{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:55:16Z","timestamp":1781538916336,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Key R&D Program of China","award":["No.2022YFB4703500"],"award-info":[{"award-number":["No.2022YFB4703500"]}]},{"name":"National Key R&D Program of China","award":["No.21JCZXJC00190"],"award-info":[{"award-number":["No.21JCZXJC00190"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,16]]},"DOI":"10.1145\/3805622.3810699","type":"proceedings-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:42:57Z","timestamp":1781534577000},"page":"1692-1700","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Uncertainty-Gated Generative Compression for Structure-Preserving Multimedia Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3967-3796","authenticated-orcid":false,"given":"Yiming","family":"Ding","sequence":"first","affiliation":[{"name":"Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2833-2929","authenticated-orcid":false,"given":"Ziang","family":"Chen","sequence":"additional","affiliation":[{"name":"Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8964-9759","authenticated-orcid":false,"given":"Jianguo","family":"Wei","sequence":"additional","affiliation":[{"name":"Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,15]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02138"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.150"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00031"},{"key":"e_1_3_3_1_5_2","first-page":"63","volume-title":"STAG","author":"Asuni Nicola","year":"2014","unstructured":"Nicola Asuni and Andrea Giachetti. 2014. TESTIMAGES: a Large-scale Archive for Testing Visual Devices and Basic Image Processing Algorithms.. In STAG. 63\u201370."},{"key":"e_1_3_3_1_6_2","volume-title":"International Conference on Learning Representations","author":"Ball\u00e9 Johannes","year":"2016","unstructured":"Johannes Ball\u00e9, Valero Laparra, and Eero\u00a0P. Simoncelli. 2016. End-to-end Optimized Image Compression. In International Conference on Learning Representations."},{"key":"e_1_3_3_1_7_2","volume-title":"International Conference on Learning Representations","author":"Ball\u00e9 Johannes","year":"2018","unstructured":"Johannes Ball\u00e9, David Minnen, Saurabh Singh, Sung\u00a0Jin Hwang, and Nick Johnston. 2018. Variational image compression with a scale hyperprior. In International Conference on Learning Representations."},{"key":"e_1_3_3_1_8_2","unstructured":"Fabrice Bellard. 2015. BPG Image format. https:\/\/bellard.org\/bpg\/"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","unstructured":"Miko\u0142aj Bi\u0144kowski Danica\u00a0J. Sutherland Michael Arbel and Arthur Gretton. 2021. Demystifying MMD GANs. 10.48550\/arXiv.1801.01401arXiv:https:\/\/arXiv.org\/abs\/1801.01401 [stat].","DOI":"10.48550\/arXiv.1801.01401"},{"key":"e_1_3_3_1_10_2","volume-title":"Calculation of average PSNR differences between RD-curves","author":"Bj\u00f8ntegaard Gisle","year":"2001","unstructured":"Gisle Bj\u00f8ntegaard. 2001. Calculation of average PSNR differences between RD-curves. Technical Report VCEG-M33. ITU-T Video Coding Experts Group (VCEG), ITU-T SG16\/Q6, Austin, TX, USA. https:\/\/www.itu.int\/wftp3\/av-arch\/video-site\/0104_Aus\/VCEG-M33.doc"},{"key":"e_1_3_3_1_11_2","first-page":"675","volume-title":"International Conference on Machine Learning","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\u2013685."},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"crossref","unstructured":"Benjamin Bross Ye-Kui Wang Yan Ye Shan Liu Jianle Chen Gary\u00a0J. Sullivan and Jens-Rainer Ohm. 2021. Overview of the Versatile Video Coding (VVC) Standard and its Applications. IEEE Transactions on Circuits and Systems for Video Technology (Oct. 2021) 3736\u20133764.","DOI":"10.1109\/TCSVT.2021.3101953"},{"key":"e_1_3_3_1_13_2","unstructured":"Jean B\u00e9gaint Fabien Racap\u00e9 Simon Feltman and Akshay Pushparaja. 