CASIA OpenIR  > 智能感知与计算研究中心
Mirrored Non-Maximum Suppression for Accurate Object Part Localization
Fu LR(付连锐); Junge Zhang; Kaiqi Huang
2015-11
会议名称3rd IAPR Asian Conference on Pattern Recognition
会议录名称Proceeding of 3rd IAPR Asian Conference on Pattern Recognition
页码51-55
会议日期2015.11.03-2015.11.06
会议地点Kuala Lumpur, Malaysia
摘要There has been significant progress in object part localization such as human pose estimation and facial landmark detection. In most of the previous methods, two phenomena are ignored. Firstly, they usually output a set of candidate pose hypotheses but the hypothesis with the highest score obtained by Non-Maximum Suppression (NMS) is not always the optimal result. Secondly, they can not get exactly bilaterally symmetric keypoints on the mirrored images even though the training data is always augmented with mirrored images. In fact, the intrinsic relationship between the original image and the mirrored one is helpful for object part localization. In this paper, we propose Mirrored Non-Maximum Suppression (Mirrored NMS) which can utilize mirrored detections to improve the accuracy of object part localization. Experimental results show that our method can improve the state-of-the-art accuracy by 1.3∼3.0% in PCP for human pose estimation and can produce more accurate results than averaging multiple hypotheses for facial landmark detection.
关键词Non-maximum
收录类别EI
语种英语
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/11650
专题智能感知与计算研究中心
通讯作者Kaiqi Huang
作者单位中国科学院自动化研究所
推荐引用方式
GB/T 7714
Fu LR,Junge Zhang,Kaiqi Huang. Mirrored Non-Maximum Suppression for Accurate Object Part Localization[C],2015:51-55.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
[ACPR15_Fu]Mirrored (3090KB)会议论文 开放获取CC BY-NC-SA浏览 请求全文
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Fu LR(付连锐)]的文章
[Junge Zhang]的文章
[Kaiqi Huang]的文章
百度学术
百度学术中相似的文章
[Fu LR(付连锐)]的文章
[Junge Zhang]的文章
[Kaiqi Huang]的文章
必应学术
必应学术中相似的文章
[Fu LR(付连锐)]的文章
[Junge Zhang]的文章
[Kaiqi Huang]的文章
相关权益政策
暂无数据
收藏/分享
文件名: [ACPR15_Fu]Mirrored Non-Maximum Suppression for Accurate Object Part Localization.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。