{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T18:21:52Z","timestamp":1782930112698,"version":"3.54.5"},"reference-count":137,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62225112"],"award-info":[{"award-number":["62225112"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key R&D Program of China","award":["2021YFE0206700"],"award-info":[{"award-number":["2021YFE0206700"]}]},{"name":"Shanghai Municipal Science and Technology","award":["2021SHZDZX0102"],"award-info":[{"award-number":["2021SHZDZX0102"]}]},{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["22DZ2229005"],"award-info":[{"award-number":["22DZ2229005"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1109\/tpami.2024.3367879","type":"journal-article","created":{"date-parts":[[2024,2,20]],"date-time":"2024-02-20T18:50:02Z","timestamp":1708455002000},"page":"5852-5872","source":"Crossref","is-referenced-by-count":41,"title":["A Coding Framework and Benchmark Towards Low-Bitrate Video Understanding"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6073-8582","authenticated-orcid":false,"given":"Yuan","family":"Tian","sequence":"first","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6951-0090","authenticated-orcid":false,"given":"Guo","family":"Lu","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3209-8965","authenticated-orcid":false,"given":"Yichao","family":"Yan","sequence":"additional","affiliation":[{"name":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8165-9322","authenticated-orcid":false,"given":"Guangtao","family":"Zhai","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9899-2535","authenticated-orcid":false,"given":"Li","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyong","family":"Gao","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2938758"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref6","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00129"},{"key":"ref8","article-title":"Benchmarking the robustness of spatial-temporal models against corruptions","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track (Round 2)","author":"Yi"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS48785.2022.9937612"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3101953"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2629447"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2502552"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2015.7351258"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1999.790410"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/11744023_32"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2018.2873844"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2500034"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2013.6571989"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2012.6467407"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8546064"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462653"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428417"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_19"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3056134"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01505-4"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.2018.8547134"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350849"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2941660"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9190860"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_29"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01403"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3068580"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01491-7"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3121131"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506712"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3042517"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414465"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19884"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICME46284.2020.9102750"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3180208"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413968"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3160602"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3367293"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3016485"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref48","article-title":"Hybrid video and feature coding and decoding","author":"Veselov","year":"2021"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2003.815165"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2221191"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00445"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3242774"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2988453"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00155"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2003.1292216"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803255"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1117\/12.298354"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2000.899352"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CISP.2009.5303718"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2011.2148490"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2127464"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2004.826768"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2214049"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/access.2019.2921975"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00720"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01358"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2021.103188"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.297"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00631"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00136"},{"key":"ref72","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Simonyan"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2868668"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01661-1"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00055"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_5"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3183112"},{"key":"ref84","first-page":"1","article-title":"","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Zhang"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_40"},{"key":"ref87","article-title":"Variational image compression with a scale hyperprior","author":"Ball\u00e9","year":"2018"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1147\/rd.282.0135"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2913372"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01142"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6693"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.207"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2968521"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref99","first-page":"10794","article-title":"Joint autoregressive and hierarchical priors for learned image compression","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Minnen"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3203630"},{"key":"ref104","article-title":"Categorical reparameterization with Gumbel-Softmax","author":"Jang","year":"2016"},{"key":"ref105","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_32"},{"key":"ref109","article-title":"MOT16: A benchmark for multi-object tracking","author":"Milan","year":"2016"},{"key":"ref110","article-title":"SFU-HW-Tracks-v1: Object tracking dataset on raw video sequences","author":"Tanaka","year":"2021"},{"key":"ref111","article-title":"The 2017 Davis challenge on video object segmentation","author":"Pont-Tuset","year":"2017"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2020.106701"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_26"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.57"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_2"},{"key":"ref118","article-title":"Calculation of average PSNR differences between RD-curves (VCEG-M33)","author":"Bj\u00f8ntegaard","year":"2001","journal-title":"Proc. VCEG Meeting (ITU-T SG16 Q.6)"},{"key":"ref119","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref120","first-page":"18114","article-title":"Deep contextual video compression","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00583"},{"key":"ref122","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW53276.2021.9455944"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/214"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2007.905532"},{"key":"ref128","article-title":"Converting video formats with FFmpeg","volume":"2006","author":"Tomar","year":"2006","journal-title":"Linux J."},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00248"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01126"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00588"},{"key":"ref138","first-page":"675","article-title":"Rethinking lossy compression: The rate-distortion-perception tradeoff","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Blau"},{"key":"ref139","first-page":"6629","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Heusel"},{"key":"ref140","first-page":"18661","article-title":"Supervised contrastive learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Khosla"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6697"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00254"},{"key":"ref143","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.164"},{"key":"ref145","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP48831.2020.9287049"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10582780\/10440520.pdf?arnumber=10440520","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T19:09:59Z","timestamp":1725995399000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10440520\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":137,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3367879","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8]]}}}