Learning class prototypes via structure alignment for zero-shot recognition

doi:10.1007/978-3-030-01249-6_8

	Learning class prototypes via structure alignment for zero-shot recognition
	Jiang, Huajie1,2,3,4 ; Wang, Ruiping 1,4; Shan, Shiguang 1,4; Chen, Xilin1,4
	2018
会议录名称	15TH EUROPEAN CONFERENCE ON COMPUTER VISION, ECCV 2018
卷号	11214 LNCS
页码	121-138
发表状态	已发表
DOI	10.1007/978-3-030-01249-6_8
摘要	Zero-shot learning (ZSL) aims to recognize objects of novel classes without any training samples of specific classes, which is achieved by exploiting the semantic information and auxiliary datasets. Recently most ZSL approaches focus on learning visual-semantic embeddings to transfer knowledge from the auxiliary datasets to the novel classes. However, few works study whether the semantic information is discriminative or not for the recognition task. To tackle such problem, we propose a coupled dictionary learning approach to align the visual-semantic structures using the class prototypes, where the discriminative information lying in the visual space is utilized to improve the less discriminative semantic space. Then, zero-shot recognition can be performed in different spaces by the simple nearest neighbor approach using the learned class prototypes. Extensive experiments on four benchmark datasets show the effectiveness of the proposed approach. © Springer Nature Switzerland AG 2018.
会议地点	Munich, Germany
收录类别	EI ; CPCI ; CPCI-S
资助项目	Chinese Academy of Sciences[2015085] ; National Natural Science Foundation of China[61390511] ; National Natural Science Foundation of China[61772500]
出版者	Springer Verlag
EI入藏号	20184305978729
EI主题词	Computer vision
EI分类号	Computer Applications:723.5
原始文献类型	Conference article (CA)
引用统计	正在获取...
文献类型	会议论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/28669
专题	信息科学与技术学院_博士生信息科学与技术学院_特聘教授组_陈熙霖组
通讯作者	Wang, Ruiping
作者单位	1.Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing; 100190, China 2.Shanghai Institute of Microsystem and Information Technology, CAS, Shanghai; 200050, China 3.ShanghaiTech University, Shanghai; 200031, China 4.University of Chinese Academy of Sciences, Beijing; 100049, China
第一作者单位	上海科技大学
推荐引用方式 GB/T 7714	Jiang, Huajie,Wang, Ruiping,Shan, Shiguang,et al. Learning class prototypes via structure alignment for zero-shot recognition[C]:Springer Verlag,2018:121-138.