{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T10:47:58Z","timestamp":1781174878992,"version":"3.54.1"},"reference-count":90,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Hong Kong Research Grants Council General Research Fund","award":["11203220"],"award-info":[{"award-number":["11203220"]}]},{"name":"Hong Kong Research Grants Council General Research Fund","award":["11200323"],"award-info":[{"award-number":["11200323"]}]},{"DOI":"10.13039\/501100010428","name":"Innovation and Technology Fund","doi-asserted-by":"publisher","award":["GHP\/044\/21SZ"],"award-info":[{"award-number":["GHP\/044\/21SZ"]}],"id":[{"id":"10.13039\/501100010428","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/tcsvt.2024.3488181","type":"journal-article","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T17:59:16Z","timestamp":1730311156000},"page":"2870-2880","source":"Crossref","is-referenced-by-count":7,"title":["High Efficiency Image Compression for Large Visual-Language Models"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1535-0121","authenticated-orcid":false,"given":"Binzhe","family":"Li","sequence":"first","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Pokfulam, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shurun","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, 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, Pokfulam, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7278-0822","authenticated-orcid":false,"given":"Yan","family":"Ye","sequence":"additional","affiliation":[{"name":"Alibaba Group U.S., Sunnyvale, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3638036.3640291"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2003.815165"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2221191"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3101953"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-021-3461-9"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01126"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00360"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3233221"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3316429"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19800-7_36"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3319275"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10222075"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3441049"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3348995"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ISM52913.2021.00046"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/DCC50243.2021.00049"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428417"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/DCC50243.2021.00024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3094300"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2022.3195322"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3230843"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350849"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9190843"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053011"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/DCC47342.2020.00044"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9190933"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref29","first-page":"2961","article-title":"Mask RCNN","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"He"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"ref31","first-page":"1","article-title":"SimVLM: Simple visual language model pretraining with weak supervision","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref32","article-title":"PanGu-\u03c0: Enhancing language model architectures via nonlinearity compensation","author":"Wang","year":"2023","journal-title":"arXiv:2312.17276"},{"key":"ref33","first-page":"23318","article-title":"OFA: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref34","article-title":"ONE-PEACE: Exploring one general representation model toward unlimited modalities","author":"Wang","year":"2023","journal-title":"arXiv:2305.11172"},{"key":"ref35","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"arXiv:2301.12597"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/30.125072"},{"issue":"2","key":"ref37","doi-asserted-by":"crossref","first-page":"286","DOI":"10.1117\/1.1469618","article-title":"JPEG2000: Image compression fundamentals, standards and practice","volume":"11","author":"Rabbani","year":"2002","journal-title":"J. Electron. Imag."},{"key":"ref38","first-page":"2","article-title":"Webp: A new image compression format based on VP8 encoding","volume":"3","author":"Lian","year":"2012","journal-title":"Microcontrollers Embedded Syst."},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/iNIS.2015.12"},{"key":"ref40","volume-title":"Generic Coding of Moving Pictures and Associated Audio Information: Video","year":"1995"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3043399"},{"key":"ref42","first-page":"1","article-title":"Variable rate image compression with recurrent neural networks","volume-title":"Proc. ICLR","author":"Toderici"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-73600-6_6"},{"key":"ref44","first-page":"1","article-title":"End-to-end optimized image compression","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ball\u00e9"},{"key":"ref45","first-page":"1","article-title":"Variational image compression with a scale hyperprior","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ball\u00e9"},{"key":"ref46","first-page":"1","article-title":"Joint autoregressive and hierarchical priors for learned image compression","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Minnen"},{"key":"ref47","article-title":"Density modeling of images using a generalized normalization transformation","author":"Ball\u00e9","year":"2015","journal-title":"arXiv:1511.06281"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00796"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00155"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02166"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096674"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414465"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/OJCAS.2021.3126061"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3356548"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3068580"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2500034"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2018.2873844"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_7"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2965306"},{"key":"ref60","article-title":"End-to-end facial deep learning feature compression with teacher\u2013student enhancement","author":"Wang","year":"2020","journal-title":"arXiv:2002.03627"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3302858"},{"key":"ref62","volume-title":"Call for Proposals for Feature Compression for Video Coding for Machines","year":"2024"},{"key":"ref63","volume-title":"AHG15: Feature Based Encoder-Only Algorithms for the Video Coding for Machines","author":"Li","year":"2023"},{"key":"ref64","volume-title":"[VCM] Adaptive Spatial Resampling Based on MI-RPR for VCM","author":"Kim","year":"2023"},{"key":"ref65","volume-title":"[VCM] Response To CFP on Video Coding for Machines From China Telecom","author":"Wang","year":"2022"},{"key":"ref66","volume-title":"AHG8: A Post-processing Algorithm for Machine Consumption","author":"Li","year":"2024"},{"key":"ref67","first-page":"4055","article-title":"Image transformer","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Parmar"},{"key":"ref68","article-title":"Generating long sequences with sparse transformers","author":"Child","year":"2019","journal-title":"arXiv:1904.10509"},{"key":"ref69","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref70","article-title":"BEiT: BERT pre-training of image transformers","author":"Bao","year":"2021","journal-title":"arXiv:2106.08254"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref75","article-title":"Layer normalization","author":"Lei Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_2"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref78","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":"ref79","first-page":"2793","article-title":"Attention is not all you need: Pure attention loses rank doubly exponentially with depth","volume-title":"Proc. 38th Int. Conf. Mach. Learn. (ICML)","author":"Dong"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref82","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"Chen","year":"2015","journal-title":"arXiv:1504.00325"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref86","volume-title":"Calculation of Average PSNR Differences Between RD-curves","author":"Bjontegaard","year":"2001"},{"key":"ref87","volume-title":"Common Test Conditions for Video Coding for Machines","author":"Zhang","year":"2021"},{"key":"ref88","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Represent.","author":"Kingma"},{"key":"ref89","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016","journal-title":"arXiv:1608.03983"},{"key":"ref90","volume-title":"The VVCSoftware Website","year":"2022"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10916540\/10738826.pdf?arnumber=10738826","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T18:52:41Z","timestamp":1741373561000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10738826\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":90,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3488181","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}