{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T19:46:13Z","timestamp":1793130373460,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":50,"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"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,10,10]]},"DOI":"10.1145\/3503161.3547845","type":"proceedings-article","created":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T15:42:35Z","timestamp":1665416555000},"page":"1503-1511","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":218,"title":["Hybrid Spatial-Temporal Entropy Modelling for Neural Video Compression"],"prefix":"10.1145","author":[{"given":"Jiahao","family":"Li","sequence":"first","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Lu","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,10,10]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"2022. HM-16.20. https:\/\/vcgit.hhi.fraunhofer.de\/jvet\/HM\/. Accessed: 2022-03-02.  2022. HM-16.20. https:\/\/vcgit.hhi.fraunhofer.de\/jvet\/HM\/. Accessed: 2022-03-02."},{"key":"e_1_3_2_2_2_1","unstructured":"2022. PyTorchVideoCompression. https:\/\/github.com\/ZhihaoHu\/PyTorchVideoCompression. Accessed: 2022-03-02.  2022. PyTorchVideoCompression. https:\/\/github.com\/ZhihaoHu\/PyTorchVideoCompression. Accessed: 2022-03-02."},{"key":"e_1_3_2_2_3_1","volume-title":"Ultra video group test sequences","unstructured":"2022. Ultra video group test sequences . http:\/\/ultravideo.cs.tut.fi. Accessed: 2022-03-02. 2022. Ultra video group test sequences. http:\/\/ultravideo.cs.tut.fi. Accessed: 2022-03-02."},{"key":"e_1_3_2_2_4_1","unstructured":"2022. VTM-13.2. https:\/\/vcgit.hhi.fraunhofer.de\/jvet\/VVCSoftware_VTM\/. Accessed: 2022-03-02.  2022. VTM-13.2. https:\/\/vcgit.hhi.fraunhofer.de\/jvet\/VVCSoftware_VTM\/. Accessed: 2022-03-02."},{"key":"e_1_3_2_2_5_1","unstructured":"2022. x265. https:\/\/www.videolan.org\/developers\/x265.html. Accessed: 2022-03-02.  2022. x265. https:\/\/www.videolan.org\/developers\/x265.html. Accessed: 2022-03-02."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00853"},{"key":"e_1_3_2_2_7_1","volume-title":"End-to-end Optimized Image Compression. In 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 . 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_2_8_1","volume-title":"6th International Conference on Learning Representations, ICLR","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 . 6th International Conference on Learning Representations, ICLR (2018). Johannes Ball\u00e9, David Minnen, Saurabh Singh, Sung Jin Hwang, and Nick Johnston. 2018. Variational image compression with a scale hyperprior. 6th International Conference on Learning Representations, ICLR (2018)."},{"key":"e_1_3_2_2_9_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_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3101953"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00491"},{"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\/CVPR46437.2021.01039"},{"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","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00713"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01453"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_12"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00155"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00578"},{"key":"e_1_3_2_2_22_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 43, 8 ( 2020 ), 2555--2569. 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 43, 8 (2020), 2555--2569."},{"key":"e_1_3_2_2_23_1","volume-title":"Contextformer: A Transformer with Spatio-Channel Attention for Context Modeling in Learned Image Compression. arXiv preprint arXiv:2203.02452","author":"Koyuncu A Burakhan","year":"2022","unstructured":"A Burakhan Koyuncu , Han Gao , and Eckehard Steinbach . 2022 . Contextformer: A Transformer with Spatio-Channel Attention for Context Modeling in Learned Image Compression. arXiv preprint arXiv:2203.02452 (2022). A Burakhan Koyuncu, Han Gao, and Eckehard Steinbach. 2022. Contextformer: A Transformer with Spatio-Channel Attention for Context Modeling in Learned Image Compression. arXiv preprint arXiv:2203.02452 (2022)."},{"key":"e_1_3_2_2_24_1","volume-title":"Optical Flow and Mode Selection for Learning-based Video Coding. In 22nd IEEE International Workshop on Multimedia Signal Processing.","author":"Ladune Th\u00e9o","year":"2020","unstructured":"Th\u00e9o Ladune , Pierrick Philippe , Wassim Hamidouche , Lu Zhang , and Olivier D\u00e9forges . 2020 . Optical Flow and Mode Selection for Learning-based Video Coding. In 22nd IEEE International Workshop on Multimedia Signal Processing. Th\u00e9o Ladune, Pierrick Philippe, Wassim Hamidouche, Lu Zhang, and Olivier D\u00e9forges. 2020. Optical Flow and Mode Selection for Learning-based Video Coding. In 22nd IEEE International Workshop on Multimedia Signal Processing."},{"key":"e_1_3_2_2_25_1","volume-title":"Conditional Coding and Variable Bitrate for Practical Learned Video Coding. CLIC workshop, CVPR","author":"Ladune Th\u00e9o","year":"2021","unstructured":"Th\u00e9o Ladune , Pierrick Philippe , Wassim Hamidouche , Lu Zhang , and Olivier D\u00e9forges . 2021 . Conditional Coding and Variable Bitrate for Practical Learned Video Coding. CLIC workshop, CVPR (2021). Th\u00e9o Ladune, Pierrick Philippe, Wassim Hamidouche, Lu Zhang, and Olivier D\u00e9forges. 2021. Conditional Coding and Variable Bitrate for Practical Learned Video Coding. CLIC workshop, CVPR (2021)."