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
Conference Name3rd IAPR Asian Conference on Pattern Recognition
Source PublicationProceeding of 3rd IAPR Asian Conference on Pattern Recognition
Pages51-55
Conference Date2015.11.03-2015.11.06
Conference PlaceKuala Lumpur, Malaysia
AbstractThere 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.
KeywordNon-maximum
Indexed ByEI
Language英语
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/11650
Collection智能感知与计算研究中心
Corresponding AuthorKaiqi Huang
Affiliation中国科学院自动化研究所
Recommended Citation
GB/T 7714
Fu LR,Junge Zhang,Kaiqi Huang. Mirrored Non-Maximum Suppression for Accurate Object Part Localization[C],2015:51-55.
Files in This Item: Download All
File Name/Size DocType Version Access License
[ACPR15_Fu]Mirrored (3090KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Fu LR(付连锐)]'s Articles
[Junge Zhang]'s Articles
[Kaiqi Huang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Fu LR(付连锐)]'s Articles
[Junge Zhang]'s Articles
[Kaiqi Huang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Fu LR(付连锐)]'s Articles
[Junge Zhang]'s Articles
[Kaiqi Huang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: [ACPR15_Fu]Mirrored Non-Maximum Suppression for Accurate Object Part Localization.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.