{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:28:52Z","timestamp":1787012932896,"version":"build-2736575974"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Shenzhen Science and Technology Program","award":["JCYJ20220530140816037"],"award-info":[{"award-number":["JCYJ20220530140816037"]}]},{"name":"Innovation and Technology Fund Project","award":["GHP\/044\/21SZ"],"award-info":[{"award-number":["GHP\/044\/21SZ"]}]},{"name":"Innovation and Technology Fund Project","award":["MHP\/061\/23"],"award-info":[{"award-number":["MHP\/061\/23"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tcsvt.2025.3564264","type":"journal-article","created":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T13:42:24Z","timestamp":1745588544000},"page":"10493-10499","source":"Crossref","is-referenced-by-count":3,"title":["Learning Spatio-Temporal Resolutions for Deep Video Compression"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-8199-9657","authenticated-orcid":false,"given":"Jiancong","family":"Chen","sequence":"first","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6636-522X","authenticated-orcid":false,"given":"Peilin","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3583-959X","authenticated-orcid":false,"given":"Shiqi","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2003.815165"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2221191"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3101953"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01126"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00155"},{"key":"ref6","first-page":"18114","article-title":"Deep contextual video compression","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"34","author":"Li"},{"issue":"9","key":"ref7","doi-asserted-by":"crossref","first-page":"2513","DOI":"10.1109\/TIP.2006.877415","article-title":"Adaptive downsampling to improve image compression at low bit rates","volume":"15","author":"Lin","year":"2006","journal-title":"IEEE Trans. Image Process."},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2025.117277"},{"key":"ref9","article-title":"Joint hierarchical priors and adaptive spatial resolution for efficient neural image compression","author":"Ghorbel","year":"2023","journal-title":"arXiv:2307.02273"},{"issue":"11","key":"ref10","doi-asserted-by":"crossref","first-page":"1957","DOI":"10.1109\/TCSVT.2014.2302519","article-title":"Adaptive downsampling video coding with spatially scalable rate-distortion modeling","volume":"24","author":"Wang","year":"2014","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref11","doi-asserted-by":"crossref","first-page":"1702","DOI":"10.1109\/TIP.2020.3046872","article-title":"RR-DnCNN v2.0: Enhanced restoration-reconstruction deep neural network for down-sampling-based video coding","volume":"30","author":"Ho","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"ref12","first-page":"1","article-title":"Video compression with arbitrary rescaling network","volume-title":"Proc. Data Compress. Conf. (DCC)","author":"Guo"},{"issue":"5","key":"ref13","doi-asserted-by":"crossref","first-page":"4027","DOI":"10.1109\/TCSVT.2023.3313611","article-title":"Sparse-to-dense: High efficiency rate control for end-to-end scale-adaptive video coding","volume":"34","author":"Chen","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"11","key":"ref14","doi-asserted-by":"crossref","first-page":"4508","DOI":"10.1109\/TCSVT.2020.3046881","article-title":"Quality-driven variable frame-rate for green video coding in broadcast applications","volume":"31","author":"Herrou","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref15","first-page":"2821","article-title":"Learning-based end-to-end video compression with spatial\u2013temporal adaptation","volume-title":"Proc. IEEE Int. Conf. Image Process. (ICIP)","author":"Zhang"},{"issue":"1","key":"ref16","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1109\/TCSVT.2018.2878952","article-title":"Video compression based on spatio-temporal resolution adaptation","volume":"29","author":"Afonso","year":"2019","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref17","first-page":"1785","article-title":"Learned low bitrate video compression with space-time super-resolution","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. Workshops (CVPRW)","author":"Yang"},{"key":"ref18","first-page":"3526","article-title":"Video rescaling networks with joint optimization strategies for downscaling and upscaling","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Huang"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"1300","DOI":"10.1109\/TIP.2023.3242774","article-title":"CLSA: A contrastive learning framework with selective aggregation for video rescaling","volume":"32","author":"Tian","year":"2023","journal-title":"IEEE Trans. Image Process."},{"key":"ref20","first-page":"2523","article-title":"COMISR: Compression-informed video super-resolution","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis. (ICCV)","author":"Li"},{"issue":"3","key":"ref21","doi-asserted-by":"crossref","first-page":"660","DOI":"10.3390\/electronics12030660","article-title":"Lightweight video super-resolution for compressed video","volume":"12","author":"Kwon","year":"2023","journal-title":"Electronics"},{"key":"ref22","first-page":"1578","article-title":"A unified pyramid recurrent network for video frame interpolation","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Jin"},{"issue":"11","key":"ref23","first-page":"1","article-title":"CycMuNet+: Cycle-projected mutual learning for spatial\u2013temporal video super-resolution","volume":"45","author":"Hu","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19797-0_10"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104425"},{"key":"ref27","first-page":"2017","article-title":"Spatial transformer networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Jaderberg"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"4259","DOI":"10.1109\/TIP.2023.3296891","article-title":"Scale-arbitrary invertible image downscaling","volume":"32","author":"Xing","year":"2023","journal-title":"IEEE Trans. Image Process."},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-01144-2"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3339825.3394937"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7532610"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2880603"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2015.7351309"},{"key":"ref34","volume-title":"Calculation of Average PSNR Differences Between RD-Curves","author":"Bjontegaard","year":"2001"},{"key":"ref35","volume-title":"Toward a Practical Perceptual Video Quality Metric","author":"Li","year":"2016"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11192799\/10976735.pdf?arnumber=10976735","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T17:39:49Z","timestamp":1759772389000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10976735\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":35,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3564264","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}