Cross-modal subspace clustering via deep canonical correlation analysis

CORC > 沈阳自动化研究所 > 中国科学院沈阳自动化研究所 > 机器人学研究室

	Cross-modal subspace clustering via deep canonical correlation analysis
	Gao QX(高全学)2; Lian, Huanhuan 2; Wang QQ(王倩倩)2; Sun G(孙干)1
	2020
会议日期	February 7-12, 2020
会议地点	New York
页码	3938-3945
英文摘要	For cross-modal subspace clustering, the key point is how to exploit the correlation information between cross-modal data. However, most hierarchical and structural correlation information among cross-modal data cannot be well exploited due to its high-dimensional non-linear property. To tackle this problem, in this paper, we propose an unsupervised framework named Cross-Modal Subspace Clustering via Deep Canonical Correlation Analysis (CMSC-DCCA), which incorporates the correlation constraint with a self-expressive layer to make full use of information among the inter-modal data and the intra-modal data. More specifically, the proposed model consists of three components: 1) deep canonical correlation analysis (Deep CCA) model; 2) self-expressive layer; 3) Deep CCA decoders. The Deep CCA model consists of convolutional encoders and correlation constraint. Convolutional encoders are used to obtain the latent representations of cross-modal data, while adding the correlation constraint for the latent representations can make full use of the information of the inter-modal data. Furthermore, self-expressive layer works on latent representations and constrain it perform self-expression properties, which makes the shared coefficient matrix could capture the hierarchical intra-modal correlations of each modality. Then Deep CCA decoders reconstruct data to ensure that the encoded features can preserve the structure of the original data. Experimental results on several real-world datasets demonstrate the proposed method outperforms the state-of-the-art methods.
源文献作者	Association for the Advancement of Artificial Intelligence
产权排序	2
会议录	AAAI 2020 - 34th AAAI Conference on Artificial Intelligence
会议录出版者	AAAI press
会议录出版地	Palo Alto, CA
语种	英语
ISBN号	978-1-57735-835-0
WOS记录号	WOS:000667722804002
内容类型	会议论文
源URL	[http://ir.sia.cn/handle/173321/28935]
专题	沈阳自动化研究所_机器人学研究室
通讯作者	Lian, Huanhuan; Wang QQ(王倩倩)
作者单位	1.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, China 2.State Key Laboratory of Integrated Services Networks, Xidian University, Xi'an 710071, China
推荐引用方式 GB/T 7714	Gao QX,Lian, Huanhuan,Wang QQ,et al. Cross-modal subspace clustering via deep canonical correlation analysis[C]. 见:. New York. February 7-12, 2020.