Robust Relative Attributes for Human Action Recognition
Zhang,zhong; Wang,Chunheng; Xiao,Baihua; Zhou,Wen; Liu,Shuang
Source PublicationPattern Analysis and Applications (PAA)
Abstract High-level semantic feature is important to recognize human action. Recently, relative attributes, which are used to describe relative relationship, have been proposed as one of high-level semantic features and have shown promising performance. However, the training process is very sensitive to noises and moreover it is not robust to zero-shot learning. In this paper, to overcome these drawbacks, we propose a robust learning framework using relative attributes for human action recognition. We simultaneously add Sigmoid and Gaussian envelops into the loss objective. In this way, the influence of outliers will be greatly reduced in the process of optimization, thus improving the accuracy. In addition, we adopt Gaussian Mixture models for better fitting the distribution of actions in rank score space. Correspondingly, a novel transfer strategy is proposed to evaluate the parameters of Gaussian Mixture models for unseen classes. Our method is verified on three challenging datasets (KTH, UIUC and HOLLYWOOD2), and the experimental results demonstrate that our method achieves better results than previous methods
in both zero-shot classification and traditional recognition task for human action recognition.
KeywordRelative Attributes Envelop Loss Zero-shot Learning Human Action Recognition
Document Type期刊论文
AffiliationChinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
First Author AffilicationChinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Zhang,zhong,Wang,Chunheng,Xiao,Baihua,et al. Robust Relative Attributes for Human Action Recognition[J]. Pattern Analysis and Applications (PAA),2015(2015):157-171.
APA Zhang,zhong,Wang,Chunheng,Xiao,Baihua,Zhou,Wen,&Liu,Shuang.(2015).Robust Relative Attributes for Human Action Recognition.Pattern Analysis and Applications (PAA)(2015),157-171.
MLA Zhang,zhong,et al."Robust Relative Attributes for Human Action Recognition".Pattern Analysis and Applications (PAA) .2015(2015):157-171.
Files in This Item: Download All
File Name/Size DocType Version Access License
Robust Relative Attr(1116KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhang,zhong]'s Articles
[Wang,Chunheng]'s Articles
[Xiao,Baihua]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhang,zhong]'s Articles
[Wang,Chunheng]'s Articles
[Xiao,Baihua]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhang,zhong]'s Articles
[Wang,Chunheng]'s Articles
[Xiao,Baihua]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Robust Relative Attributes for Human Action Recognition.pdf
Format: Adobe PDF
All comments (0)
No comment.

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