{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T20:10:31Z","timestamp":1765311031251,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","funder":[{"name":"the China NSF under Grant award","award":["62427801"],"award-info":[{"award-number":["62427801"]}]},{"name":"the National Key RD Program of China award number","award":["023YFB4502802"],"award-info":[{"award-number":["023YFB4502802"]}]},{"name":"the China NSF under Grant award number","award":["62031009"],"award-info":[{"award-number":["62031009"]}]},{"name":"the Postdoctoral Fellowship Program of CPSF award number","award":["GZB20250135"],"award-info":[{"award-number":["GZB20250135"]}]},{"name":"the China Postdoctoral Science Foundation award number","award":["2024M762536"],"award-info":[{"award-number":["2024M762536"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755599","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:30:51Z","timestamp":1761377451000},"page":"8626-8635","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Unicorn: Unified Neural Image Compression with One Number Reconstruction"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9340-6709","authenticated-orcid":false,"given":"Qi","family":"Zheng","sequence":"first","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2988-5440","authenticated-orcid":false,"given":"Haozhi","family":"Wang","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2182-3123","authenticated-orcid":false,"given":"Zihao","family":"Liu","sequence":"additional","affiliation":[{"name":"Alibaba Group, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9629-9788","authenticated-orcid":false,"given":"Jiaming","family":"Liu","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7892-5973","authenticated-orcid":false,"given":"Zhijian","family":"Hao","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1332-6113","authenticated-orcid":false,"given":"Bu","family":"Chen","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3517-4432","authenticated-orcid":false,"given":"Min","family":"Li","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8177-1677","authenticated-orcid":false,"given":"Rui","family":"Wan","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6568-5261","authenticated-orcid":false,"given":"Peiye","family":"Liu","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4024-6125","authenticated-orcid":false,"given":"Yanheng","family":"Lu","sequence":"additional","affiliation":[{"name":"Alibaba Group, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8440-3875","authenticated-orcid":false,"given":"Dimin","family":"Niu","sequence":"additional","affiliation":[{"name":"Alibaba Group, Sunnyvale, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5078-0522","authenticated-orcid":false,"given":"Jinjia","family":"Zhou","sequence":"additional","affiliation":[{"name":"Hosei University, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0446-5600","authenticated-orcid":false,"given":"Minge","family":"Jing","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2523-8261","authenticated-orcid":false,"given":"Yibo","family":"Fan","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"doi-asserted-by":"publisher","key":"e_1_3_2_2_1_1","DOI":"10.1109\/ICCV.2019.00031"},{"key":"e_1_3_2_2_2_1","volume-title":"Sung Jin Hwang, and Nick Johnston","author":"Ball\u00e9 Johannes","year":"2018","unstructured":"Johannes Ball\u00e9, David Minnen, Saurabh Singh, Sung Jin Hwang, and Nick Johnston. 2018. Variational image compression with a scale hyperprior. arXiv preprint arXiv:1802.01436 (2018)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_3_1","DOI":"10.1109\/CVPR.2018.00652"},{"key":"e_1_3_2_2_4_1","volume-title":"International Conference on Machine Learning. PMLR, 675-685","author":"Blau Yochai","year":"2019","unstructured":"Yochai Blau and Tomer Michaeli. 2019. Rethinking lossy compression: The rate-distortion-perception tradeoff. In International Conference on Machine Learning. PMLR, 675-685."},{"key":"e_1_3_2_2_5_1","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Blier L\u00e9onard","year":"2018","unstructured":"L\u00e9onard Blier and Yann Ollivier. 2018. The description length of deep learning models. Advances in Neural Information Processing Systems, Vol. 31 (2018)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_6_1","DOI":"10.1109\/TCSVT.2021.3072204"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_7_1","DOI":"10.1109\/TCSVT.2021.3101953"},{"key":"e_1_3_2_2_8_1","volume-title":"The Twelfth International Conference on Learning Representations.","author":"Careil Marlene","year":"2023","unstructured":"Marlene Careil, Matthew J Muckley, Jakob Verbeek, and St\u00e9phane Lathuili\u00e8re. 2023. Towards image compression with perfect realism at ultra-low bitrates. