{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T18:37:09Z","timestamp":1772044629931,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":33,"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\/3581783.3612530","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:12Z","timestamp":1698391632000},"page":"8057-8066","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["High Visual-Fidelity Learned Video Compression"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6758-4122","authenticated-orcid":false,"given":"Meng","family":"Li","sequence":"first","affiliation":[{"name":"Huawei Technologies, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0840-3246","authenticated-orcid":false,"given":"Yibo","family":"Shi","sequence":"additional","affiliation":[{"name":"Huawei Technologies, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9042-3890","authenticated-orcid":false,"given":"Jing","family":"Wang","sequence":"additional","affiliation":[{"name":"Huawei Technologies, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6920-9513","authenticated-orcid":false,"given":"Yunqi","family":"Huang","sequence":"additional","affiliation":[{"name":"Huawei Technologies, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00853"},{"key":"e_1_3_2_2_2_1","volume-title":"Multi-Realism Image Compression with a Conditional Generator. arXiv preprint arXiv:2212.13824","author":"Agustsson Eirikur","year":"2022","unstructured":"Eirikur Agustsson, David Minnen, George Toderici, and Fabian Mentzer. 2022. Multi-Realism Image Compression with a Conditional Generator. arXiv preprint arXiv:2212.13824 (2022)."},{"key":"e_1_3_2_2_3_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_2_4_1","unstructured":"Frank Bossen et al. 2013. Common test conditions and software reference configurations. JCTVC-L1100 Vol. 12 7 (2013)."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3043399"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_2_8_1","volume-title":"Versatile Learned Video Compression. arXiv preprint arXiv:2111.03386","author":"Feng Runsen","year":"2021","unstructured":"Runsen Feng, Zongyu Guo, Zhizheng Zhang, and Zhibo Chen. 2021. Versatile Learned Video Compression. arXiv preprint arXiv:2111.03386 (2021)."},{"key":"e_1_3_2_2_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_2_10_1","volume-title":"Reformer: The efficient transformer. arXiv preprint arXiv:2001.04451","author":"Kitaev Nikita","year":"2020","unstructured":"Nikita Kitaev, \u0141ukasz Kaiser, and Anselm Levskaya. 2020. Reformer: The efficient transformer. arXiv preprint arXiv:2001.04451 (2020)."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00218"},{"key":"e_1_3_2_2_12_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. 2021. 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_2_13_1","volume-title":"Tel Aviv","author":"Li Meng","year":"2022","unstructured":"Meng Li, Shangyin Gao, Yihui Feng, Yibo Shi, and Jing Wang. 2022Content-oriented learned image compression. In Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XIX. Springer, 632--647."},{"key":"e_1_3_2_2_14_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_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00352"},{"key":"e_1_3_2_2_16_1","volume-title":"Tel Aviv","author":"Mentzer Fabian","year":"2022","unstructured":"Fabian Mentzer, Eirikur Agustsson, Johannes Ball\u00e9, David Minnen, Nick Johnston, and George Toderici. 2022. Neural video compression using gans for detail synthesis and propagation. In Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XXVI. Springer, 562--578."},{"key":"e_1_3_2_2_17_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"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.23915\/distill.00003"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00661"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3220421"},{"key":"e_1_3_2_2_21_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_2_22_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451141"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1017\/ATSIP.2019.2"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2221191"},{"key":"e_1_3_2_2_26_1","volume-title":"A coding framework and benchmark towards compressed video understanding. CoRR","author":"Tian Y","year":"2022","unstructured":"Y Tian, G Lu, Y Yan, G Zhai, L Chen, and Z Gao. 2022. A coding framework and benchmark towards compressed video understanding. CoRR (2022), 02813."},{"key":"e_1_3_2_2_27_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_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2003.1292216"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2003.815165"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-01144-2"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00666"},{"key":"e_1_3_2_2_32_1","volume-title":"Luc Van Gool, and Radu Timofte","author":"Yang Ren","year":"2021","unstructured":"Ren Yang, Luc Van Gool, and Radu Timofte. 2021. Perceptual learned video compression with recurrent conditional GAN. arXiv preprint arXiv:2109.03082, Vol. 1 (2021)."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"crossref","unstructured":"Richard Zhang Phillip Isola Alexei A Efros Eli Shechtman and Oliver Wang. 2018. The Unreasonable Effectiveness of Deep Features as a Perceptual Metric. In CVPR.","DOI":"10.1109\/CVPR.2018.00068"}],"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\/3581783.3612530","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612530","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T23:57:11Z","timestamp":1755820631000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612530"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":33,"alternative-id":["10.1145\/3581783.3612530","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612530","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"}}]}}