{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T02:50:50Z","timestamp":1761965450308,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":56,"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"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611955","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:40Z","timestamp":1698391660000},"page":"7961-7970","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Towards Real-Time Neural Video Codec for Cross-Platform Application Using Calibration Information"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9409-5842","authenticated-orcid":false,"given":"Kuan","family":"Tian","sequence":"first","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0643-3187","authenticated-orcid":false,"given":"Yonghang","family":"Guan","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5476-3690","authenticated-orcid":false,"given":"Jinxi","family":"Xiang","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5579-7094","authenticated-orcid":false,"given":"Jun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5151-6547","authenticated-orcid":false,"given":"Xiao","family":"Han","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6488-2546","authenticated-orcid":false,"given":"Wei","family":"Yang","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00853"},{"key":"e_1_3_2_1_2_1","volume-title":"International Conference on Learning Representations.","author":"Ball\u00e9 Johannes","year":"2019","unstructured":"Johannes Ball\u00e9, Nick Johnston, and David Minnen. 2019. Integer networks for data compression with latent-variable models. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_3_1","volume-title":"End-to-end optimized image compression. arXiv preprint arXiv:1611.01704","author":"Ball\u00e9 Johannes","year":"2016","unstructured":"Johannes Ball\u00e9, Valero Laparra, and Eero P Simoncelli. 2016. End-to-end optimized image compression. arXiv preprint arXiv:1611.01704 (2016)."},{"key":"e_1_3_2_1_4_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)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00356"},{"key":"e_1_3_2_1_6_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_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3101953"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053885"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01039"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.316"},{"key":"e_1_3_2_1_11_1","volume-title":"Asymmetric numeral systems. arXiv preprint arXiv:0902.0271","author":"Duda Jarek","year":"2009","unstructured":"Jarek Duda. 2009. Asymmetric numeral systems. arXiv preprint arXiv:0902.0271 (2009)."},{"key":"e_1_3_2_1_12_1","volume-title":"Learned step size quantization. arXiv preprint arXiv:1902.08153","author":"Esser Steven K","year":"2019","unstructured":"Steven K Esser, Jeffrey L McKinstry, Deepika Bablani, Rathinakumar Appuswamy, and Dharmendra S Modha. 2019. Learned step size quantization. arXiv preprint arXiv:1902.08153 (2019)."},{"key":"e_1_3_2_1_13_1","volume-title":"Learning cross-scale prediction for efficient neural video compression. arXiv preprint arXiv:2112.13309","author":"Guo Zongyu","year":"2021","unstructured":"Zongyu Guo, Runsen Feng, Zhizheng Zhang, Xin Jin, and Zhibo Chen. 2021. Learning cross-scale prediction for efficient neural video compression. arXiv preprint arXiv:2112.13309 (2021)."},{"key":"e_1_3_2_1_14_1","volume-title":"Post-training quantization for cross-platform learned image compression. arXiv preprint arXiv:2202.07513","author":"He Dailan","year":"2022","unstructured":"Dailan He, Ziming Yang, Yuan Chen, Qi Zhang, Hongwei Qin, and Yan Wang. 2022. Post-training quantization for cross-platform learned image compression. arXiv preprint arXiv:2202.07513 (2022)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00447"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"e_1_3_2_1_17_1","volume-title":"Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.286189"},{"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\/CVPR.2018.00936"},{"key":"e_1_3_2_1_21_1","volume-title":"A lightweight optical flow CNN-Revisiting data fidelity and regularization","author":"Hui Tak-Wai","year":"2020","unstructured":"Tak-Wai Hui, Xiaoou Tang, and Chen Change Loy. 2020. A lightweight optical flow CNN-Revisiting data fidelity and regularization. IEEE transactions on pattern analysis and machine intelligence, Vol. 43, 8 (2020), 2555--2569."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"e_1_3_2_1_23_1","volume-title":"Device Interoperability for Learned Image Compression with Weights and Activations Quantization. In 2022 Picture Coding Symposium (PCS). IEEE, 151--155","author":"Koyuncu Esin","year":"2022","unstructured":"Esin Koyuncu, Timofey Solovyev, Elena Alshina, and Andr\u00e9 Kaup. 2022. Device Interoperability for Learned Image Compression with Weights and Activations Quantization. In 2022 Picture Coding Symposium (PCS). IEEE, 151--155."},{"key":"e_1_3_2_1_24_1","volume-title":"Quantizing deep convolutional networks for efficient inference: A whitepaper. arXiv preprint arXiv:1806.08342","author":"Krishnamoorthi Raghuraman","year":"2018","unstructured":"Raghuraman Krishnamoorthi. 2018. Quantizing deep convolutional networks for efficient inference: A whitepaper. arXiv preprint arXiv:1806.08342 (2018)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3524273.3532906"},{"key":"e_1_3_2_1_26_1","volume-title":"Pruning filters for efficient convnets. arXiv preprint arXiv:1608.08710","author":"Li Hao","year":"2016","unstructured":"Hao Li, Asim Kadav, Igor Durdanovic, Hanan Samet, and Hans Peter Graf. 2016. Pruning filters for efficient convnets. arXiv preprint arXiv:1608.08710 (2016)."