2020. CompressAI: a PyTorch library and evaluation platform for end-to-end compression research. arXiv:https:\/\/arXiv.org\/abs\/2011.03029 [cs eess]."},{"key":"e_1_3_3_1_14_2","volume-title":"The Twelfth International Conference on Learning Representations","author":"Careil Marlene","year":"2023","unstructured":"Marlene Careil, Matthew\u00a0J. 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_3_1_15_2","unstructured":"Keyan Ding Kede Ma Shiqi Wang and Eero\u00a0P. Simoncelli. 2020. Image quality assessment: Unifying structure and texture similarity. IEEE transactions on pattern analysis and machine intelligence 44 5 (2020) 2567\u20132581."},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.517"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","unstructured":"Noor\u00a0Fathima Ghouse Jens Petersen Auke Wiggers Tianlin Xu and Guillaume Sauti\u00e8re. 2023. A Residual Diffusion Model for High Perceptual Quality Codec Augmentation. 10.48550\/arXiv.2301.05489","DOI":"10.48550\/arXiv.2301.05489"},{"key":"e_1_3_3_1_18_2","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 30 (2017)."},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","unstructured":"Emiel Hoogeboom Eirikur Agustsson Fabian Mentzer Luca Versari George Toderici and Lucas Theis. 2024. High-Fidelity Image Compression with Score-based Generative Models. 10.48550\/arXiv.2305.18231arXiv:https:\/\/arXiv.org\/abs\/2305.18231 [eess].","DOI":"10.48550\/arXiv.2305.18231"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","unstructured":"Michael\u00a0F. Hutchinson. 1990. A stochastic estimator of the trace of the influence matrix for Laplacian smoothing splines. Communications in Statistics - Simulation and Computation 19 2 (1990) 433\u2013450. 10.1080\/03610919008812866","DOI":"10.1080\/03610919008812866"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","unstructured":"Herv\u00e9 J\u00e9gou Matthijs Douze and Cordula Schmid. 2011. Product quantization for nearest neighbor search. IEEE Transactions on Pattern Analysis and Machine Intelligence 33 1 (2011) 117\u2013128. 10.1109\/TPAMI.2010.57","DOI":"10.1109\/TPAMI.2010.57"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","unstructured":"Anle Ke Xu Zhang Tong Chen Ming Lu Chao Zhou Jiawen Gu and Zhan Ma. 2025. Ultra Lowrate Image Compression with Semantic Residual Coding and Compression-aware Diffusion. 10.48550\/arXiv.2505.08281arXiv:https:\/\/arXiv.org\/abs\/2505.08281 [cs].","DOI":"10.48550\/arXiv.2505.08281"},{"key":"e_1_3_3_1_23_2","unstructured":"E. Kodak. 1993. Kodak lossless true color image suite. https:\/\/r0k.us\/graphics\/kodak\/"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"crossref","unstructured":"Alina Kuznetsova Hassan Rom Neil Alldrin Jasper Uijlings Ivan Krasin Jordi Pont-Tuset Shahab Kamali Stefan Popov Matteo Malloci Alexander Kolesnikov Tom Duerig and Vittorio Ferrari. 2020. The Open Images Dataset V4: Unified Image Classification Object Detection and Visual Relationship Detection at Scale. International Journal of Computer Vision 128 7 (July 2020) 1956\u20131981.","DOI":"10.1007\/s11263-020-01316-z"},{"key":"e_1_3_3_1_25_2","unstructured":"Jooyoung Lee Seyoon Jeong and Munchurl Kim. 2022. Selective compression learning of latent representations for variable-rate image compression. arXiv:https:\/\/arXiv.org\/abs\/2211.04104 [eess.IV]."},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","unstructured":"Zijian Liang Kai Niu Changshuo Wang Jin Xu and Ping Zhang. 2025. Synonymous Variational Inference for Perceptual Image Compression. 10.48550\/arXiv.2505.22438arXiv:https:\/\/arXiv.org\/abs\/2505.22438 [cs].","DOI":"10.48550\/arXiv.2505.22438"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.151"},{"key":"e_1_3_3_1_28_2","unstructured":"Fabian Mentzer George\u00a0D. Toderici Michael Tschannen and Eirikur Agustsson. 2020. High-fidelity generative image compression. Advances in neural information processing systems 33 (2020) 11913\u201311924."},{"key":"e_1_3_3_1_29_2","unstructured":"David Minnen Johannes Ball\u00e9 and George\u00a0D. Toderici. 