CASIA OpenIR  > 模式识别国家重点实验室  > 图像与视频分析
What Visual Attributes Characterize an Object Class?
Jianlong Fu; Jinqiao Wang; Xin-Jing Wang; Yong Rui; Hanqing Lu
2014
Conference NameACCV2014
Source PublicationAsian Conference on Computer Vision (ACCV)
Pages243-259
Conference Date2014
Conference PlaceSingapore
AbstractVisual attribute-based learning has shown a big impact on many computer vision problems in recent years. Albeit its usefulness, most of works only focus on predicting either the presence or the strength of pre-defined attributes. In this paper, we discuss how to automatically learn visual attributes that characterize an object class. Starting from the images of an object class that are collected from the Web, we first mine visual prototypes of attributes (i.e., a clean intermediate representation for learning attributes) by clustering with Gaussian mixtures from multi-scale salient areas in noisy Web images. Second, a joint optimization model is proposed to fulfill the attribute learning with feature selection. As sparse approximation is adopted for feature selection during the joint optimization, the learned attributes tend to present a more representative visual property, e.g., stripe pattern (when texture features are selected), yellow-color (when color features are selected). Finally, to quantify the confidence of attributes and restrain the noisy attributes learned from the Web, a ranking-based method is proposed to refine the learned attributes. Our approach ensures the learned visual attributes to be visually recognizable and representative, in contrast to manually constructed attributes [1] that contain properties difficult to be visualized, e.g., “smelly,” “smart.” We evaluated our approach on two benchmark datasets, and compared with state-of-the-art approaches in two aspects: the quality of the learned visual attributes and their effectiveness in object categorization.
KeywordVisual Attributes Characterize
Indexed ByEI
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/4697
Collection模式识别国家重点实验室_图像与视频分析
Corresponding AuthorJinqiao Wang
Recommended Citation
GB/T 7714
Jianlong Fu,Jinqiao Wang,Xin-Jing Wang,et al. What Visual Attributes Characterize an Object Class?[C],2014:243-259.
Files in This Item: Download All
File Name/Size DocType Version Access License
What Visual Attribut(3432KB)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
[Jianlong Fu]'s Articles
[Jinqiao Wang]'s Articles
[Xin-Jing Wang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Jianlong Fu]'s Articles
[Jinqiao Wang]'s Articles
[Xin-Jing Wang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Jianlong Fu]'s Articles
[Jinqiao Wang]'s Articles
[Xin-Jing Wang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: What Visual Attributes Characterize an Object Class.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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