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_2_9_1","volume-title":"The Twelfth International Conference on Learning Representations.","author":"Careil Marlene","year":"2024","unstructured":"Marlene Careil, Matthew J Muckley, Jakob Verbeek, and St\u00e9phane Lathuili\u00e8re. 2024. Towards image compression with perfect realism at ultra-low bitrates. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_2_10_1","volume-title":"Matthew Aitchison, Laurent Orseau, et al.","author":"Del\u00e9tang Gr\u00e9goire","year":"2023","unstructured":"Gr\u00e9goire Del\u00e9tang, Anian Ruoss, Paul-Ambroise Duquenne, Elliot Catt, Tim Genewein, Christopher Mattern, Jordi Grau-Moya, Li Kevin Wenliang, Matthew Aitchison, Laurent Orseau, et al., 2023. Language modeling is compression. arXiv preprint arXiv:2309.10668 (2023)."},{"key":"e_1_3_2_2_11_1","volume-title":"Image quality assessment: Unifying structure and texture similarity","author":"Ding Keyan","year":"2020","unstructured":"Keyan Ding, Kede Ma, Shiqi Wang, and Eero P Simoncelli. 2020. Image quality assessment: Unifying structure and texture similarity. IEEE transactions on pattern analysis and machine intelligence, Vol. 44, 5 (2020), 2567-2581."},{"key":"e_1_3_2_2_12_1","volume-title":"Yee Whye Teh, and Arnaud Doucet","author":"Dupont Emilien","year":"2021","unstructured":"Emilien Dupont, Adam Goli\u0144ski, Milad Alizadeh, Yee Whye Teh, and Arnaud Doucet. 2021. Coin: Compression with implicit neural representations. arXiv preprint arXiv:2103.03123 (2021)."},{"key":"e_1_3_2_2_13_1","first-page":"1938","article-title":"Compression with bayesian implicit neural representations","volume":"36","author":"Guo Zongyu","year":"2023","unstructured":"Zongyu Guo, Gergely Flamich, Jiajun He, Zhibo Chen, and Jos\u00e9 Miguel Hern\u00e1ndez-Lobato. 2023. Compression with bayesian implicit neural representations. Advances in Neural Information Processing Systems, Vol. 36 (2023), 1938-1956.","journal-title":"Advances in Neural Information Processing Systems"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_14_1","DOI":"10.1109\/TCSI.2025.3543575"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_15_1","DOI":"10.1109\/TBC.2024.3374078"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_16_1","DOI":"10.1109\/ISCAS48785.2022.9937709"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_17_1","DOI":"10.1109\/CVPR52688.2022.00563"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_18_1","DOI":"10.1109\/CVPR46437.2021.01453"},{"key":"e_1_3_2_2_19_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_2_20_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_2_21_1","first-page":"4194","article-title":"Learning end-to-end lossy image compression: A benchmark","volume":"44","author":"Hu Yueyu","year":"2021","unstructured":"Yueyu Hu, Wenhan Yang, Zhan Ma, and Jiaying Liu. 2021. Learning end-to-end lossy image compression: A benchmark. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 44, 8 (2021), 4194-4211.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_22_1","DOI":"10.1145\/3581783.3611694"},{"key":"e_1_3_2_2_23_1","first-page":"94720","article-title":"IEEE standard 754 for binary floating-point arithmetic","volume":"754","author":"Kahan William","year":"1996","unstructured":"William Kahan. 1996. IEEE standard 754 for binary floating-point arithmetic. Lecture Notes on the Status of IEEE, Vol. 754, 94720-1776 (1996), 11.","journal-title":"Lecture Notes on the Status of IEEE"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_24_1","DOI":"10.1016\/S0304-3975(98)00075-9"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_25_1","DOI":"10.1109\/TIT.2002.800493"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_26_1","DOI":"10.1109\/ICCV51070.2023.01243"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_27_1","DOI":"10.1109\/ICCV51070.2023.01243"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_28_1","DOI":"10.1109\/CVPR52734.2025.01196"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_29_1","DOI":"10.1109\/TPAMI.2007.1085"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_30_1","DOI":"10.1109\/ISIT.2004.1365499"},{"key":"e_1_3_2_2_31_1","first-page":"11913","article-title":"High-fidelity generative image compression","volume":"33","author":"Mentzer Fabian","year":"2020","unstructured":"Fabian Mentzer, George D Toderici, Michael Tschannen, and Eirikur Agustsson. 