A discriminative graph inferring framework towards weakly supervised image parsing

doi:10.1007/s00530-015-0458-5

	A discriminative graph inferring framework towards weakly supervised image parsing
	Yu, Lei; Bao, Bing-Kun; Xu, Changsheng
发表期刊	MULTIMEDIA SYSTEMS
	2017-02-01
卷号	23 期号:1 页码:5-18
文章类型	Article
摘要	In this paper, we focus on the task of assigning labels to the over-segmented image patches in a weakly supervised manner, in which the training images contain the labels but do not have the labels' locations in the images. We propose a unified discriminative graph inferring framework by simultaneously inferring patch labels and learning the patch appearance models. On one hand, graph inferring reasons the patch labels by a graph propagation procedure. The graph is constructed by connecting the nearest neighbors which share the same image label, and multiple correlations among patches and image labels are imposed as constraints to the inferring. On the other hand, for each label, the patches which do not contain the target label are adopted as negative samples to learn the appearance model. In this way, the predicted labels will be more accurate in the propagation. Graph inferring and the learned patch appearance models are finally embedded to complement each other in one unified formulation. Experiments on three public datasets demonstrate the effectiveness of our method in comparison with other baselines.
关键词	Image Annotation Appearance Model Label Propagation Label Localization Image Parsing
WOS标题词	Science & Technology ; Technology
DOI	10.1007/s00530-015-0458-5
关键词[WOS]	TAG LOCALIZATION ; RECOGNITION ; ANNOTATION ; FEATURES ; DATABASE ; OBJECT
收录类别	SCI
语种	英语
项目资助者	973 Program(2012CB316304) ; National Natural Science Foundation of China(61201374 ; Beijing Natural Science Foundation(4131004 ; 61225009 ; 4152053) ; 61432019)
WOS研究方向	Computer Science
WOS类目	Computer Science, Information Systems ; Computer Science, Theory & Methods
WOS记录号	WOS:000393759100002
引用统计	被引频次：1[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/11170
专题	多模态人工智能系统全国重点实验室_多媒体计算
作者单位	Chinese Acad Sci, Inst Automat, 95 Zhongguancun East Rd, Beijing 100190, Peoples R China
第一作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Yu, Lei,Bao, Bing-Kun,Xu, Changsheng. A discriminative graph inferring framework towards weakly supervised image parsing[J]. MULTIMEDIA SYSTEMS,2017,23(1):5-18.
APA	Yu, Lei,Bao, Bing-Kun,&Xu, Changsheng.(2017).A discriminative graph inferring framework towards weakly supervised image parsing.MULTIMEDIA SYSTEMS,23(1),5-18.
MLA	Yu, Lei,et al."A discriminative graph inferring framework towards weakly supervised image parsing".MULTIMEDIA SYSTEMS 23.1(2017):5-18.

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
A discriminative gra（2793KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载