{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T18:00:51Z","timestamp":1772042451528,"version":"3.50.1"},"reference-count":78,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"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":["62171429"],"award-info":[{"award-number":["62171429"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61931014"],"award-info":[{"award-number":["61931014"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62021001"],"award-info":[{"award-number":["62021001"]}],"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","award":["WK3490000006"],"award-info":[{"award-number":["WK3490000006"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["WK3490000007"],"award-info":[{"award-number":["WK3490000007"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"GPU cluster built"},{"name":"MCC Lab of Information Science and Technology Institution"},{"DOI":"10.13039\/501100009076","name":"University of Science and Technology of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100009076","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":[[2024,7]]},"DOI":"10.1109\/tpami.2024.3356548","type":"journal-article","created":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T18:40:21Z","timestamp":1705948821000},"page":"4579-4596","source":"Crossref","is-referenced-by-count":21,"title":["VNVC: A Versatile Neural Video Coding Framework for Efficient Human-Machine Vision"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7350-4929","authenticated-orcid":false,"given":"Xihua","family":"Sheng","sequence":"first","affiliation":[{"name":"CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7163-6263","authenticated-orcid":false,"given":"Li","family":"Li","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9100-2906","authenticated-orcid":false,"given":"Dong","family":"Liu","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2188-3028","authenticated-orcid":false,"given":"Houqiang","family":"Li","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System, University of Science and Technology of China, Hefei, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"Cisco visual networking index (VNI) complete forecast update, 2017\u20132022","author":"Barnett","year":"2018","journal-title":"Americas\/EMEAR Cisco Knowl. Netw. Presentation"},{"key":"ref2","article-title":"Recent standard development activities on video coding for machines","author":"Gao","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803136"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00143"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00342"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00247"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00477"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3243059"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20272"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3029799"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.52"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3042517"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_1"},{"key":"ref17","first-page":"2491","article-title":"Associating objects with transformers for video object segmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.565"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2023.3245919"},{"key":"ref20","article-title":"JPEG AI use cases and requirements","author":"Ascenso","year":"2021","journal-title":"ISO\/IEC JTC1\/SC29\/WG1 M90014"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2500034"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2018.2873844"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3016485"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICME46284.2020.9102843"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2023.103816"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP55362.2022.9949576"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2988453"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00360"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3210652"},{"key":"ref30","first-page":"18 114","article-title":"Deep contextual video compression","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3220421"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19800-7_36"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_12"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547845"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1023\/b:visi.0000029664.99615.94"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2941660"},{"key":"ref37","article-title":"Use cases and requirements for video coding for machines","author":"Zhang","year":"2021","journal-title":"ISO\/IEC JTC"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_26"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_27"},{"key":"ref40","article-title":"VCT: A video compression transformer","author":"Mentzer","year":"2022"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00713"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_15"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2221191"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2003.815165"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3101953"},{"key":"ref46","article-title":"Variational image compression with a scale hyperprior","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ball\u00e9"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.291"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.179"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref50","article-title":"End-to-end optimized image compression","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ball\u00e9"},{"key":"ref51","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":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2913372"},{"key":"ref53","article-title":"W-Net: A deep model for fully unsupervised image segmentation","author":"Xia","year":"2017"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00210"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00931"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00023"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-01144-2"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3339825.3394937"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7532610"},{"key":"ref63","article-title":"Doc. JCTVC-N1006: Common test conditions and software reference configurations for HEVC range extensions","author":"David","year":"2013","journal-title":"Joint Collaborative Team on Video Coding (JCT-VC) ITU-T SG"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00251"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.127"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00474"},{"key":"ref68","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref69","first-page":"5843","article-title":"The \u201csomething something","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Goyal"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2016.10.018"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref72","article-title":"MOT16: A benchmark for multi-object tracking","author":"Milan","year":"2016"},{"key":"ref73","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2003.1292216"},{"key":"ref75","article-title":"OpenMMLabs next generation video understanding toolbox and benchmark","year":"2020"},{"key":"ref76","article-title":"MMTracking: OpenMMLab video perception toolbox and benchmark","year":"2020"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00578"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.3390\/fi12070120"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10550108\/10411051.pdf?arnumber=10411051","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,6]],"date-time":"2025-01-06T19:28:55Z","timestamp":1736191735000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10411051\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":78,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3356548","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":[[2024,7]]}}}