{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T19:27:47Z","timestamp":1783106867540,"version":"3.54.6"},"reference-count":82,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tpami.2022.3233482","type":"journal-article","created":{"date-parts":[[2023,1,2]],"date-time":"2023-01-02T19:00:18Z","timestamp":1672686018000},"page":"1-13","source":"Crossref","is-referenced-by-count":29,"title":["Dynamic Unary Convolution in Transformers"],"prefix":"10.1109","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9956-7020","authenticated-orcid":false,"given":"Haoran","family":"Duan","sequence":"first","affiliation":[{"name":"Department of Computer Science, Durham University, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Long","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Durham University, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1023-1286","authenticated-orcid":false,"given":"Shidong","family":"Wang","sequence":"additional","affiliation":[{"name":"School of engineering, Newcastle University, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4039-7618","authenticated-orcid":false,"given":"Haofeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing university of Science and Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6821-3924","authenticated-orcid":false,"given":"Chris G.","family":"Willcocks","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Durham University, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8264-6117","authenticated-orcid":false,"given":"Ling","family":"Shao","sequence":"additional","affiliation":[{"name":"Terminus Group, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Regionvit: Regional-to-local attention for vision transformers","author":"chen","year":"2022","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_33"},{"key":"ref12","article-title":"Shuffle transformer: Rethinking spatial shuffle for vision transformer","author":"huang","year":"2021"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.70"},{"key":"ref15","article-title":"Transformers in remote sensing: A survey","author":"aleissaee","year":"2022"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00845"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3505244"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00745"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref52","first-page":"173","article-title":"Object-contextual representations for semantic segmentation","author":"yuan","year":"2020","journal-title":"Proc 16th Eur Conf Comp Vis"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref55","article-title":"Cctrans: Simplifying and improving crowd counting with transformer","author":"tian","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00335"},{"key":"ref17","article-title":"Self-distilled vision transformer for domain generalization","author":"sultana","year":"2022"},{"key":"ref16","article-title":"3D vision with transformers: A survey","author":"lahoud","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00564"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00685"},{"key":"ref50","first-page":"801","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","author":"chen","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00045"},{"key":"ref48","first-page":"418","article-title":"Unified perceptual parsing for scene understanding","author":"xiao","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref42","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref44","first-page":"491","article-title":"Big transfer (bit): General visual representation learning","author":"kolesnikov","year":"2020","journal-title":"Proc 16th Eur Conf"},{"key":"ref43","first-page":"1997","article-title":"Neural architecture search: A survey","volume":"20","author":"elsken","year":"2019","journal-title":"J Mach Learn Res"},{"key":"ref49","article-title":"MMSegmentation: OpenMMLab semantic segmentation toolbox and benchmark","author":"contributors","year":"2020"},{"key":"ref8","article-title":"On the relationship between self-attention and convolutional layers","author":"cordonnier","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref7","first-page":"4055","article-title":"Image transformer","author":"parmar","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref9","first-page":"15908","article-title":"Transformer in transformer","volume":"34","author":"han","year":"2021","journal-title":"Adv in Neural Inf Process Syst"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref3","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020"},{"key":"ref6","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"raffel","year":"2020","journal-title":"J Mach Learn Res"},{"key":"ref5","first-page":"3965","article-title":"CoatNet: Marrying convolution and attention for all data sizes","author":"dai","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01563"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_21"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00648"},{"key":"ref35","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","author":"tan","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00063"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00844"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref36","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","author":"touvron","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref31","first-page":"4905","article-title":"Understanding the effective receptive field in deep convolutional neural networks","author":"luo","year":"2016","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00325"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240552"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00336"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6775"},{"key":"ref2","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref1","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref39","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref38","article-title":"Mobilevit: Light-weight, general-purpose, and mobile-friendly vision transformer","author":"mehta","year":"2022","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.133"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01474"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00380"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00016"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00338"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01526"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00201"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00356"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref69","article-title":"Boosting crowd counting with transformers","author":"sun","year":"2021"},{"key":"ref20","article-title":"Transvisdrone: Spatio-temporal transformer for vision-based drone-to-drone detection in aerial videos","author":"sangam","year":"2022"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_10"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00476"},{"key":"ref22","article-title":"LocalViT: Bringing locality to vision transformers","author":"li","year":"2021"},{"key":"ref66","first-page":"3386","article-title":"Modeling noisy annotations for crowd counting","author":"wan","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00062"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_15"},{"key":"ref28","first-page":"12116","article-title":"Do vision transformers see like convolutional neural networks?","author":"raghu","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3505244"},{"key":"ref29","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume":"25","author":"krizhevsky","year":"2012","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00186"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00443"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00624"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/4359286\/10004645.pdf?arnumber=10004645","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,4]],"date-time":"2023-10-04T15:12:29Z","timestamp":1696432349000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10004645\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":82,"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3233482","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":[[2023]]}}}