{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T07:09:07Z","timestamp":1776064147752,"version":"3.50.1"},"reference-count":70,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1109\/tcsvt.2024.3371686","type":"journal-article","created":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T19:01:55Z","timestamp":1709233315000},"page":"7498-7511","source":"Crossref","is-referenced-by-count":24,"title":["Efficient Contextformer: Spatio-Channel Window Attention for Fast Context Modeling in Learned Image Compression"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6291-3476","authenticated-orcid":false,"given":"A. Burakhan","family":"Koyuncu","sequence":"first","affiliation":[{"name":"Department of Computer Engineering, School of Computation, Information and Technology, Chair of Media Technology, Technical University of Munich, Munich, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5480-0137","authenticated-orcid":false,"given":"Panqi","family":"Jia","sequence":"additional","affiliation":[{"name":"Huawei Munich Research Center, Munich, Germany"}]},{"given":"Atanas","family":"Boev","sequence":"additional","affiliation":[{"name":"Huawei Munich Research Center, Munich, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7099-5371","authenticated-orcid":false,"given":"Elena","family":"Alshina","sequence":"additional","affiliation":[{"name":"Huawei Munich Research Center, Munich, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8853-2703","authenticated-orcid":false,"given":"Eckehard","family":"Steinbach","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, School of Computation, Information and Technology, Chair of Media Technology, Technical University of Munich, Munich, Germany"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2910119"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-019-08572-3"},{"key":"ref3","first-page":"1","article-title":"End-to-end optimized image compression","volume-title":"Proc. 5th Int. Conf. Learn. Represent. ICLR","author":"Ball\u00e9"},{"key":"ref4","first-page":"1","article-title":"Variational image compression with a scale hyperprior","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ball\u00e9"},{"key":"ref5","first-page":"1","article-title":"Joint autoregressive and hierarchical priors for learned image compression","volume-title":"Proc. NeurIPS","author":"Minnen"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3058615"},{"key":"ref7","article-title":"Multi-scale and context-adaptive entropy model for image compression","author":"Zhou","year":"2019","journal-title":"arXiv:1910.07844"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01039"},{"key":"ref9","article-title":"Context-adaptive entropy model for end-to-end optimized image compression","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lee"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00462"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00796"},{"key":"ref12","article-title":"Learning accurate entropy model with global reference for image compression","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Qian"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2985225"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP53242.2021.9675377"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01453"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9190935"},{"key":"ref17","article-title":"Entroformer: A transformer-based entropy model for learned image compression","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Qian"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/30.125072"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/79.952804"},{"key":"ref20","volume-title":"BPG Image Format","author":"Bellard","year":"2015"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-06895-4"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00563"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3089491"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19800-7_26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/vcip49819.2020.9301847"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01383"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.3034501"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2223056"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref30","volume-title":"Versatile Video Coding (VVC) Reference Software: Vvc Test Model (VTM)","year":"2022"},{"key":"ref31","volume-title":"Kodak lossless true color image suite","author":"Franzen","year":"1999"},{"key":"ref32","article-title":"Workshop and challenge on learned image compression (CLIC 2020)","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Toderici"},{"key":"ref33","first-page":"63","article-title":"TESTIMAGES: A large-scale archive for testing visual devices and basic image processing algorithms","volume-title":"Proc. STAG","author":"Asuni"},{"key":"ref34","article-title":"Content adaptive optimization for neural image compression","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. Workshops","author":"Campos"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref36","article-title":"Imagenet classification with deep convolutional neural networks","volume-title":"Advances in Neural Information Processing Systems","volume":"25","author":"Krizhevsky","year":"2012"},{"key":"ref37","first-page":"23296","article-title":"Intriguing properties of vision transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Naseer"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref39","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref40","article-title":"TransGAN: Two transformers can make one strong GAN","author":"Jiang","year":"2021","journal-title":"arXiv:2102.07074"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref42","first-page":"4055","article-title":"Image transformer","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Parmar"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1147\/rd.232.0149"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3199472"},{"key":"ref45","article-title":"EVC: Towards real-time neural image compression with mask decay","author":"Wang","year":"2023","journal-title":"arXiv:2302.05071"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3237274"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00055"},{"key":"ref48","first-page":"573","article-title":"Improving inference for neural image compression","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Yang"},{"key":"ref49","first-page":"12184","article-title":"Flexible neural image compression via code editing","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Gao"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2023.3245919"},{"key":"ref51","volume-title":"Calculation of Average PSNR Differences Between RD-curves","author":"Bjontegaard","year":"2001"},{"key":"ref52","article-title":"Density modeling of images using a generalized normalization transformation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ball\u00e9"},{"key":"ref53","first-page":"1","article-title":"Residual non-local attention networks for image restoration","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref54","volume-title":"Making Pytorch Transformer Twice As Fast on Sequence Generation","author":"Matton","year":"2020"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-demo.26"},{"key":"ref56","article-title":"CompressAI: A Pytorch library and evaluation platform for end-to-end compression research","author":"B\u00e9gaint","year":"2020","journal-title":"arXiv:2011.03029"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-01144-2"},{"key":"ref58","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2003.1292216"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref61","first-page":"8024","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Paszke","year":"2019"},{"key":"ref62","volume-title":"TensorFlow: Large-scale Machine Learning on Heterogeneous Systems","author":"Abadi","year":"2015"},{"key":"ref63","volume-title":"PTflops: A Flops Counting Tool for Neural Networks in Pytorch Framework","author":"Sovrasov","year":"2023"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"ref65","volume-title":"Cuda, Release: 11.4","year":"2021"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.150"},{"key":"ref68","article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","author":"Bengio","year":"2013","journal-title":"arXiv:1308.3432"},{"key":"ref69","first-page":"2546","article-title":"Algorithms for hyper-parameter optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"24","author":"Bergstra"},{"key":"ref70","volume-title":"Notes on Contemporary Machine Learning for Physicists","author":"Kaplan","year":"2019"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10634006\/10453616.pdf?arnumber=10453616","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T05:11:25Z","timestamp":1723525885000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10453616\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":70,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3371686","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8]]}}}