{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T17:24:27Z","timestamp":1792689867297,"version":"4.5.0"},"reference-count":72,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100010663","name":"European Research Council (ERC)","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010663","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,6]]},"DOI":"10.1109\/cvpr52688.2022.01420","type":"proceedings-article","created":{"date-parts":[[2022,9,27]],"date-time":"2022-09-27T15:56:41Z","timestamp":1664294201000},"page":"14585-14595","source":"Crossref","is-referenced-by-count":118,"title":["DETReg: Unsupervised Pretraining with Region Priors for Object Detection"],"prefix":"10.1109","author":[{"given":"Amir","family":"Bar","sequence":"first","affiliation":[{"name":"Tel-Aviv University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vadim","family":"Kantorov","sequence":"additional","affiliation":[{"name":"Tel-Aviv University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Colorado J","family":"Reed","sequence":"additional","affiliation":[{"name":"Berkeley AI Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roei","family":"Herzig","sequence":"additional","affiliation":[{"name":"Tel-Aviv University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gal","family":"Chechik","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anna","family":"Rohrbach","sequence":"additional","affiliation":[{"name":"Berkeley AI Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Trevor","family":"Darrell","sequence":"additional","affiliation":[{"name":"Berkeley AI Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amir","family":"Globerson","sequence":"additional","affiliation":[{"name":"Tel-Aviv University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref72","first-page":"3","article-title":"Edge boxes: Locating object proposals from edges","author":"zitnick","year":"2014","journal-title":"ECCV"},{"key":"ref71","first-page":"2, 3, 4","article-title":"Deformable DETR: Deformable trans-formers for end-to-end object detection","author":"zhu","year":"2020","journal-title":"Arxiv preprint arXiv"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_16"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00311"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.5244\/C.28.24"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2465908"},{"key":"ref31","first-page":"2","article-title":"Ef-ficient visual pretraining with contrastive detection","author":"h\u00e9naff","year":"2021","journal-title":"Arxiv preprint arXiv"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_47"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00534"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00851"},{"key":"ref34","first-page":"2, 7","article-title":"Consistency-based semi-supervised learning for object detection","author":"jeong","year":"0","journal-title":"NIPS"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413832"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01037"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref63","first-page":"192","article-title":"Few-shot object detection and viewpoint estimation for objects in the wild","author":"xiao","year":"0","journal-title":"European Conference on Computer Vision"},{"key":"ref28","first-page":"2, 5","article-title":"Momentum contrast for unsupervised visual repre-sentation learning","author":"he","year":"0","journal-title":"CVPR"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00828"},{"key":"ref27","first-page":"1, 2","article-title":"Momentum contrast for unsupervised visual repre-sentation learning","author":"he","year":"0","journal-title":"CVPR"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00305"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00967"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00502"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00398"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2016.2636090"},{"key":"ref69","first-page":"2","article-title":"Meta-detr: Few-shot object detection via unified image-level meta-learning","author":"zhang","year":"2021","journal-title":"Arxiv preprint arXiv"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540226"},{"key":"ref1","first-page":"2","year":"0","journal-title":"Airbus Ship Detection Challenge"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00450"},{"key":"ref22","first-page":"2","article-title":"Learning representations by pre-dicting bags of visual words","author":"gidaris","year":"0","journal-title":"CVPR"},{"key":"ref21","first-page":"8","article-title":"Imagenet-trained cnns are biased towards texture; increasing shape bias improves accuracy and robustness","author":"geirhos","year":"2018","journal-title":"Arxiv preprint arXiv"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref26","first-page":"1","article-title":"Bootstrap your own latent-a new approach to self-supervised learning","author":"grill","year":"2020","journal-title":"NeurIPS"},{"key":"ref25","first-page":"2","article-title":"Scaling and benchmarking self-supervised visual rep-resentation learning","author":"goyal","year":"0","journal-title":"ICCV"},{"key":"ref50","first-page":"4","article-title":"Generalized in-tersection over union: A metric and a loss for bounding box regression","author":"rezatofighi","year":"0","journal-title":"CVPR"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00120"},{"key":"ref59","first-page":"456","article-title":"Multi-scale positive sample refinement for few-shot object detection","author":"wu","year":"0","journal-title":"European Conference on Computer Vision"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01002"},{"key":"ref57","first-page":"12","article-title":"Dense contrastive learning for self-supervised visual pre-training","author":"wang","year":"2020","journal-title":"Arxiv preprint arXiv"},{"key":"ref56","first-page":"2, 6","article-title":"Frustratingly simple few-shot object detection","author":"wang","year":"2020","journal-title":"Arxiv preprint arXiv"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126456"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref53","first-page":"2, 7","article-title":"A simple semi-supervised learning framework for object detection","author":"sohn","year":"2020","journal-title":"Arxiv preprint arXiv"},{"key":"ref52","first-page":"8","article-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","author":"simonyan","year":"2013","journal-title":"Arxiv preprint arXiv"},{"key":"ref10","first-page":"2, 5","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"Arxiv preprint arXiv"},{"key":"ref11","first-page":"1","article-title":"Big self-supervised models are strong semi-supervised learners","author":"chen","year":"2020","journal-title":"NeurIPS"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref12","first-page":"2","article-title":"Should i look at the head or the tail? dual-awareness attention for few-shot object detection","author":"chen","year":"2021","journal-title":"Arxiv preprint arXiv"},{"key":"ref13","first-page":"2","article-title":"Im-proved baselines with momentum contrastive learning","author":"chen","year":"2020","journal-title":"Arxiv preprint arXiv"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2345401"},{"key":"ref15","first-page":"3286","article-title":"Bing: Binarized normed gradients for objectness esti-mation at 300fps","author":"cheng","year":"0","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00165"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.122"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00407"},{"key":"ref4","first-page":"3","article-title":"The OpenCV Library","author":"bradski","year":"2000","journal-title":"Dr Dobb's Journal of Software Tools"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.49"},{"key":"ref6","first-page":"1, 2, 4, 5","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","author":"caron","year":"2020","journal-title":"NeurIPS"},{"key":"ref5","first-page":"2, 3, 4, 5","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"ECCV"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.231"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11716"},{"key":"ref46","first-page":"1","article-title":"Addressing the exorbitant cost of labeling medical images with active learning","author":"rahimi","year":"2021","journal-title":"International Conference on Machine Learning in Medical Imaging and Analysis"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2964540"},{"key":"ref48","first-page":"2","article-title":"Self-supervised pretraining improves self-supervised pretraining","author":"reed","year":"2021","journal-title":"Arxiv preprint arXiv"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref42","first-page":"2, 7","article-title":"Unbiased teacher for semi-supervised object detection","author":"liu","year":"2021","journal-title":"Arxiv preprint arXiv"},{"key":"ref41","first-page":"2","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"ECCV"},{"key":"ref44","first-page":"5","article-title":"Rectified linear units improve restricted boltzmann machines","author":"nair","year":"0","journal-title":"ICML"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00674"}],"event":{"name":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","location":"New Orleans, LA, USA","start":{"date-parts":[[2022,6,18]]},"end":{"date-parts":[[2022,6,24]]}},"container-title":["2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9878378\/9878366\/09879947.pdf?arnumber=9879947","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,14]],"date-time":"2022-10-14T16:55:34Z","timestamp":1665766534000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9879947\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6]]},"references-count":72,"URL":"https:\/\/doi.org\/10.1109\/cvpr52688.2022.01420","relation":{},"subject":[],"published":{"date-parts":[[2022,6]]}}}