面向对象识别的零件模型学习集合

Ian Endres, Kevin J. Shih, Johnston Jiaa, Derek Hoiem
{"title":"面向对象识别的零件模型学习集合","authors":"Ian Endres, Kevin J. Shih, Johnston Jiaa, Derek Hoiem","doi":"10.1109/CVPR.2013.126","DOIUrl":null,"url":null,"abstract":"We propose a method to learn a diverse collection of discriminative parts from object bounding box annotations. Part detectors can be trained and applied individually, which simplifies learning and extension to new features or categories. We apply the parts to object category detection, pooling part detections within bottom-up proposed regions and using a boosted classifier with proposed sigmoid weak learners for scoring. On PASCAL VOC 2010, we evaluate the part detectors' ability to discriminate and localize annotated key points. Our detection system is competitive with the best-existing systems, outperforming other HOG-based detectors on the more deformable categories.","PeriodicalId":6343,"journal":{"name":"2013 IEEE Conference on Computer Vision and Pattern Recognition","volume":"74 1","pages":"939-946"},"PeriodicalIF":0.0000,"publicationDate":"2013-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"80","resultStr":"{\"title\":\"Learning Collections of Part Models for Object Recognition\",\"authors\":\"Ian Endres, Kevin J. Shih, Johnston Jiaa, Derek Hoiem\",\"doi\":\"10.1109/CVPR.2013.126\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We propose a method to learn a diverse collection of discriminative parts from object bounding box annotations. Part detectors can be trained and applied individually, which simplifies learning and extension to new features or categories. We apply the parts to object category detection, pooling part detections within bottom-up proposed regions and using a boosted classifier with proposed sigmoid weak learners for scoring. On PASCAL VOC 2010, we evaluate the part detectors' ability to discriminate and localize annotated key points. Our detection system is competitive with the best-existing systems, outperforming other HOG-based detectors on the more deformable categories.\",\"PeriodicalId\":6343,\"journal\":{\"name\":\"2013 IEEE Conference on Computer Vision and Pattern Recognition\",\"volume\":\"74 1\",\"pages\":\"939-946\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2013-06-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"80\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2013 IEEE Conference on Computer Vision and Pattern Recognition\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CVPR.2013.126\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2013 IEEE Conference on Computer Vision and Pattern Recognition","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CVPR.2013.126","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 80

摘要

我们提出了一种从对象边界框注释中学习不同区分部分集合的方法。零件检测器可以单独训练和应用,这简化了学习和扩展到新的特征或类别。我们将零件应用于对象类别检测,在自下而上的建议区域内池化零件检测,并使用具有建议的s型弱学习器的增强分类器进行评分。在PASCAL VOC 2010上,我们评估了部件检测器区分和定位标注关键点的能力。我们的检测系统与现有最好的系统相比具有竞争力,在更可变形的类别上优于其他基于hog的探测器。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Learning Collections of Part Models for Object Recognition
We propose a method to learn a diverse collection of discriminative parts from object bounding box annotations. Part detectors can be trained and applied individually, which simplifies learning and extension to new features or categories. We apply the parts to object category detection, pooling part detections within bottom-up proposed regions and using a boosted classifier with proposed sigmoid weak learners for scoring. On PASCAL VOC 2010, we evaluate the part detectors' ability to discriminate and localize annotated key points. Our detection system is competitive with the best-existing systems, outperforming other HOG-based detectors on the more deformable categories.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Segment-Tree Based Cost Aggregation for Stereo Matching Event Retrieval in Large Video Collections with Circulant Temporal Encoding Articulated and Restricted Motion Subspaces and Their Signatures Subspace Interpolation via Dictionary Learning for Unsupervised Domain Adaptation Learning Video Saliency from Human Gaze Using Candidate Selection
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1