{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T15:49:25Z","timestamp":1776181765379,"version":"3.50.1"},"reference-count":94,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61836012"],"award-info":[{"award-number":["61836012"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62171431"],"award-info":[{"award-number":["62171431"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62225208"],"award-info":[{"award-number":["62225208"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Strategic Priority Research Program of Chinese Academy of Sciences","award":["XDA27000000"],"award-info":[{"award-number":["XDA27000000"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,8]]},"DOI":"10.1109\/tpami.2023.3243048","type":"journal-article","created":{"date-parts":[[2023,2,7]],"date-time":"2023-02-07T18:58:43Z","timestamp":1675796323000},"page":"9454-9468","source":"Crossref","is-referenced-by-count":159,"title":["Conformer: Local Features Coupling Global Representations for Recognition and Detection"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6643-9329","authenticated-orcid":false,"given":"Zhiliang","family":"Peng","sequence":"first","affiliation":[{"name":"School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences (UCAS), Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8492-2130","authenticated-orcid":false,"given":"Zonghao","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences (UCAS), Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8899-0069","authenticated-orcid":false,"given":"Wei","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences (UCAS), Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2197-9038","authenticated-orcid":false,"given":"Yaowei","family":"Wang","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, Guangdong Province, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4831-9451","authenticated-orcid":false,"given":"Lingxi","family":"Xie","sequence":"additional","affiliation":[{"name":"Huawei Cloud, Shenzhen, Guangdong Province, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0454-3929","authenticated-orcid":false,"given":"Jianbin","family":"Jiao","sequence":"additional","affiliation":[{"name":"School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences (UCAS), Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7252-5047","authenticated-orcid":false,"given":"Qi","family":"Tian","sequence":"additional","affiliation":[{"name":"Huawei Cloud, Shenzhen, Guangdong Province, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1215-6259","authenticated-orcid":false,"given":"Qixiang","family":"Ye","sequence":"additional","affiliation":[{"name":"School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences (UCAS), Beijing, China"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Pre-trained image processing transformer","author":"chen","year":"2020"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/0031-3203(91)90143-S"},{"key":"ref12","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref15","article-title":"Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers","author":"zheng","year":"2020"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.433"},{"key":"ref14","article-title":"Toward transformer-based object detection","author":"beal","year":"2020"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2002.1017623"},{"key":"ref53","article-title":"You only look at one sequence: Rethinking transformer in vision through object detection","author":"fang","year":"2021"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00360"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1126\/science.7134969"},{"key":"ref10","article-title":"Training data-efficient image transformers & distillation through attention","author":"touvron","year":"2020"},{"key":"ref54","first-page":"217","article-title":"Are complex visual features derived from simple ones","author":"pomerantz","year":"1978","journal-title":"Formal Theories of Visual Perception"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref16","article-title":"TransGAN: Two transformers can make one strong GAN","author":"jiang","year":"2021"},{"key":"ref19","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref18","article-title":"Layer normalization","author":"ba","year":"2016"},{"key":"ref93","first-page":"13564","article-title":"RelationNet++: Bridging visual representations for object detection via transformer decoder","author":"chi","year":"2020","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01283"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"ref50","article-title":"Anchor DETR: Query design for transformer-based detector","author":"wang","year":"2021"},{"key":"ref94","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref91","article-title":"Objects as points","author":"zhou","year":"2019"},{"key":"ref90","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref46","first-page":"30392","article-title":"Early convolutions help transformers see better","author":"xiao","year":"2021","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01204"},{"key":"ref89","article-title":"Rethinking transformer-based set prediction for object detection","author":"sun","year":"2020"},{"key":"ref48","first-page":"20014","article-title":"XCiT: Cross-covariance image transformers","author":"el-nouby","year":"2021","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref47","first-page":"3965","article-title":"CoatNet: Marrying convolution and attention for all data sizes","volume":"34","author":"dai","year":"2021","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00062"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00729"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00044"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_22"},{"key":"ref44","first-page":"2286","article-title":"ConViT: Improving vision transformers with soft convolutional inductive biases","author":"d\u2019ascoli","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref43","article-title":"Conditional positional encodings for vision transformers","author":"chu","year":"2021","journal-title":"arXiv 2102 10882"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"ref49","article-title":"ViDT: An efficient and effective fully transformer-based object detector","author":"song","year":"2021"},{"key":"ref8","article-title":"An image is worth 16 × 16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020"},{"key":"ref7","article-title":"Attention is all you need","author":"vaswani","year":"2017"},{"key":"ref9","article-title":"Visual transformers: Token-based image representation and processing for computer vision","author":"wu","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref82","first-page":"10 506","article-title":"Learning robust global representations by penalizing local predictive power","author":"wang","year":"2019","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref84","first-page":"936","article-title":"Feature pyramid networks for object detection","author":"lin","year":"2017","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref83","article-title":"The Caltech-UCSD birds-200–2011 dataset","author":"wah","year":"2011"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref35","article-title":"Language models are few-shot learners","author":"brown","year":"2020"},{"key":"ref79","first-page":"5389","article-title":"Do ImageNet classifiers generalize to ImageNet?","author":"recht","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref34","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018"},{"key":"ref78","article-title":"Rethinking localization map: Towards accurate object perception with self-enhancement maps","author":"zhang","year":"2020"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00288"},{"key":"ref36","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"zhu","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00338"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"ref77","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2017"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00378"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref2","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014"},{"key":"ref1","first-page":"1106","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref38","first-page":"1691","article-title":"Generative pretraining from pixels","author":"chen","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_30"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref24","article-title":"Gather-excite: Exploiting feature context in convolutional neural networks","author":"hu","year":"2018"},{"key":"ref68","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":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"ref67","article-title":"ResNet strikes back: An improved training procedure in timm","author":"wightman","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.75"},{"key":"ref25","article-title":"Multi-scale context aggregation by dilated convolutions","author":"yu","year":"2015"},{"key":"ref69","first-page":"10 096","article-title":"EfficientNetV2: Smaller models and faster training","author":"tan","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00042"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00288"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref65","article-title":"PyTorch image models","author":"wightman","year":"2019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref60","article-title":"Position, padding and predictions: A deeper look at position information in CNNs","author":"islam","year":"2021"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.385"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10169863\/10040235.pdf?arnumber=10040235","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,17]],"date-time":"2023-07-17T17:42:01Z","timestamp":1689615721000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10040235\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8]]},"references-count":94,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3243048","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":[[2023,8]]}}}