{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T21:57:55Z","timestamp":1773093475196,"version":"3.50.1"},"reference-count":38,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,6]]},"DOI":"10.1109\/cvpr.2016.91","type":"proceedings-article","created":{"date-parts":[[2016,12,13]],"date-time":"2016-12-13T01:38:49Z","timestamp":1481593129000},"page":"779-788","source":"Crossref","is-referenced-by-count":36939,"title":["You Only Look Once: Unified, Real-Time Object Detection"],"prefix":"10.1109","author":[{"given":"Joseph","family":"Redmon","sequence":"first","affiliation":[]},{"given":"Santosh","family":"Divvala","sequence":"additional","affiliation":[]},{"given":"Ross","family":"Girshick","sequence":"additional","affiliation":[]},{"given":"Ali","family":"Farhadi","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref38","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1007\/978-3-319-10602-1_26","article-title":"Edge boxes: Locating object proposals from edges","author":"zitnick","year":"2014","journal-title":"Computer Vision—ECCV 2014"},{"key":"ref33","author":"szegedy","year":"2014","journal-title":"Going Deeper with Convolutions"},{"key":"ref32","author":"shen","year":"2014","journal-title":"Do more dropouts in poo15 feature maps for better object detection"},{"key":"ref31","author":"sermanet","year":"2013","journal-title":"Overfeat Integrated Recognition Localization and Detection Using Convolutional Networks"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1007\/978-3-319-10590-1_5","article-title":"30hz object detection with dpm v5","author":"sadeghi","year":"2014","journal-title":"Computer Vision-ECCV 2014"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.320"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000013087.49260.fb"},{"key":"ref35","first-page":"34","article-title":"Robust real-time object detection","volume":"4","author":"viola","year":"2001","journal-title":"International Journal of Computer Vision"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.135"},{"key":"ref12","first-page":"101","article-title":"Detecting people in cubist art","author":"ginosar","year":"2014","journal-title":"Computer Vision-ECCV 2014 Workshops"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref15","first-page":"655","article-title":"Region-based segmentation and object detection","author":"gould","year":"2009","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1007\/978-3-319-10584-0_20","article-title":"Simultaneous detection and segmentation","author":"hariharan","year":"2014","journal-title":"Computer Vision—ECCV 2014"},{"key":"ref17","author":"he","year":"2014","journal-title":"Spatial pyramid pooling in deep convolutional networks for visual recognition"},{"key":"ref18","author":"hinton","year":"2012","journal-title":"Improving Neural Networks by Preventing Co-adaptation of Feature Detectors"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"340","DOI":"10.1007\/978-3-642-33712-3_25","article-title":"Diagnosing error in object detectors","author":"hoiem","year":"2012","journal-title":"Computer Vision-ECCV 2012"},{"key":"ref28","author":"ren","year":"2015","journal-title":"Object detection networks on convolutional feature maps"},{"key":"ref4","first-page":"886","article-title":"Histograms of oriented gradients for human detection","volume":"1","author":"dalal","year":"2005","journal-title":"Computer Vision and Pattern Recognition 2005 CVPR 2005 IEEE Computer Society Conference on"},{"key":"ref27","author":"ren","year":"2015","journal-title":"Faster r-cnn Towards real-time object detection with region proposal networks"},{"key":"ref3","author":"cai","year":"2015","journal-title":"The cross-depiction problem Computer vision algorithms for recognising objects in artwork and in photographs"},{"key":"ref6","author":"donahue","year":"2013","journal-title":"Decaf A Deep Convolutional Activation Feature for Generic Visual Recognition"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.237"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.276"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1007\/978-3-319-10602-1_20","article-title":"Towards unified object detection and semantic segmentation","author":"dong","year":"2014","journal-title":"Computer Vision—ECCV 2014"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459303"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1007\/978-3-540-88682-2_2","article-title":"Learning to localize objects with structured output regression","author":"blaschko","year":"2008","journal-title":"Computer Vision–ECCV 2008"},{"key":"ref20","author":"lenc","year":"2015","journal-title":"R-cnn minus r"},{"key":"ref22","author":"lin","year":"2013","journal-title":"Network in Network"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2002.1038171"},{"key":"ref24","author":"mishkin","year":"0","journal-title":"Models accuracy on imagenet 2012 val"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"1150","DOI":"10.1109\/ICCV.1999.790410","article-title":"Object recognition from local scale-invariant features","volume":"2","author":"lowe","year":"1999","journal-title":"Computer Vision 1999 The Proceedings of the Seventh IEEE International Conference on"},{"key":"ref26","author":"redmon","year":"2014","journal-title":"Real-time grasp detection using convolutional neural networks"},{"key":"ref25","first-page":"555","article-title":"A general framework for object detection","author":"papageorgiou","year":"1998","journal-title":"Computer Vision 1998 Sixth International Conference on"}],"event":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","location":"Las Vegas, NV, USA","start":{"date-parts":[[2016,6,27]]},"end":{"date-parts":[[2016,6,30]]}},"container-title":["2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7776647\/7780329\/07780460.pdf?arnumber=7780460","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,16]],"date-time":"2019-09-16T12:54:12Z","timestamp":1568638452000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7780460\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,6]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/cvpr.2016.91","relation":{},"subject":[],"published":{"date-parts":[[2016,6]]}}}