},{"key":"e_1_3_2_2_26_1","unstructured":"Th\u00e9o Ladune Pierrick Philippe Wassim Hamidouche Lu Zhang and Olivier D\u00e9forges. 2021. Conditional Coding for Flexible Learned Video Compression. In Neural Compression: From Information Theory to Applications -- Workshop @ ICLR.  Th\u00e9o Ladune Pierrick Philippe Wassim Hamidouche Lu Zhang and Olivier D\u00e9forges. 2021. Conditional Coding for Flexible Learned Video Compression. In Neural Compression: From Information Theory to Applications -- Workshop @ ICLR."},{"key":"e_1_3_2_2_27_1","volume-title":"Deep contextual video compression. Advances in Neural Information Processing Systems 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 34 ( 2021 ). Jiahao Li, Bin Li, and Yan Lu. 2021. Deep contextual video compression. Advances in Neural Information Processing Systems 34 (2021)."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00360"},{"key":"e_1_3_2_2_29_1","volume-title":"Neural video coding using multiscale motion compensation and spatiotemporal context model","author":"Liu Haojie","year":"2020","unstructured":"Haojie Liu , Ming Lu , Zhan Ma , Fan Wang , Zhihuang Xie , Xun Cao , and Yao Wang . 2020. Neural video coding using multiscale motion compensation and spatiotemporal context model . IEEE Transactions on Circuits and Systems for Video Technology ( 2020 ). Haojie Liu, Ming Lu, Zhan Ma, Fan Wang, Zhihuang Xie, Xun Cao, and Yao Wang. 2020. Neural video coding using multiscale motion compensation and spatiotemporal context model. IEEE Transactions on Circuits and Systems for Video Technology (2020)."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6825"},{"key":"e_1_3_2_2_31_1","volume-title":"Meet Shah, Rui Hu, Pranaab Dhawan, and Raquel Urtasun. 2020. 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. 2020. 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. 2020. Conditional entropy coding for efficient video compression. In European Conference on Computer Vision. Springer, 453--468."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_27"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01126"},{"key":"e_1_3_2_2_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 ( 2020 ). 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 (2020)."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3339825.3394937"},{"key":"e_1_3_2_2_36_1","volume-title":"Joint autoregressive and hierarchical priors for learned image compression. Advances in neural information processing systems 31","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 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 31 (2018)."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/SiPS50750.2020.9195249"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.291"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01421"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00355"},{"key":"e_1_3_2_2_41_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_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_15"},{"key":"e_1_3_2_2_43_1","volume-title":"5th International Conference on Learning Representations, ICLR","author":"Theis Lucas","year":"2017","unstructured":"Lucas Theis , Wenzhe Shi , Andrew Cunningham , and Ferenc Husz\u00e1r . 2017 . Lossy image compression with compressive autoencoders . 5th International Conference on Learning Representations, ICLR (2017). Lucas Theis, Wenzhe Shi, Andrew Cunningham, and Ferenc Husz\u00e1r. 2017. Lossy image compression with compressive autoencoders. 5th International Conference on Learning Representations, ICLR (2017)."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7532610"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2003.1292216"},{"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","volume-title":"W-net: A deep model for fully unsupervised image segmentation. arXiv preprint arXiv:1711.08506","author":"Xia Xide","year":"2017","unstructured":"Xide Xia and Brian Kulis . 2017 . W-net: A deep model for fully unsupervised image segmentation. arXiv preprint arXiv:1711.08506 (2017). Xide Xia and Brian Kulis. 2017. W-net: A deep model for fully unsupervised image segmentation. arXiv preprint arXiv:1711.08506 (2017)."},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-01144-2"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.3043590"},{"key":"e_1_3_2_2_50_1","volume-title":"9th International Conference on Learning Representations, ICLR","author":"Yang Ruihan","year":"2021","unstructured":"Ruihan Yang , Yibo Yang , Joseph Marino , and Stephan Mandt . 2021 . Hierarchical autoregressive modeling for neural video compression . 9th International Conference on Learning Representations, ICLR (2021). Ruihan Yang, Yibo Yang, Joseph Marino, and Stephan Mandt. 2021. Hierarchical autoregressive modeling for neural video compression. 9th International Conference on Learning Representations, ICLR (2021)."}],"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\/3503161.3547845","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3503161.3547845","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:35Z","timestamp":1750186955000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3547845"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,10]]},"references-count":50,"alternative-id":["10.1145\/3503161.3547845","10.1145\/3503161"],"URL":"https:\/\/doi.org\/10.1145\/3503161.3547845","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"}}]}}