{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T20:00:22Z","timestamp":1775937622431,"version":"3.50.1"},"reference-count":83,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T00:00:00Z","timestamp":1741564800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation","doi-asserted-by":"crossref","award":["62071449, U20A20184"],"award-info":[{"award-number":["62071449, U20A20184"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","award":["E2ET1104"],"award-info":[{"award-number":["E2ET1104"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2025,3,31]]},"abstract":"<jats:p>Recently, many works have applied deep learning techniques to video compression tasks, achieving promising results and advancing the field of Deep Learning-Based Video Compression (DLVC). However, the architecture design of the existing DLVC is rigid and limited in terms of flexibility. Specifically, different networks must be designed for different scenarios, such as delay-constrained scenario or non-delay-constrained scenario. Frequent switching between networks would reduce the speed of modern deep learning platforms and increase the maintenance costs. To address this problem, we propose a Unified Video Compression (UVC) framework that can be freely switched to different application scenarios without changing the network architecture. Our proposed UVC framework is based on the explicit-compression and implicit-generation perspective, which contains two sub-networks\u2014the Explicit Reference Frame Compression Network (ERFCN) and the Implicit Reference Frame Generation Network (IRFGN). The aim of ERFCN is to compress the current frame with the help of the reference frame. To improve the performance of ERFCN, we first introduce the Transformer in this network, which can fully remove the spatial redundancy of the input image and is beneficial for the following inter-prediction process. We also develop a novel long-range motion estimation module for inter-prediction to generate motion vectors based on global motion information between two frames, which can handle long-range complex motion relations. The aim of IRFGN is to capture the temporal relationship between forward and backward reconstructed frames and synthesize a high-quality implicit reference frame for the current frame. To achieve this, we design the split spatial-temporal attention and multi-scale prediction module. We conduct extensive experiments on three widely used video compression databases (HEVC, UVG, and MCL-JVC), and the results demonstrate the superiority of our approach over other related DLVC methods.<\/jats:p>","DOI":"10.1145\/3715144","type":"journal-article","created":{"date-parts":[[2025,1,24]],"date-time":"2025-01-24T15:51:50Z","timestamp":1737733910000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["UVC: A Unified Deep Video Compression Framework"],"prefix":"10.1145","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7359-1057","authenticated-orcid":false,"given":"Lv","family":"Tang","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7517-3868","authenticated-orcid":false,"given":"Xinfeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3463-9211","authenticated-orcid":false,"given":"Li","family":"Zhang","sequence":"additional","affiliation":[{"name":"ByteDance Inc, San Diego, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,3,10]]},"reference":[{"key":"e_1_3_1_2_2","first-page":"1141","volume-title":"NIPS","author":"Agustsson Eirikur","year":"2017","unstructured":"Eirikur Agustsson, Fabian Mentzer, Michael Tschannen, Lukas Cavigelli, Radu Timofte, Luca Benini, and Luc Van Gool. 2017. Soft-to-hard vector quantization for end-to-end learning compressible representations. In NIPS, 1141\u20131151."},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00853"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00031"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/T-C.1974.223784"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00988"},{"key":"e_1_3_1_7_2","first-page":"1","volume-title":"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 ICLR, 1\u201327."},{"key":"e_1_3_1_8_2","first-page":"1","volume-title":"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. In ICLR, 1\u201347."},{"key":"e_1_3_1_9_2","unstructured":"Fabrice Bellard. 2015. BPG Image Format. Retrieved from https:\/\/bellard.org\/bpg\/"},{"key":"e_1_3_1_10_2","unstructured":"Gisle Bjontegaard. 2001. Calculation of average PSNR differences between RD-curves. VCEG-M33."},{"key":"e_1_3_1_11_2","first-page":"675","volume-title":"PMLR","author":"Blau Yochai","year":"2019","unstructured":"Yochai Blau and Tomer Michaeli. 2019. Rethinking lossy compression: The rate-distortion-perception tradeoff. In PMLR, 675\u2013685."},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3101953"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2222904"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3531015"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3301016"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3058615"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP.2017.8305033"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00213"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00796"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/DCC.2017.53"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3059994"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00652"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00713"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01453"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_12"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00583"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00155"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00461"},{"key":"e_1_3_1_30_2","unstructured":"Ivan Kirillov Denis Parkhomenko Kirill Chernyshev Alexander Pletnev Yibo Shi Kai Lin and Dmitry Babin. 2024. Hierarchical B-frame video coding for long group of pictures. arXiv:2406.16544. Retrieved from https:\/\/arxiv.org\/abs\/2406.16544"},{"key":"e_1_3_1_31_2","first-page":"1","volume-title":"ICLR","author":"Lee Jooyoung","year":"2019","unstructured":"Jooyoung Lee, Seunghyun Cho, and Seung-Kwon Beack. 