Unifying Visual Attribute Learning with Object Recognition in a Multiplicative Framework

doi:10.1109/TPAMI.2018.2836461

CORC > 计算技术研究所 > 中国科学院计算技术研究所 > 中国科学院计算技术研究所期刊论文 > 英文

	Unifying Visual Attribute Learning with Object Recognition in a Multiplicative Framework
	Shan, Shiguang 1,2,3; Liang, Kongming 2,3; Chang, Hong 2,3; Ma, Bingpeng 2,3; Chen, Xilin 2,3
刊名	IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
	2019-07-01
卷号	41 期号:7 页码:1747-1760
关键词	Attribute learning zero-shot learning image understanding
ISSN号	0162-8828
DOI	10.1109/TPAMI.2018.2836461
英文摘要	Attributes are mid-level semantic properties of objects. Recent research has shown that visual attributes can benefit many typical learning problems in computer vision community. However, attribute learning is still a challenging problem as the attributes may not always be predictable directly from input images and the variation of visual attributes is sometimes large across categories. In this paper, we propose a unified multiplicative framework for attribute learning, which tackles the key problems. Specifically, images and category information are jointly projected into a shared feature space, where the latent factors are disentangled and multiplied to fulfil attribute prediction. The resulting attribute classifier is category-specific instead of being shared by all categories. Moreover, our model can leverage auxiliary data to enhance the predictive ability of attribute classifiers, which can reduce the effort of instance-level attribute annotation to some extent. By integrated into an existing deep learning framework, our model can both accurately predict attributes and learn efficient image representations. Experimental results show that our method achieves superior performance on both instance-level and category-level attribute prediction. For zero-shot learning based on visual attributes and human-object interaction recognition, our method can improve the state-of-the-art performance on several widely used datasets.
资助项目	973 Program[2015CB351802] ; Natural Science Foundation of China (NSFC)[61390515] ; Natural Science Foundation of China (NSFC)[61390511] ; Natural Science Foundation of China (NSFC)[61572465] ; Natural Science Foundation of China (NSFC)[61650202]
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	IEEE COMPUTER SOC
WOS记录号	WOS:000470972300017
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/4165]
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Chang, Hong
作者单位	1.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 3.Chinese Acad Sci, Key Lab Intelligent Informat Proc, Inst Comp Technol, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Shan, Shiguang,Liang, Kongming,Chang, Hong,et al. Unifying Visual Attribute Learning with Object Recognition in a Multiplicative Framework[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2019,41(7):1747-1760.
APA	Shan, Shiguang,Liang, Kongming,Chang, Hong,Ma, Bingpeng,&Chen, Xilin.(2019).Unifying Visual Attribute Learning with Object Recognition in a Multiplicative Framework.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,41(7),1747-1760.
MLA	Shan, Shiguang,et al."Unifying Visual Attribute Learning with Object Recognition in a Multiplicative Framework".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 41.7(2019):1747-1760.