{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:44:35Z","timestamp":1772909075718,"version":"3.50.1"},"reference-count":84,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","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":[[2025,7]]},"DOI":"10.1109\/tpami.2025.3548516","type":"journal-article","created":{"date-parts":[[2025,3,5]],"date-time":"2025-03-05T18:47:30Z","timestamp":1741200450000},"page":"5501-5519","source":"Crossref","is-referenced-by-count":4,"title":["Rate-Distortion Theory in Coding for Machines and Its Applications"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1287-9860","authenticated-orcid":false,"given":"Alon","family":"Harell","sequence":"first","affiliation":[{"name":"Simon Fraser University, Burnaby, BC, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3462-2405","authenticated-orcid":false,"given":"Yalda","family":"Foroutan","sequence":"additional","affiliation":[{"name":"Simon Fraser University, Burnaby, BC, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9467-4628","authenticated-orcid":false,"given":"Nilesh","family":"Ahuja","sequence":"additional","affiliation":[{"name":"Intel Labs, Hillsboro, OR, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Parual","family":"Datta","sequence":"additional","affiliation":[{"name":"Intel Labs, Hillsboro, OR, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0599-8879","authenticated-orcid":false,"given":"Bhavya","family":"Kanzariya","sequence":"additional","affiliation":[{"name":"Intel Labs, Hillsboro, OR, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"V. Srinivasa","family":"Somayazulu","sequence":"additional","affiliation":[{"name":"Intel Labs, Hillsboro, OR, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Omesh","family":"Tickoo","sequence":"additional","affiliation":[{"name":"Intel Labs, Hillsboro, OR, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anderson","family":"de Andrade","sequence":"additional","affiliation":[{"name":"Simon Fraser University, Burnaby, BC, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3154-5743","authenticated-orcid":false,"given":"Ivan V.","family":"Baji\u0107","sequence":"additional","affiliation":[{"name":"Simon Fraser University, Burnaby, BC, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"YOLOv3: An incremental improvement","author":"Redmon","year":"2018"},{"key":"ref2","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref7","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref8","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2022"},{"key":"ref9","first-page":"27826","article-title":"Unsupervised speech recognition","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Baevski"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2018.112130030"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ETS.2019.8791554"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IOTM.001.2200152"},{"key":"ref15","volume-title":"Versatile Video Coding","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3403\/30310209"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3160602"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3093337.3037698"},{"key":"ref19","first-page":"10771","article-title":"Joint autoregressive and hierarchical priors for learned image compression","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Minnen"},{"key":"ref20","article-title":"End-to-end optimized image compression","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ball\u00e9"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00796"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00563"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611694"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/OJCAS.2021.3123201"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00355"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_12"},{"key":"ref27","article-title":"Scalable neural video representations with learnable positional features","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kim"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/30.125072"},{"key":"ref29","volume-title":"High Efficiency Video Coding","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1117\/12.2555368"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ITW.2015.7133169"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00100"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1002\/0471200611"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCOM.1972.1091311"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462653"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451100"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956232"},{"key":"ref40","article-title":"Towards image understanding from deep compression without decoding","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Torfason"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/PCS56426.2022.10018075"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.2018.8547134"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3068580"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3121131"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP55362.2022.9949576"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2022.3207596"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1186\/s13640-024-00657-w"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/PCS60826.2024.10566441"},{"key":"ref49","article-title":"A theory of usable information under computational constraints","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xu"},{"key":"ref50","first-page":"14014","article-title":"Lossy compression for lossless prediction","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dubois"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3060875"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/PCS56426.2022.10018035"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/DCC50243.2021.00024"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICME46284.2020.9102797"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/0377-0427(87)90125-7"},{"key":"ref56","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref58","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"issue":"11","key":"ref59","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref60","article-title":"Calculation of average PSNR differences between RD-curves","author":"Bj\u00f8ntegaard","year":"2001"},{"key":"ref61","volume-title":"Common Test Conditions and Evaluation Methodology for Video Coding for Machines","year":"2022"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00201"},{"key":"ref63","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017"},{"key":"ref64","article-title":"Variational image compression with a scale hyperprior","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ball\u00e9"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref66","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref68","volume-title":"Call for Evidence for Video Coding for Machines","author":"Zhang","year":"2022"},{"key":"ref69","article-title":"Density modeling of images using a generalized normalization transformation","author":"Ball\u00e9","year":"2015"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01453"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9190935"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-01144-2"},{"key":"ref74","article-title":"Detectron2","author":"Wu","year":"2019"},{"key":"ref77","article-title":"CompressAI: A PyTorch library and evaluation platform for end-to-end compression research","author":"B\u00e9gaint","year":"2020"},{"key":"ref78","article-title":"darknet","author":"Bochkovskiy","year":"2019"},{"key":"ref79","article-title":"DarkNet: Open source neural networks in C","author":"Redmon","year":"2016"},{"key":"ref80","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref81","first-page":"5621","article-title":"RepPoints V2: Verification meets regression for object detection","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref82","article-title":"MMDetection: Open MMLab detection toolbox and benchmark","author":"Chen","year":"2019"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW53276.2021.9455944"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00342"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610894"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP59012.2023.10337709"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803275"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3348995"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11026037\/10912768.pdf?arnumber=10912768","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T17:42:23Z","timestamp":1749231743000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10912768\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":84,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3548516","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":[[2025,7]]}}}