{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T15:15:25Z","timestamp":1778858125948,"version":"3.51.4"},"reference-count":68,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T00:00:00Z","timestamp":1622505600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T00:00:00Z","timestamp":1622505600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T00:00:00Z","timestamp":1622505600000},"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":[],"published-print":{"date-parts":[[2021,6]]},"DOI":"10.1109\/cvpr46437.2021.01625","type":"proceedings-article","created":{"date-parts":[[2021,11,2]],"date-time":"2021-11-02T21:56:02Z","timestamp":1635890162000},"page":"16514-16524","source":"Crossref","is-referenced-by-count":1072,"title":["Bottleneck Transformers for Visual Recognition"],"prefix":"10.1109","author":[{"given":"Aravind","family":"Srinivas","sequence":"first","affiliation":[]},{"given":"Tsung-Yi","family":"Lin","sequence":"additional","affiliation":[]},{"given":"Niki","family":"Parmar","sequence":"additional","affiliation":[]},{"given":"Jonathon","family":"Shlens","sequence":"additional","affiliation":[]},{"given":"Pieter","family":"Abbeel","sequence":"additional","affiliation":[]},{"given":"Ashish","family":"Vaswani","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref38","article-title":"Compounding the performance improvements of assembled techniques in a convolutional neural network","author":"lee","year":"2020","journal-title":"arXiv preprint arXiv 2001 04786"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00356"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00378"},{"key":"ref31","article-title":"Axial attention in multidimensional transformers","author":"ho","year":"2019"},{"key":"ref30","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015"},{"key":"ref37","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"NeurIPS"},{"key":"ref36","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref35","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"arXiv preprint arXiv 1502 03167"},{"key":"ref34","first-page":"603","article-title":"Ccnet: Criss-cross attention for semantic segmentation","author":"huang","year":"2019","journal-title":"Proceedings of the IEEE International Conference on Computer Vision"},{"key":"ref60","author":"touvron","year":"2021","journal-title":"Training data-efficient image transformers & distillation through attention"},{"key":"ref62","article-title":"Axial-deeplab: Standalone axial-attention for panoptic segmentation","author":"wang","year":"2020","journal-title":"arXiv preprint arXiv 2003 07516"},{"key":"ref61","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref64","first-page":"3","article-title":"Group normalization","author":"wu","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00059"},{"key":"ref29","article-title":"Data-efficient image recognition with contrastive predictive coding","author":"h\u00e9naff","year":"2019","journal-title":"arXiv preprint arXiv 1905 09010"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref67","author":"zhang","year":"2020","journal-title":"Resnest Splitattention networks"},{"key":"ref68","author":"zhao","year":"2020","journal-title":"Exploring self-attention for image recognition"},{"key":"ref2","article-title":"Lambdanetworks: Modeling long-range interactions without attention","author":"bello","year":"2021","journal-title":"International Conference on Learning Representations"},{"key":"ref1","article-title":"Layer normalization","author":"ba","year":"2016"},{"key":"ref20","first-page":"1440","article-title":"Fast r-cnn","author":"girshick","year":"2015","journal-title":"Proceedings of the IEEE International Conference on Computer Vision"},{"key":"ref22","author":"girshick","year":"2018","journal-title":"Detectron"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref24","article-title":"Bootstrap your own latent: A new approach to self-supervised learning","author":"grill","year":"2020","journal-title":"arXiv preprint arXiv 2006 04989"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00988"},{"key":"ref26","author":"he","year":"2019","journal-title":"Momentum contrast for unsupervised visual representation learning"},{"key":"ref25","first-page":"297","article-title":"Simultaneous detection and segmentation","author":"hariharan","year":"2014","journal-title":"European Conference on Computer Vision"},{"key":"ref50","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"NeurIPS"},{"key":"ref51","first-page":"1400","article-title":"Tresnet: High performance gpu-dedicated architecture","author":"ridnik","year":"2021","journal-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision"},{"key":"ref59","article-title":"Contrastive multiview coding","author":"tian","year":"2019","journal-title":"arXiv preprint arXiv 1906 03008"},{"key":"ref58","article-title":"Efficient transformers: A survey","author":"tay","year":"2020","journal-title":"arXiv preprint arXiv 2009 02026"},{"key":"ref57","article-title":"Efficientdet: Scalable and efficient object detection","author":"tan","year":"2019"},{"key":"ref56","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"tan","year":"2019"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref54","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv preprint arXiv 1409 1556"},{"key":"ref53","article-title":"Selfattention with relative position representations","author":"shaw","year":"2018","journal-title":"arXiv preprint arXiv 1803 02155"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref10","article-title":"Endto-end object detection with transformers","author":"carion","year":"2020","journal-title":"arXiv preprint arXiv 2005 10545"},{"key":"ref40","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"European Conference on Computer Vision"},{"key":"ref11","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020"},{"key":"ref12","article-title":"Exploring simple siamese representation learning","author":"chen","year":"2020"},{"key":"ref13","first-page":"3150","article-title":"Instance-aware semantic segmentation via multi-task network cascades","author":"dai","year":"2016","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref14","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"arXiv preprint arXiv 1810 04805"},{"key":"ref15","author":"dosovitskiy","year":"2020","journal-title":"An image is worth 16x16 words Transformers for image recognition at scale"},{"key":"ref16","article-title":"Spinenet: Learning scale-permuted backbone for recognition and localization","author":"du","year":"2019"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref18","author":"ghiasi","year":"2020","journal-title":"Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00720"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00338"},{"key":"ref3","author":"bello","year":"2021","journal-title":"Revisiting ResNets Improved Training and Scaling Strategies"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.38"},{"key":"ref5","article-title":"Language models are few-shot learners","author":"brown","year":"2020","journal-title":"arXiv preprint arXiv 2005 14354"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref49","article-title":"Standalone self-attention in vision models","author":"ramachandran","year":"2019"},{"key":"ref9","first-page":"7291","article-title":"Realtime multi-person 2d pose estimation using part affinity fields","author":"cao","year":"2017","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref46","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"radford","year":"2019","journal-title":"OpenAIRE blog"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00647"},{"key":"ref48","first-page":"10428","article-title":"Designing network design spaces","author":"radosavovic","year":"2020","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00197"},{"key":"ref42","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"liu","year":"2019","journal-title":"arXiv preprint arXiv 1907 11634"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00913"},{"key":"ref44","first-page":"13","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"lu","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref43","article-title":"Cbnet: A novel composite backbone network architecture for object detection","author":"liu","year":"2019","journal-title":"arXiv preprint arXiv 1909 02107"}],"event":{"name":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","location":"Nashville, TN, USA","start":{"date-parts":[[2021,6,20]]},"end":{"date-parts":[[2021,6,25]]}},"container-title":["2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9577055\/9577056\/09577771.pdf?arnumber=9577771","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:47:47Z","timestamp":1652197667000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9577771\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/cvpr46437.2021.01625","relation":{},"subject":[],"published":{"date-parts":[[2021,6]]}}}