{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T14:56:41Z","timestamp":1784905001190,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"The Startup Funding and the Seed Funding for Basic Research for New Staff from The University of Hong Kong"},{"name":"The Hong Kong Jockey Club Charities Trust","award":["2022-0174"],"award-info":[{"award-number":["2022-0174"]}]},{"name":"UBTECH Robotics"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612041","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:12Z","timestamp":1698391632000},"page":"8047-8056","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":23,"title":["ICMH-Net: Neural Image Compression Towards both Machine Vision and Human Vision"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1350-3072","authenticated-orcid":false,"given":"Lei","family":"Liu","sequence":"first","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0430-5875","authenticated-orcid":false,"given":"Zhihao","family":"Hu","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0155-4462","authenticated-orcid":false,"given":"Zhenghao","family":"Chen","sequence":"additional","affiliation":[{"name":"The University of Sydney, Sydney, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2775-9730","authenticated-orcid":false,"given":"Dong","family":"Xu","sequence":"additional","affiliation":[{"name":"The University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19884"},{"key":"e_1_3_2_1_2_1","volume-title":"5th International Conference on Learning Representations, ICLR","author":"Ball\u00e9 Johannes","year":"2017","unstructured":"Johannes Ball\u00e9, Valero Laparra, and Eero P Simoncelli. 2017. End-to-end optimized image compression. In 5th International Conference on Learning Representations, ICLR 2017."},{"key":"e_1_3_2_1_3_1","volume-title":"International Conference on Learning Representations.","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. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_4_1","volume-title":"Calculation of average PSNR differences between RD-curves. ITU SG16 Doc. VCEG-M33","author":"Bjontegaard Gisle","year":"2001","unstructured":"Gisle Bjontegaard. 2001. Calculation of average PSNR differences between RD-curves. ITU SG16 Doc. VCEG-M33 (2001)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3140608"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428078"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00598"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611960"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7965979"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00796"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3160602"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01039"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3016485"},{"key":"e_1_3_2_1_15_1","volume-title":"Christopher KI Williams, John Winn, and Andrew Zisserman.","author":"Everingham Mark","year":"2010","unstructured":"Mark Everingham, Luc Van Gool, Christopher KI Williams, John Winn, and Andrew Zisserman. 2010. The pascal visual object classes (voc) challenge. International journal of computer vision, Vol. 88 (2010), 303--338."},{"key":"e_1_3_2_1_16_1","unstructured":"Bellard Fabrice. 2018. BPG image format. http:\/\/bellard.org\/bpg\/ accessed:2022."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01453"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_12"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00583"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00155"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01380"},{"key":"e_1_3_2_1_23_1","volume-title":"International Conference on Learning Representations (ICLR","author":"Jang Eric","year":"2017","unstructured":"Eric Jang, Shixiang Gu, and Ben Poole. 2017. Categorical reparametrization with gumble-softmax. In International Conference on Learning Representations (ICLR 2017). OpenReview. net."},{"key":"e_1_3_2_1_24_1","volume-title":"Adam: A Method for Stochastic Optimization. In ICLR (Poster).","author":"Kingma Diederik P","year":"2015","unstructured":"Diederik P Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In ICLR (Poster)."},{"key":"e_1_3_2_1_25_1","volume-title":"Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems","author":"Krizhevsky Alex","year":"2012","unstructured":"Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, Vol. 25 (2012)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414465"},{"key":"e_1_3_2_1_27_1","first-page":"13146","article-title":"Selective compression learning of latent representations for variable-rate image compression","volume":"35","author":"Lee Jooyoung","year":"2022","unstructured":"Jooyoung Lee, Seyoon Jeong, and Munchurl Kim. 2022b. Selective compression learning of latent representations for variable-rate image compression. Advances in Neural Information Processing Systems, Vol. 35 (2022), 13146--13157.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01564"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46672-9_72"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01491-7"},{"key":"e_1_3_2_1_32_1","volume-title":"PCHM-Net: A New Point Cloud Compression Framework for Both Human Vision and Machine Vision. IEEE International Conference on Multimedia and Expo","author":"Liu Lei","year":"2023","unstructured":"Lei Liu, Zhihao Hu, and Jing Zhang. 2023. PCHM-Net: A New Point Cloud Compression Framework for Both Human Vision and Machine Vision. IEEE International Conference on Multimedia and Expo (2023)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01126"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP53242.2021.9675387"},{"key":"e_1_3_2_1_35_1","volume-title":"Joint autoregressive and hierarchical priors for learned image compression. Advances in neural information processing systems","author":"Minnen David","year":"2018","unstructured":"David Minnen, Johannes Ball\u00e9, and George D Toderici. 2018. Joint autoregressive and hierarchical priors for learned image compression. Advances in neural information processing systems, Vol. 31 (2018)."},{"key":"e_1_3_2_1_36_1","volume-title":"Tel Aviv","author":"Pan Guanbo","year":"2022","unstructured":"Guanbo Pan, Guo Lu, Zhihao Hu, and Dong Xu. 2022. Content Adaptive Latents and Decoder for Neural Image Compression. In Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XVIII. Springer, 556--573."},{"key":"e_1_3_2_1_37_1","volume-title":"Entroformer: A Transformer-based Entropy Model for Learned Image Compression. In International Conference on Learning Representations.","author":"Qian Yichen","year":"2022","unstructured":"Yichen Qian, Xiuyu Sun, Ming Lin, Zhiyu Tan, and Rong Jin. 2022. Entroformer: A Transformer-based Entropy Model for Learned Image Compression. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_38_1","volume-title":"Learning Accurate Entropy Model with Global Reference for Image Compression. In International Conference on Learning Representations.","author":"Qian Yichen","year":"2021","unstructured":"Yichen Qian, Zhiyu Tan, Xiuyu Sun, Ming Lin, Dongyang Li, Zhenhong Sun, Li Hao, and Rong Jin. 2021. Learning Accurate Entropy Model with Global Reference for Image Compression. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_39_1","volume-title":"Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems","author":"Ren Shaoqing","year":"2015","unstructured":"Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems, Vol. 28 (2015)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00238"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00238"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1117\/1.1469618"},{"key":"e_1_3_2_1_43_1","volume-title":"Towards image understanding from deep compression without decoding. OpenReniew. net-ICLR 2018","author":"Torfason Robert","year":"2018","unstructured":"Robert Torfason, Fabian Mentzer, Eirikur Agustsson, Michael Tschannen, Radu Timofte, and Luc Van Gool. 2018. Towards image understanding from deep compression without decoding. OpenReniew. net-ICLR 2018 (2018)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_28"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01686"},{"key":"e_1_3_2_1_46_1","volume-title":"Towards analysis-friendly face representation with scalable feature and texture compression","author":"Wang Shurun","year":"2021","unstructured":"Shurun Wang, Shiqi Wang, Wenhan Yang, Xinfeng Zhang, Shanshe Wang, Siwei Ma, and Wen Gao. 2021b. Towards analysis-friendly face representation with scalable feature and texture compression. IEEE Transactions on Multimedia (2021)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/OJCAS.2021.3126061"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3119660"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00496"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3068580"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_17"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01709"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01697"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612041","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612041","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:01:47Z","timestamp":1755820907000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612041"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":53,"alternative-id":["10.1145\/3581783.3612041","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612041","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}