2020. High-fidelity generative image compression. Advances in Neural Information Processing Systems, Vol. 33 (2020), 11913-11924.","journal-title":"Advances in Neural Information Processing Systems"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_32_1","DOI":"10.1109\/TIP.2012.2214050"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_33_1","DOI":"10.1109\/LSP.2012.2227726"},{"key":"e_1_3_2_2_34_1","volume-title":"Sinfusion: Training diffusion models on a single image or video. arXiv preprint arXiv:2211.11743","author":"Nikankin Yaniv","year":"2022","unstructured":"Yaniv Nikankin, Niv Haim, and Michal Irani. 2022. Sinfusion: Training diffusion models on a single image or video. arXiv preprint arXiv:2211.11743 (2022)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_35_1","DOI":"10.1109\/ICCV51070.2023.00387"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_36_1","DOI":"10.1109\/CVPR52688.2022.01042"},{"doi-asserted-by":"crossref","unstructured":"Olga Russakovsky Jia Deng Hao Su Jonathan Krause Sanjeev Satheesh Sean Ma Zhiheng Huang Andrej Karpathy Aditya Khosla Michael Bernstein et al. 2015. Imagenet large scale visual recognition challenge. International journal of computer vision Vol. 115 (2015) 211-252.","key":"e_1_3_2_2_37_1","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_2_38_1","first-page":"36","volume-title":"The JPEG 2000 still image compression standard. IEEE Signal processing magazine","volume":"18","author":"Skodras Athanassios","year":"2001","unstructured":"Athanassios Skodras, Charilaos Christopoulos, and Touradj Ebrahimi. 2001. The JPEG 2000 still image compression standard. IEEE Signal processing magazine, Vol. 18, 5 (2001), 36-58."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_39_1","DOI":"10.1007\/978-3-031-19809-0_5"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_40_1","DOI":"10.1109\/TCSVT.2012.2221191"},{"key":"e_1_3_2_2_41_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_42_1","DOI":"10.1145\/103085.103089"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_43_1","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"e_1_3_2_2_44_1","volume-title":"Idempotence and Perceptual Image Compression. In The Twelfth International Conference on Learning Representations.","author":"Xu Tongda","year":"2024","unstructured":"Tongda Xu, Ziran Zhu, Dailan He, Yanghao Li, Lina Guo, Yuanyuan Wang, Zhe Wang, Hongwei Qin, Yan Wang, Jingjing Liu, and Ya-Qin Zhang. 2024. Idempotence and Perceptual Image Compression. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_2_45_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Yang Ruihan","year":"2024","unstructured":"Ruihan Yang and Stephan Mandt. 2024. Lossy image compression with conditional diffusion models. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_46_1","DOI":"10.1145\/3446776"},{"key":"e_1_3_2_2_47_1","first-page":"11517","article-title":"Universal rate-distortion-perception representations for lossy compression","volume":"34","author":"Zhang George","year":"2021","unstructured":"George Zhang, Jingjing Qian, Jun Chen, and Ashish Khisti. 2021b. Universal rate-distortion-perception representations for lossy compression. Advances in Neural Information Processing Systems, Vol. 34 (2021), 11517-11529.","journal-title":"Advances in Neural Information Processing Systems"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_48_1","DOI":"10.1109\/CVPR.2018.00068"},{"unstructured":"Qi Zheng Yibo Fan Leilei Huang Tianyu Zhu Jiaming Liu Zhijian Hao Shuo Xing Chia-Ju Chen Xiongkuo Min Alan C Bovik et al. 2024. Video quality assessment: A comprehensive survey. arXiv preprint arXiv:2412.04508 (2024).","key":"e_1_3_2_2_49_1"}],"event":{"sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"acronym":"MM '25","name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755599","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T20:06:24Z","timestamp":1765310784000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755599"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":49,"alternative-id":["10.1145\/3746027.3755599","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755599","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}