CASIA OpenIR  > 智能感知与计算研究中心
VFM: Visual Feedback Model for Robust Object Recognition
Wang, Chong; Huang, Kai-Qi
Source PublicationJOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY
2015-03-01
Volume30Issue:2Pages:325-339
SubtypeArticle
AbstractObject recognition, which consists of classification and detection, has two important attributes for robustness: 1) closeness: detection windows should be as close to object locations as possible, and 2) adaptiveness: object matching should be adaptive to object variations within an object class. It is difficult to satisfy both attributes using traditional methods which consider classification and detection separately; thus recent studies propose to combine them based on confidence contextualization and foreground modeling. However, these combinations neglect feature saliency and object structure, and biological evidence suggests that the feature saliency and object structure can be important in guiding the recognition from low level to high level. In fact, object recognition originates in the mechanism of "what" and "where" pathways in human visual systems. More importantly, these pathways have feedback to each other and exchange useful information, which may improve closeness and adaptiveness. Inspired by the visual feedback, we propose a robust object recognition framework by designing a computational visual feedback model (VFM) between classification and detection. In the "what" feedback, the feature saliency from classification is exploited to rectify detection windows for better closeness; while in the "where" feedback, object parts from detection are used to match object structure for better adaptiveness. Experimental results show that the "what" and "where" feedback is effective to improve closeness and adaptiveness for object recognition, and encouraging improvements are obtained on the challenging PASCAL VOC 2007 dataset.
KeywordObject Recognition Object Classification Object Detection Visual Feedback
WOS HeadingsScience & Technology ; Technology
WOS KeywordIMAGE CLASSIFICATION ; POSE ESTIMATION ; ATTENTION ; VISION ; LOCALIZATION ; ALTERNATIVES ; ENHANCEMENT ; HISTOGRAMS ; COMPONENTS ; NETWORKS
Indexed BySCI
Language英语
WOS Research AreaComputer Science
WOS SubjectComputer Science, Hardware & Architecture ; Computer Science, Software Engineering
WOS IDWOS:000351292400011
Citation statistics
Cited Times:4[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/8090
Collection智能感知与计算研究中心
AffiliationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Wang, Chong,Huang, Kai-Qi. VFM: Visual Feedback Model for Robust Object Recognition[J]. JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY,2015,30(2):325-339.
APA Wang, Chong,&Huang, Kai-Qi.(2015).VFM: Visual Feedback Model for Robust Object Recognition.JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY,30(2),325-339.
MLA Wang, Chong,et al."VFM: Visual Feedback Model for Robust Object Recognition".JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY 30.2(2015):325-339.
Files in This Item: Download All
File Name/Size DocType Version Access License
Chong Wang_VFM Visua(24239KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Wang, Chong]'s Articles
[Huang, Kai-Qi]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wang, Chong]'s Articles
[Huang, Kai-Qi]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wang, Chong]'s Articles
[Huang, Kai-Qi]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Chong Wang_VFM Visual Feedback Model for Robust Object 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.