{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:32:41Z","timestamp":1787013161840,"version":"build-2736575974"},"reference-count":90,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["62431015"],"award-info":[{"award-number":["62431015"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["24511106200"],"award-info":[{"award-number":["24511106200"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Fundamental Research Funds for the Central Universities, Shanghai Key Laboratory of Digital Media Processing and Transmission","award":["22DZ2229005"],"award-info":[{"award-number":["22DZ2229005"]}]},{"DOI":"10.13039\/501100013314","name":"Higher Education Discipline Innovation Project","doi-asserted-by":"publisher","award":["BP0719010"],"award-info":[{"award-number":["BP0719010"]}],"id":[{"id":"10.13039\/501100013314","id-type":"DOI","asserted-by":"publisher"}]},{"name":"SJTU-Waseda Seed Research Fund and Ant Group Research Fund"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2025.3602648","type":"journal-article","created":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T19:32:52Z","timestamp":1756755172000},"page":"5776-5791","source":"Crossref","is-referenced-by-count":1,"title":["Instance-Adaptive Spatial-Temporal Enhancement for Efficient Video Compression"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-3776-0329","authenticated-orcid":false,"given":"Yan","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5364-7427","authenticated-orcid":false,"given":"Zhengxue","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2681-5159","authenticated-orcid":false,"given":"Jiangchuan","family":"Li","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8984-0425","authenticated-orcid":false,"given":"Donghui","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qunshan","family":"Gu","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1825-9091","authenticated-orcid":false,"given":"Qi","family":"Wang","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, 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":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7124-5182","authenticated-orcid":false,"given":"Li","family":"Song","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Electrical Engineering and the MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/PCS.2018.8456249"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3101953"},{"key":"ref3","article-title":"VCT: A video compression transformer","author":"Mentzer","year":"2022","journal-title":"arXiv:2206.07307"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01126"},{"key":"ref5","first-page":"18114","article-title":"Deep contextual video compression","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"34","author":"Li"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00155"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3138300"},{"key":"ref8","first-page":"1","article-title":"Neural rate control for learned video compression","volume-title":"Proc. The 12th Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3276333"},{"key":"ref10","first-page":"72692","article-title":"HiNeRV: Video compression with hierarchical encoding-based neural representation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kwan"},{"key":"ref11","article-title":"NVRC: Neural video representation compression","author":"Man Kwan","year":"2024","journal-title":"arXiv:2409.07414"},{"key":"ref12","first-page":"645","article-title":"Neural adaptive content-aware Internet video delivery","volume-title":"Proc. USENIX Symp. Oper. Syst. Design Implement.","author":"Yeo"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155384"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3419185"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405856"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00448"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3229079"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19797-0_18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3151259"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00989"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096031"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3377372"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00803"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_30"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10147-y"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00588"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01177"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.37"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00382"},{"key":"ref30","first-page":"624","article-title":"Real-time intermediate flow estimation for video frame interpolation","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Zhewei"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01696"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00293"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6788"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00343"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00632"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00209"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02608"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02114"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01692"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3293522"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00418"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3665646"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref44","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv:2106.09685"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25160"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2969554"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00459"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3374104"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72855-6_21"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00247"},{"key":"ref51","first-page":"1","article-title":"Convolutional LSTM network: A machine learning approach for precipitation nowcasting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Shi"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00355"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref56","article-title":"UniFormer: Unified transformer for efficient spatiotemporal representation learning","author":"Li","year":"2022","journal-title":"arXiv:2201.04676"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00995"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref59","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016","journal-title":"arXiv:1606.08415"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00210"},{"key":"ref62","first-page":"30392","article-title":"Early convolutions help transformers see better","volume-title":"Proc. NIPS","author":"Xiao"},{"key":"ref63","article-title":"Deep multi-scale video prediction beyond mean square error","author":"Mathieu","year":"2015","journal-title":"arXiv:1511.05440"},{"key":"ref64","volume":"3","author":"Duda","year":"1973","journal-title":"Pattern Classification and Scene Analysis"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.2019.8901772"},{"issue":"10","key":"ref66","first-page":"70","article-title":"Image interpolation techniques in digital image processing: An overview","volume":"4","author":"Fadnavis","year":"2014","journal-title":"Int. J. Eng. Res. Appl."},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/T-C.1974.223784"},{"key":"ref68","volume-title":"Jvet Common Test Conditions and Software Reference Configurations"},{"key":"ref69","volume-title":"Uvg Dataset: A High-Resolution Video Dataset for Video Compression Research","year":"2018"},{"key":"ref70","volume-title":"Xiph.Org Video Test Media: Derf\u2019s Collection","year":"2004"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02466"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW53276.2021.9455944"},{"key":"ref73","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref74","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016","journal-title":"arXiv:1608.03983"},{"key":"ref75","volume-title":"PySceneDetect","author":"Castellano","year":"2025"},{"key":"ref76","volume-title":"Ffmpeg","year":"2000"},{"key":"ref77","volume-title":"Xz Utils: General-Purpose Data Compression Software With a High Compression Ratio","year":"2023"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.151"},{"key":"ref79","article-title":"Wide activation for efficient and accurate image super-resolution","author":"Yu","year":"2018","journal-title":"arXiv:1808.08718"},{"key":"ref80","volume-title":"Calculation of Average PSNR Differences Between RD-curves","author":"Bj{\\o}ntegaard","year":"2001"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1175\/1520-0450(1979)018<1016:LFIOAT>2.0.CO;2"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1985.13124"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref84","volume-title":"Vmaf: The Journey Towards a Perceptual Video Quality Metric","author":"Zhi Li","year":"2016"},{"key":"ref85","volume-title":"X265 Hevc Encoder \/ H.265 Video Codec","year":"2025"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2221191"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02166"},{"key":"ref88","first-page":"1","article-title":"Cupy: A numpy-compatible library for NVIDIA GPU calculations","volume-title":"Proc. Workshop Mach. Learn. Syst. (LearningSys)","author":"Okuta"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2010.118"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511779633"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/11146415.pdf?arnumber=11146415","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T05:11:52Z","timestamp":1759295512000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11146415\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":90,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3602648","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}