},{"key":"e_1_3_2_1_27_1","first-page":"18114","article-title":"Deep contextual video compression","volume":"34","author":"Li Jiahao","year":"2021","unstructured":"Jiahao Li, Bin Li, and Yan Lu. 2021b. Deep contextual video compression. Advances in Neural Information Processing Systems, Vol. 34 (2021), 18114--18125.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547845"},{"key":"e_1_3_2_1_29_1","volume-title":"Neural Video Compression with Diverse Contexts. arXiv preprint arXiv:2302.14402","author":"Li Jiahao","year":"2023","unstructured":"Jiahao Li, Bin Li, and Yan Lu. 2023. Neural Video Compression with Diverse Contexts. arXiv preprint arXiv:2302.14402 (2023)."},{"key":"e_1_3_2_1_30_1","volume-title":"Brecq: Pushing the limit of post-training quantization by block reconstruction. arXiv preprint arXiv:2102.05426","author":"Li Yuhang","year":"2021","unstructured":"Yuhang Li, Ruihao Gong, Xu Tan, Yang Yang, Peng Hu, Qi Zhang, Fengwei Yu, Wei Wang, and Shi Gu. 2021a. Brecq: Pushing the limit of post-training quantization by block reconstruction. arXiv preprint arXiv:2102.05426 (2021)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00360"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"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","volume-title":"An end-to-end learning framework for video compression","author":"Lu Guo","year":"2020","unstructured":"Guo Lu, Xiaoyun Zhang, Wanli Ouyang, Li Chen, Zhiyong Gao, and Dong Xu. 2020. An end-to-end learning framework for video compression. IEEE transactions on pattern analysis and machine intelligence, Vol. 43, 10 (2020), 3292--3308."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00153"},{"key":"e_1_3_2_1_36_1","volume-title":"Vct: A video compression transformer. arXiv preprint arXiv:2206.07307","author":"Mentzer Fabian","year":"2022","unstructured":"Fabian Mentzer, George Toderici, David Minnen, Sung-Jin Hwang, Sergi Caelles, Mario Lucic, and Eirikur Agustsson. 2022. Vct: A video compression transformer. arXiv preprint arXiv:2206.07307 (2022)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3339825.3394937"},{"key":"e_1_3_2_1_38_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_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01152"},{"key":"e_1_3_2_1_40_1","volume-title":"International Conference on Machine Learning. PMLR, 7197--7206","author":"Nagel Markus","year":"2020","unstructured":"Markus Nagel, Rana Ali Amjad, Mart Van Baalen, Christos Louizos, and Tijmen Blankevoort. 2020. Up or down? adaptive rounding for post-training quantization. In International Conference on Machine Learning. PMLR, 7197--7206."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00141"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.291"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01421"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3220421"},{"key":"e_1_3_2_1_45_1","volume-title":"Tel Aviv","author":"Shi Yibo","year":"2022","unstructured":"Yibo Shi, Yunying Ge, Jing Wang, and Jue Mao. 2022. AlphaVC: High-Performance and Efficient Learned Video Compression. In Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XIX. Springer, 616--631."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00931"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/PCS50896.2021.9477496"},{"key":"e_1_3_2_1_48_1","first-page":"8183","article-title":"Distilling knowledge by mimicking features","volume":"44","author":"Wang Guo-Hua","year":"2021","unstructured":"Guo-Hua Wang, Yifan Ge, and Jianxin Wu. 2021. Distilling knowledge by mimicking features. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 44, 11 (2021), 8183--8195.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_1_49_1","volume-title":"Evc: Towards real-time neural image compression with mask decay. arXiv preprint arXiv:2302.05071","author":"Wang Guo-Hua","year":"2023","unstructured":"Guo-Hua Wang, Jiahao Li, Bin Li, and Yan Lu. 2023. Evc: Towards real-time neural image compression with mask decay. arXiv preprint arXiv:2302.05071 (2023)."},{"key":"e_1_3_2_1_50_1","volume-title":"Image quality assessment: from error visibility to structural similarity","author":"Wang Zhou","year":"2004","unstructured":"Zhou Wang, Alan C Bovik, Hamid R Sheikh, and Eero P Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing, Vol. 13, 4 (2004), 600--612."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/214762.214771"},{"volume-title":"MIMT: Masked Image Modeling Transformer for Video Compression. In The Eleventh International Conference on Learning Representations.","author":"Xiang Jinxi","key":"e_1_3_2_1_52_1","unstructured":"Jinxi Xiang, Kuan Tian, and Jun Zhang. [n.,d.]. MIMT: Masked Image Modeling Transformer for Video Compression. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-01144-2"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00666"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01165"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01697"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Ottawa ON Canada","acronym":"MM '23"},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611955","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611955","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:07:43Z","timestamp":1755821263000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611955"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":56,"alternative-id":["10.1145\/3581783.3611955","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611955","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"}}]}}