{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T05:23:44Z","timestamp":1769923424066,"version":"3.49.0"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2020,2,1]],"date-time":"2020-02-01T00:00:00Z","timestamp":1580515200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/OAPA.html"}],"funder":[{"name":"NSF China","award":["61622204"],"award-info":[{"award-number":["61622204"]}]},{"name":"NSF China","award":["61572134"],"award-info":[{"award-number":["61572134"]}]},{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["16JC1420400"],"award-info":[{"award-number":["16JC1420400"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Municipal Science and Technology Major","award":["2017SHZDZX01"],"award-info":[{"award-number":["2017SHZDZX01"]}]},{"name":"Shanghai Municipal Science and Technology Major","award":["2018SHZDZX01"],"award-info":[{"award-number":["2018SHZDZX01"]}]},{"name":"ZJLab"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2020,2,1]]},"DOI":"10.1109\/tpami.2019.2922181","type":"journal-article","created":{"date-parts":[[2019,6,11]],"date-time":"2019-06-11T19:56:17Z","timestamp":1560282977000},"page":"398-412","source":"Crossref","is-referenced-by-count":80,"title":["Object Detection from Scratch with Deep Supervision"],"prefix":"10.1109","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4560-5092","authenticated-orcid":false,"given":"Zhiqiang","family":"Shen","sequence":"first","affiliation":[]},{"given":"Zhuang","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Jianguo","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1907-8567","authenticated-orcid":false,"given":"Yu-Gang","family":"Jiang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9333-1746","authenticated-orcid":false,"given":"Yurong","family":"Chen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4897-9209","authenticated-orcid":false,"given":"Xiangyang","family":"Xue","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"ref72","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","author":"han","year":"2016","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref71","article-title":"OpenImages: A public dataset for large-scale multi-label and multi-class image classification","author":"krasin","year":"2016"},{"key":"ref70","first-page":"340","article-title":"Diagnosing error in object detectors","author":"hoiem","year":"2012","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref74","article-title":"Rethinking ImageNet pre-training","author":"he","year":"2018"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref75","article-title":"Differentiable learning-to-normalize via switchable normalization","author":"luo","year":"0","journal-title":"Int Conf Learn Representations"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.164"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.548"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref30","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref37","first-page":"562","article-title":"Deeply-supervised nets","author":"lee","year":"2015","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.309"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.494"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.156"},{"key":"ref62","first-page":"3","article-title":"Group normalization","author":"wu","year":"0","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00647"},{"key":"ref63","article-title":"DeepID3: Face recognition with very deep neural networks","author":"sun","year":"2015"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.276"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.170"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref66","article-title":"ParseNet: Looking wider to see better","author":"liu","year":"0","journal-title":"ICLR Workshop"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299194"},{"key":"ref67","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref68","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref69","first-page":"630","article-title":"Identity mappings in deep residual networks","author":"he","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref20","first-page":"798","article-title":"Deep regionlets for object detection","author":"xu","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref21","first-page":"1963","article-title":"Pelee: A real-time object detection system on mobile devices","author":"wang","year":"2018","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref24","article-title":"Semantic image segmentation with deep convolutional nets and fully connected crfs","author":"chen","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298642"},{"key":"ref26","first-page":"834","article-title":"Part-based R-CNNs for fine-grained category detection","author":"zhang","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref25","article-title":"Multi-scale context aggregation by dilated convolutions","author":"yu","year":"2016","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref50","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref59","article-title":"Inception-v4, Inception-ResNet and the impact of residual connections on learning","author":"szegedy","year":"2016","journal-title":"Proc Workshop Int Conf Learn Represent"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.351"},{"key":"ref57","article-title":"PVANET: Deep but lightweight neural networks for real-time object detection","author":"kim","year":"2016"},{"key":"ref56","article-title":"YOLOv3: An incremental improvement","author":"redmon","year":"2018"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref54","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"0","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref53","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.212"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.98"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.314"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.557"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00647"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00377"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00378"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref19","article-title":"STDnet: A convnet for small target detection","author":"bosquet","year":"2018","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.222"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref8","first-page":"379","article-title":"R-FCN: Object detection via region-based fully convolutional networks","author":"li","year":"2016","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref7","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":"ref49","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref9","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref46","first-page":"385","article-title":"Receptive field block net for accurate and fast object detection","author":"liu","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00442"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00094"},{"key":"ref47","first-page":"734","article-title":"CornerNet: Detecting objects as paired keypoints","author":"law","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref42","article-title":"Tiny-DSOD: Lightweight object detection for resource-restricted usages","author":"li","year":"0","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref41","article-title":"Learning object detectors from scratch with gated recurrent feature pyramids","author":"shen","year":"2017"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00062"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/8952810\/08734700.pdf?arnumber=8734700","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:58:36Z","timestamp":1639771116000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8734700\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,2,1]]},"references-count":76,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2019.2922181","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":[[2020,2,1]]}}}