{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T18:20:36Z","timestamp":1781720436031,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T00:00:00Z","timestamp":1665360000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Key R&D Program of China","award":["2018YFE0203900"],"award-info":[{"award-number":["2018YFE0203900"]}]},{"name":"Sichuan Science and Technology Program","award":["2020YFG0476"],"award-info":[{"award-number":["2020YFG0476"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,10,10]]},"DOI":"10.1145\/3503161.3548156","type":"proceedings-article","created":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T15:43:12Z","timestamp":1665416592000},"page":"3055-3063","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":17,"title":["Structure-Preserving Motion Estimation for Learned Video Compression"],"prefix":"10.1145","author":[{"given":"Han","family":"Gao","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinzhong","family":"Cui","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mao","family":"Ye","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuai","family":"Li","sequence":"additional","affiliation":[{"name":"Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiatian","family":"Zhu","sequence":"additional","affiliation":[{"name":"University of Surrey, Guildford, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,10,10]]},"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","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00031"},{"key":"e_1_3_2_2_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 ). 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_2_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). 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_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/DCC.2019.00068"},{"key":"e_1_3_2_2_6_1","volume-title":"Compressai: a pytorch library and evaluation platform for end-to-end compression research. arXiv preprint arXiv:2011.03029","author":"B\u00e9gaint Jean","year":"2020","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 preprint arXiv:2011.03029 ( 2020 ). 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 preprint arXiv:2011.03029 (2020)."},{"key":"e_1_3_2_2_7_1","volume-title":"BPG image format","author":"Bellard Fabrice","year":"2014","unstructured":"Fabrice Bellard . 2016. BPG image format ( 2014 ). URL http:\/\/bellard. org\/bpg\/.[Online, Accessed 2016-08-05], Vol. 1 , 2 (2016). Fabrice Bellard. 2016. BPG image format (2014). URL http:\/\/bellard. org\/bpg\/.[Online, Accessed 2016-08-05], Vol. 1, 2 (2016)."},{"key":"e_1_3_2_2_8_1","volume-title":"Calculation of average PSNR differences between RD-curves. VCEG-M33","author":"Bjontegaard Gisle","year":"2001","unstructured":"Gisle Bjontegaard . 2001. Calculation of average PSNR differences between RD-curves. VCEG-M33 ( 2001 ). Gisle Bjontegaard. 2001. Calculation of average PSNR differences between RD-curves. VCEG-M33 (2001)."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3101953"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2960869"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01031"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00796"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00652"},{"key":"e_1_3_2_2_15_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 ). 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_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00068"},{"key":"e_1_3_2_2_17_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 ). 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_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00713"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00155"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00461"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP48831.2020.9287049"},{"key":"e_1_3_2_2_22_1","volume-title":"Context-adaptive entropy model for end-to-end optimized image compression. arXiv preprint arXiv:1809.10452","author":"Lee Jooyoung","year":"2018","unstructured":"Jooyoung Lee , Seunghyun Cho , and Seung-Kwon Beack . 2018. Context-adaptive entropy model for end-to-end optimized image compression. arXiv preprint arXiv:1809.10452 ( 2018 ). Jooyoung Lee, Seunghyun Cho, and Seung-Kwon Beack. 2018. Context-adaptive entropy model for end-to-end optimized image compression. arXiv preprint arXiv:1809.10452 (2018)."},{"key":"e_1_3_2_2_23_1","volume-title":"Advances in Neural Information Processing Systems","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). Jiahao Li, Bin Li, and Yan Lu. 2021. Deep contextual video compression. Advances in Neural Information Processing Systems, Vol. 34 (2021)."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2985225"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00360"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3035680"},{"key":"e_1_3_2_2_27_1","volume-title":"Meet Shah, Rui Hu, Pranaab Dhawan, and Raquel Urtasun. 