{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T07:19:14Z","timestamp":1757575154166,"version":"3.28.0"},"reference-count":51,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,8]]},"DOI":"10.1109\/icinfa.2018.8812318","type":"proceedings-article","created":{"date-parts":[[2019,8,27]],"date-time":"2019-08-27T00:19:17Z","timestamp":1566865157000},"page":"427-432","source":"Crossref","is-referenced-by-count":5,"title":["Deep Learning for Object Detection and Grasping: A Survey"],"prefix":"10.1109","author":[{"given":"Qun","family":"Jia","sequence":"first","affiliation":[]},{"given":"Jun","family":"Cai","sequence":"additional","affiliation":[]},{"given":"Zhiqiang","family":"Cao","sequence":"additional","affiliation":[]},{"given":"Yelan","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Xionglei","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Junzhi","family":"Yu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2004.1371616"},{"year":"0","key":"ref38"},{"key":"ref33","first-page":"1817","article-title":"A Large-Scale Hierarchical MultiView RGB-D Object Dataset","author":"lai","year":"2016","journal-title":"IEEE International Conference on Robotics and Automation"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref31","first-page":"740","article-title":"Microsoft COCO: common objects in context","author":"lin","year":"0","journal-title":"IEEE European Conference on Computer Vision"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref37","article-title":"Automated Construction of Robotic Manipulation Programs","author":"diankov","year":"2010","journal-title":"PhD thesis"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.2478\/s13230-012-0020-5"},{"key":"ref35","first-page":"1710","article-title":"The columbia grasp database","author":"goldfeder","year":"2008","journal-title":"IEEE International Conference on Robotics and Automation"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980145"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.1561\/9781601982957","author":"bengio","year":"2009","journal-title":"Learning Deep Architectures for AI Foundations and Trends in Machine Learning"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.557"},{"journal-title":"ImageNet Large Scale Visual Recognition Competition 2012 (ILSVRC2012)","year":"0","author":"deng","key":"ref29"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1986.4767851"},{"key":"ref1","first-page":"1289","article-title":"Advances and Perspectives on Application of Deep Learning in Visual Object Detection","volume":"43","author":"zhang","year":"2017","journal-title":"Acta Automatic Sinica"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.314"},{"article-title":"You only look once: Unified, real-time object detection","year":"2015","author":"redmon","key":"ref22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.98"},{"key":"ref24","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"0"},{"journal-title":"YOLO9000 Better Faster Stronger","year":"2016","author":"redmon","key":"ref23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.212"},{"article-title":"DSSD: Deconvolutional single shot detector","year":"2016","author":"fu","key":"ref25"},{"article-title":"Multi-view Self-supervised Deep Learning for 6D Pose Estimation in the Amazon Picking Challenge","year":"2016","author":"zeng","key":"ref50"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206470"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2389824"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6224697"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238663"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref15","first-page":"379","article-title":"R-FCN: object detection via region-based fully convolutional networks","author":"dai","year":"2016","journal-title":"International Conference on Neural Information Processing Systems"},{"article-title":"Light-Head R-CNN: In Defense of Two-Stage Object Detector","year":"2017","author":"li","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.324"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2011.07.016"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2006.479"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/34.121791"},{"key":"ref9","first-page":"580","article-title":"Rich feature hierarchies for accurate object detection and semantic segmentation","author":"girshick","year":"2014","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition"},{"article-title":"Real-Time Grasp Detection Using Convolutional Neural Networks","year":"2014","author":"redmon","key":"ref46"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1177\/0278364914549607"},{"article-title":"Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection","year":"2016","author":"levine","key":"ref48"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759657"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487517"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2010.06.001"},{"key":"ref44","first-page":"2038","article-title":"Object Discovery and Grasp Detection with a Shared Convolutional Neural Network","author":"guo","year":"2016","journal-title":"IEEE International Conference on Robotics and Automation"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980145"}],"event":{"name":"2018 IEEE International Conference on Information and Automation (ICIA)","start":{"date-parts":[[2018,8,11]]},"location":"Wuyishan, China","end":{"date-parts":[[2018,8,13]]}},"container-title":["2018 IEEE International Conference on Information and Automation (ICIA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8796847\/8812311\/08812318.pdf?arnumber=8812318","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,1,17]],"date-time":"2021-01-17T12:17:44Z","timestamp":1610885864000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8812318\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,8]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/icinfa.2018.8812318","relation":{},"subject":[],"published":{"date-parts":[[2018,8]]}}}