":"ref33","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02405"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73247-8_5"},{"key":"ref36","first-page":"19 730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"ICML","author":"Li"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw63382.2024.00179"},{"key":"ref38","article-title":"Deoldify","year":"2019"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00799"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555432"},{"key":"ref41","article-title":"Colorization transformer","volume-title":"ICLR","author":"Kumar"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555471"},{"key":"ref43","article-title":"L-cad: Language-based colorization with any-level descriptions using diffusion priors","volume":"36","author":"Weng","year":"2024","journal-title":"NeurIPS"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680726"},{"key":"ref48","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"}],"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\/10888355.pdf?arnumber=10888355","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:21:44Z","timestamp":1774416104000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888355\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888355","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}