2020b. Conditional entropy coding for efficient video compression. In European Conference on Computer Vision. Springer, 453--468","author":"Liu Jerry","unstructured":"Jerry Liu , Shenlong Wang , Wei-Chiu Ma , Meet Shah, Rui Hu, Pranaab Dhawan, and Raquel Urtasun. 2020b. Conditional entropy coding for efficient video compression. In European Conference on Computer Vision. Springer, 453--468 . Jerry Liu, Shenlong Wang, Wei-Chiu Ma, Meet Shah, Rui Hu, Pranaab Dhawan, and Raquel Urtasun. 2020b. Conditional entropy coding for efficient video compression. In European Conference on Computer Vision. Springer, 453--468."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01126"},{"key":"e_1_3_2_2_29_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. 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_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00462"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3339825.3394937"},{"key":"e_1_3_2_2_32_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 ). 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_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.291"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01421"},{"key":"e_1_3_2_2_35_1","volume-title":"Temporal Context Mining for Learned Video Compression. arXiv preprint arXiv:2111.13850","author":"Sheng Xihua","year":"2021","unstructured":"Xihua Sheng , Jiahao Li , Bin Li , Li Li , Dong Liu , and Yan Lu. 2021. Temporal Context Mining for Learned Video Compression. arXiv preprint arXiv:2111.13850 ( 2021 ). Xihua Sheng, Jiahao Li, Bin Li, Li Li, Dong Liu, and Yan Lu. 2021. Temporal Context Mining for Learned Video Compression. arXiv preprint arXiv:2111.13850 (2021)."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2221191"},{"key":"e_1_3_2_2_37_1","volume-title":"Spatiotemporal Entropy Model is All You Need for Learned Video Compression. arXiv preprint arXiv:2104.06083","author":"Sun Zhenhong","year":"2021","unstructured":"Zhenhong Sun , Zhiyu Tan , Xiuyu Sun , Fangyi Zhang , Dongyang Li , Yichen Qian , and Hao Li. 2021. Spatiotemporal Entropy Model is All You Need for Learned Video Compression. arXiv preprint arXiv:2104.06083 ( 2021 ). Zhenhong Sun, Zhiyu Tan, Xiuyu Sun, Fangyi Zhang, Dongyang Li, Yichen Qian, and Hao Li. 2021. Spatiotemporal Entropy Model is All You Need for Learned Video Compression. arXiv preprint arXiv:2104.06083 (2021)."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2002.800725"},{"key":"e_1_3_2_2_39_1","volume-title":"Lossy image compression with compressive autoencoders. arXiv preprint arXiv:1703.00395","author":"Theis Lucas","year":"2017","unstructured":"Lucas Theis , Wenzhe Shi , Andrew Cunningham , and Ferenc Husz\u00e1r . 2017. Lossy image compression with compressive autoencoders. arXiv preprint arXiv:1703.00395 ( 2017 ). Lucas Theis, Wenzhe Shi, Andrew Cunningham, and Ferenc Husz\u00e1r. 2017. Lossy image compression with compressive autoencoders. arXiv preprint arXiv:1703.00395 (2017)."},{"key":"e_1_3_2_2_40_1","volume-title":"Damien Vincent, David Minnen, Shumeet Baluja, Michele Covell, and Rahul Sukthankar.","author":"Toderici George","year":"2015","unstructured":"George Toderici , Sean M O'Malley , Sung Jin Hwang , Damien Vincent, David Minnen, Shumeet Baluja, Michele Covell, and Rahul Sukthankar. 2015 . Variable rate image compression with recurrent neural networks. arXiv preprint arXiv:1511.06085 (2015). George Toderici, Sean M O'Malley, Sung Jin Hwang, Damien Vincent, David Minnen, Shumeet Baluja, Michele Covell, and Rahul Sukthankar. 2015. Variable rate image compression with recurrent neural networks. arXiv preprint arXiv:1511.06085 (2015)."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.577"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/30.125072"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7532610"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2003.1292216"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2003.815165"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_26"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-01144-2"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.3043590"}],"event":{"name":"MM '22: The 30th ACM International Conference on Multimedia","location":"Lisboa Portugal","acronym":"MM '22","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 30th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3548156","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3503161.3548156","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:00:19Z","timestamp":1750186819000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3548156"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,10]]},"references-count":48,"alternative-id":["10.1145\/3503161.3548156","10.1145\/3503161"],"URL":"https:\/\/doi.org\/10.1145\/3503161.3548156","relation":{},"subject":[],"published":{"date-parts":[[2022,10,10]]},"assertion":[{"value":"2022-10-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}