2019. Context-adaptive entropy model for end-to-end optimized image compression. In ICLR, 1\u201320."},{"key":"e_1_3_1_32_2","first-page":"18114","volume-title":"NIPS","author":"Li Jiahao","year":"2021","unstructured":"Jiahao Li, Bin Li, and Yan Lu. 2021. Deep contextual video compression. In NIPS, 18114\u201318125."},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02166"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02466"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00360"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3368405"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2601264"},{"key":"e_1_3_1_39_2","first-page":"1","volume-title":"ICLR","author":"Loshchilov Ilya","year":"2019","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled weight decay regularization. In ICLR, 1\u201318."},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01126"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_35"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2988453"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451166"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2910119"},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00462"},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3339825.3394937"},{"key":"e_1_3_1_47_2","first-page":"10794","volume-title":"NIPS","author":"Minnen David","year":"2018","unstructured":"David Minnen, Johannes Ball\u00e9, and George Toderici. 2018. Joint autoregressive and hierarchical priors for learned image compression. In NIPS, 10794\u201310803."},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3551389"},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3633459"},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/SiPS50750.2020.9195249"},{"key":"e_1_3_1_51_2","first-page":"2922","volume-title":"PMLR","author":"Rippel Oren","year":"2017","unstructured":"Oren Rippel and Lubomir D. Bourdev. 2017. Real-time adaptive image compression. In PMLR, 2922\u20132930."},{"key":"e_1_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00355"},{"key":"e_1_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3220421"},{"key":"e_1_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3360248"},{"key":"e_1_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/79.952804"},{"key":"e_1_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP.2017.8305104"},{"key":"e_1_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2221191"},{"key":"e_1_3_1_58_2","first-page":"1","volume-title":"ICLR","author":"Theis Lucas","year":"2017","unstructured":"Lucas Theis, Wenzhe Shi, Andrew Cunningham, and Ferenc Husz\u00e1r. 2017. Lossy image compression with compressive autoencoders. In ICLR, 1\u201319."},{"key":"e_1_3_1_59_2","first-page":"1","volume-title":"ICLR","author":"Toderici George","year":"2016","unstructured":"George Toderici, Sean M. O\u2019Malley, Sung Jin Hwang, Damien Vincent, David Minnen, Shumeet Baluja, Michele Covell, and Rahul Sukthankar. 2016. Variable rate image compression with recurrent neural networks. In ICLR, 1\u201312."},{"key":"e_1_3_1_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.577"},{"key":"e_1_3_1_61_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_1_62_2","first-page":"5998","volume-title":"NIPS","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In NIPS, 5998\u20136008."},{"key":"e_1_3_1_63_2","doi-asserted-by":"publisher","DOI":"10.1145\/103085.103089"},{"key":"e_1_3_1_64_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7532610"},{"key":"e_1_3_1_65_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3065244"},{"key":"e_1_3_1_66_2","doi-asserted-by":"publisher","DOI":"10.1145\/3631710"},{"key":"e_1_3_1_67_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2003.1292216"},{"key":"e_1_3_1_68_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2003.815165"},{"key":"e_1_3_1_69_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_26"},{"key":"e_1_3_1_70_2","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475213"},{"key":"e_1_3_1_71_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-01144-2"},{"key":"e_1_3_1_72_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2816932"},{"key":"e_1_3_1_73_2","doi-asserted-by":"publisher","DOI":"10.1145\/3661824"},{"key":"e_1_3_1_74_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00666"},{"key":"e_1_3_1_75_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.3043590"},{"key":"e_1_3_1_76_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00697"},{"key":"e_1_3_1_77_2","first-page":"1","volume-title":"ICLR","author":"Yang Ruihan","year":"2021","unstructured":"Ruihan Yang, Yibo Yang, Joseph Marino, and Stephan Mandt. 2021. Hierarchical autoregressive modeling for neural video compression. In ICLR, 1\u201315."},{"key":"e_1_3_1_78_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3138300"},{"key":"e_1_3_1_79_2","doi-asserted-by":"publisher","DOI":"10.1145\/3634705"},{"key":"e_1_3_1_80_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2877355"},{"key":"e_1_3_1_81_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2815841"},{"key":"e_1_3_1_82_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2954474"},{"key":"e_1_3_1_83_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2913545"},{"key":"e_1_3_1_84_2","doi-asserted-by":"publisher","DOI":"10.1145\/3563699"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3715144","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3715144","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:18Z","timestamp":1750295898000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3715144"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,10]]},"references-count":83,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,3,31]]}},"alternative-id":["10.1145\/3715144"],"URL":"https:\/\/doi.org\/10.1145\/3715144","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,10]]},"assertion":[{"value":"2024-10-24","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-12-22","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-03-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}