2018. Joint autoregressive and hierarchical priors for learned image compression. Advances in neural information processing systems 31 (2018)."},{"key":"e_1_3_3_1_30_2","first-page":"25426","volume-title":"International Conference on Machine Learning","author":"Muckley Matthew\u00a0J.","year":"2023","unstructured":"Matthew\u00a0J. Muckley, Alaaeldin El-Nouby, Karen Ullrich, Herv\u00e9 J\u00e9gou, and Jakob Verbeek. 2023. Improving statistical fidelity for neural image compression with implicit local likelihood models. In International Conference on Machine Learning. PMLR, 25426\u201325443."},{"key":"e_1_3_3_1_31_2","unstructured":"Maxime Oquab Timoth\u00e9e Darcet Th\u00e9o Moutakanni Huy\u00a0V. Vo Marc Szafraniec Vasil Khalidov Pierre Fernandez Daniel Haziza Francisco Massa Alaaeldin El-Nouby Mahmoud Assran Nicolas Ballas Wojciech Galuba Russell Howes Po-Yao Huang Shang-Wen Li Ishan Misra Michael Rabbat Vasu Sharma Gabriel Synnaeve Hu Xu Herv\u00e9 J\u00e9gou Julien Mairal Patrick Labatut Armand Joulin and Piotr Bojanowski. 2024. DINOv2: Learning robust visual features without supervision. Transactions on Machine Learning Research (2024)."},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383172"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00598"},{"key":"e_1_3_3_1_34_2","first-page":"8748","volume-title":"Proceedings of the 38th international conference on machine learning (ICML)","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning transferable visual models from natural language supervision. In Proceedings of the 38th international conference on machine learning (ICML). 8748\u20138763."},{"key":"e_1_3_3_1_35_2","unstructured":"George Toderici Lucas Theis Nick Johnston Eirikur Agustsson Fabian Mentzer Johannes Ball\u00e9 Wenzhe Shi and Radu Timofte. 2020. Clic 2020: Challenge on learned image compression. Retrieved March 29 (2020) 2021."},{"key":"e_1_3_3_1_36_2","volume-title":"International conference on learning representations (ICLR)","author":"Torfason Robert","year":"2018","unstructured":"Robert Torfason, Fabian Mentzer, Eirikur Agustsson, Michael Tschannen, Radu Timofte, and Luc Van\u00a0Gool. 2018. Towards image understanding from deep compression without decoding. In International conference on learning representations (ICLR)."},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","unstructured":"Gregory\u00a0K. Wallace. 1991. The JPEG still picture compression standard. Commun. ACM 34 4 (April 1991) 30\u201344. 10.1145\/103085.103089","DOI":"10.1145\/103085.103089"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","unstructured":"Jingdong Wang Ting Zhang Jingkuan Song Nicu Sebe and Heng\u00a0Tao Shen. 2018. A survey on learning to hash. IEEE Transactions on Pattern Analysis and Machine Intelligence 40 4 (2018) 769\u2013790. 10.1109\/TPAMI.2017.2699960","DOI":"10.1109\/TPAMI.2017.2699960"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2003.1292216"},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","unstructured":"Naifu Xue Zhaoyang Jia Jiahao Li Bin Li Yuan Zhang and Yan Lu. 2025. DLF: Extreme Image Compression with Dual-generative Latent Fusion. 10.48550\/arXiv.2503.01428arXiv:https:\/\/arXiv.org\/abs\/2503.01428 [cs].","DOI":"10.48550\/arXiv.2503.01428"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"}],"event":{"name":"ICMR '26: International Conference on Multimedia Retrieval","location":"Amsterdam The Netherlands","acronym":"ICMR '26","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2026 International Conference on Multimedia Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:14:24Z","timestamp":1781536464000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805622.3810699"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,15]]},"references-count":40,"alternative-id":["10.1145\/3805622.3810699","10.1145\/3805622"],"URL":"https:\/\/doi.org\/10.1145\/3805622.3810699","relation":{},"subject":[],"published":{"date-parts":[[2026,6,15]]},"assertion":[{"value":"2026-06-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}