{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:48:40Z","timestamp":1783439320752,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680635","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"10930-10938","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["DiffTV: Identity-Preserved Thermal-to-Visible Face Translation via Feature Alignment and Dual-Stage Conditions"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1897-4148","authenticated-orcid":false,"given":"Jingyu","family":"Lin","sequence":"first","affiliation":[{"name":"Monash University, Melbourne, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7029-9755","authenticated-orcid":false,"given":"Guiqin","family":"Zhao","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7110-5377","authenticated-orcid":false,"given":"Jing","family":"Xu","sequence":"additional","affiliation":[{"name":"Monash University, Melbourne, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8685-3968","authenticated-orcid":false,"given":"Guoli","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0073-4122","authenticated-orcid":false,"given":"Zejin","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0107-7029","authenticated-orcid":false,"given":"Antitza","family":"Dantcheva","sequence":"additional","affiliation":[{"name":"INRIA, Valbonne, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9925-0223","authenticated-orcid":false,"given":"Lan","family":"Du","sequence":"additional","affiliation":[{"name":"Monash University, Melbourne, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2926-9762","authenticated-orcid":false,"given":"Cunjian","family":"Chen","sequence":"additional","affiliation":[{"name":"Monash University, Melbourne, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.3390\/s21103465"},{"key":"e_1_3_2_1_2_1","volume-title":"Accuracy comparison across face recognition algorithms: Where are we on measuring race bias? IEEE transactions on biometrics, behavior, and identity science","author":"Cavazos Jacqueline G","year":"2020","unstructured":"Jacqueline G Cavazos, P Jonathon Phillips, Carlos D Castillo, and Alice J O'Toole. 2020. Accuracy comparison across face recognition algorithms: Where are we on measuring race bias? IEEE transactions on biometrics, behavior, and identity science, Vol. 3, 1 (2020), 101--111."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICB45273.2019.8987329"},{"key":"e_1_3_2_1_5_1","volume-title":"International conference on learning representations.","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In International conference on learning representations."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00795"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00966"},{"key":"e_1_3_2_1_8_1","volume-title":"Dark: A Different Approach to Night Vision Face Detection with Thermal IR Images. In CEUR WORKSHOP PROCEEDINGS. CEUR-WS.","author":"Gaurav Singh Kinshuk","year":"2023","unstructured":"Singh Kinshuk Gaurav, Chodvadiya Charulkumar, Bhatt Chintan, Shah Pooja, Alessandro Bruno, et al. 2023. Seeing in the Dark: A Different Approach to Night Vision Face Detection with Thermal IR Images. In CEUR WORKSHOP PROCEEDINGS. CEUR-WS."},{"key":"e_1_3_2_1_9_1","volume-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems","author":"Heusel Martin","year":"2017","unstructured":"Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_10_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems, Vol. 33 (2020), 6840--6851."},{"key":"e_1_3_2_1_11_1","volume-title":"Anahita Bhiwandiwalla, and Vasudev Lal.","author":"Howard Phillip","year":"2023","unstructured":"Phillip Howard, Avinash Madasu, Tiep Le, Gustavo Lujan Moreno, Anahita Bhiwandiwalla, and Vasudev Lal. 2023. Probing and Mitigating Intersectional Social Biases in Vision-Language Models with Counterfactual Examples. arXiv preprint arXiv:2312.00825 (2023)."},{"key":"e_1_3_2_1_12_1","volume-title":"LoRA: Low-Rank Adaptation of Large Language Models. In International conference on learning representations.","author":"Hu Edward J.","year":"2022","unstructured":"Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-Rank Adaptation of Large Language Models. In International conference on learning representations."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCB52358.2021.9484353"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TTS.2020.2974996"},{"key":"e_1_3_2_1_16_1","volume-title":"International conference on learning representations.","author":"Kwon Gihyun","year":"2023","unstructured":"Gihyun Kwon and Jong Chul Ye. 2023. Diffusion-based Image Translation using disentangled style and content representation. In International conference on learning representations."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00194"},{"key":"e_1_3_2_1_18_1","volume-title":"Photomaker: Customizing realistic human photos via stacked id embedding. arXiv preprint arXiv:2312.04461","author":"Li Zhen","year":"2023","unstructured":"Zhen Li, Mingdeng Cao, Xintao Wang, Zhongang Qi, Ming-Ming Cheng, and Ying Shan. 2023. Photomaker: Customizing realistic human photos via stacked id embedding. arXiv preprint arXiv:2312.04461 (2023)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_41"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01812"},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of the IEEE\/CVF winter conference on applications of computer vision. 3434--3443","author":"Nair Nithin Gopalakrishnan","year":"2023","unstructured":"Nithin Gopalakrishnan Nair, Kangfu Mei, and Vishal M Patel. 2023. At-ddpm: Restoring faces degraded by atmospheric turbulence using denoising diffusion probabilistic models. In Proceedings of the IEEE\/CVF winter conference on applications of computer vision. 3434--3443."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG57933.2023.10042661"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02070"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00160"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_26_1","volume-title":"U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention. 234--241.","author":"Ronneberger Olaf","year":"2015","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention. 234--241."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"e_1_3_2_1_28_1","volume-title":"International conference on learning representations.","author":"Song Jiaming","year":"2021","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2021. Denoising diffusion implicit models. In International conference on learning representations."},{"key":"e_1_3_2_1_29_1","volume-title":"Dual Diffusion Implicit Bridges for Image-to-Image Translation. In International conference on learning representations.","author":"Su Xuan","year":"2023","unstructured":"Xuan Su, Jiaming Song, Chenlin Meng, and Stefano Ermon. 2023. Dual Diffusion Implicit Bridges for Image-to-Image Translation. In International conference on learning representations."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00077"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618249"},{"key":"e_1_3_2_1_32_1","unstructured":"Aaron Van Den Oord Oriol Vinyals et al. 2017. Neural discrete representation learning. Advances in neural information processing systems Vol. 30 (2017)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00552"},{"key":"e_1_3_2_1_34_1","volume-title":"FaceStudio: Put Your Face Everywhere in Seconds. arXiv preprint arXiv:2312.02663","author":"Yan Yuxuan","year":"2023","unstructured":"Yuxuan Yan, Chi Zhang, Rui Wang, Yichao Zhou, Gege Zhang, Pei Cheng, Gang Yu, and Bin Fu. 2023. FaceStudio: Put Your Face Everywhere in Seconds. arXiv preprint arXiv:2312.02663 (2023)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413965"},{"key":"e_1_3_2_1_36_1","volume-title":"Gp-unit: Generative prior for versatile unsupervised image-to-image translation","author":"Yang Shuai","year":"2023","unstructured":"Shuai Yang, Liming Jiang, Ziwei Liu, and Chen Change Loy. 2023. Gp-unit: Generative prior for versatile unsupervised image-to-image translation. IEEE Transactions on Pattern Analysis and Machine Intelligence (2023)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00017"},{"key":"e_1_3_2_1_38_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Yue Zongsheng","year":"2024","unstructured":"Zongsheng Yue, Jianyi Wang, and Chen Change Loy. 2024. Resshift: Efficient diffusion model for image super-resolution by residual shifting. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01175-3"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2959253"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3077058"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680635","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680635","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:57Z","timestamp":1750295877000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680635"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":43,"alternative-id":["10.1145\/3664647.3680635","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680635","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}