[1]尹宝才,张超辉,胡永利,等.基于图嵌入的自适应多视降维方法[J].智能系统学报,2021,16(5):963-970.[doi:10.11992/tis.202105021]
 YIN Baocai,ZHANG Chaohui,HU Yongli,et al.An adaptive multi-view dimensionality reduction method based on graph embedding[J].CAAI Transactions on Intelligent Systems,2021,16(5):963-970.[doi:10.11992/tis.202105021]
点击复制

基于图嵌入的自适应多视降维方法(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第16卷
期数:
2021年5期
页码:
963-970
栏目:
吴文俊人工智能科技进步奖一等奖
出版日期:
2021-09-05

文章信息/Info

Title:
An adaptive multi-view dimensionality reduction method based on graph embedding
作者:
尹宝才12 张超辉1 胡永利12 孙艳丰12 王博岳12
1. 北京工业大学 信息学部,北京 100124;
2. 北京人工智能研究院,北京 100124
Author(s):
YIN Baocai12 ZHANG Chaohui1 HU Yongli12 SUN Yanfeng12 WANG Boyue12
1. Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China;
2. Beijing Artificial Intelligence Institute, Beijing 100124, China
关键词:
降维多视数据图嵌入自适应学习高维数据相似性度量无监督学习表示学习
Keywords:
dimensionality reductionmulti-view datagraph embeddingadaptive learninghigh-dimensional datasimilarity measureunsupervised learningrepresentation learning
分类号:
TP18
DOI:
10.11992/tis.202105021
摘要:
随着监控摄像头的普及和数据采集技术的快速发展,多视数据呈现出规模大、维度高和多源异构的特点,使得数据存储空间大、传输慢、算法复杂度高,造成“有数据、难利用”的困境。到目前为止,国内外在多视降维方面的研究还比较少。针对这一问题,本文提出一种基于图嵌入的自适应多视降维方法。该方法在考虑视角内降维后数据重构原始高维数据的基础上,提出自适应学习相似矩阵来探索不同视角之间降维后数据的关联关系,学习各视数据的正交投影矩阵实现多视降维任务。本文在多个数据集上对降维后的多视数据进行了聚类/识别实验验证,实验结果表明基于图嵌入的自适应多视降维方法优于其他降维方法。
Abstract:
With the popularity of surveillance cameras and the rapid development of data acquisition technology, multi-view data shows the traits of large scale, high dimension and multi-source heterogeneity, which cause large data storage, low data transmission speed and high algorithm complexity, resulting in a predicament that “there are plenty of data that are hard to use”. Up to now, few domestic and foreign researches have been done on multi-view dimensionality reduction. In order to solve this problem, this paper proposes an adaptive multi-view dimensionality reduction method based on graph embedding. In consideration of the reconstructed high-dimensional data after the view-angle dimensionality reduction, this method puts forward an adaptive similarity matrix to explore the correlation between dimension-reduced data from different perspectives and learn the orthogonal projection matrix of each perspective to achieve the multi-view dimensionality reduction task. In this paper, a clustering/recognition verification experiment is performed on the dimension-reduced multi-view data from multiple data sets. The experimental results present that the proposed method is better than other dimensionality reduction methods.

参考文献/References:

[1] SHARIF M, MOHSIN S, JAVED M Y. A survey: face recognition techniques[J]. Research journal of applied sciences, engineering and technology, 2012, 4(23): 4979-4990.
[2] CHALLA A, DANDA S, SAGAR B S D, et al. Power spectral clustering[J]. Journal of mathematical imaging and vision, 2020, 62(9): 1195-1213.
[3] DONOHO D L. High-dimensional data analysis: the curses and blessings of dimensionality[J]. AMS math challenges lecture, 2000, 1: 32.
[4] YAN Yan, RICCI E, SUBRAMANIAN R, et al. Multitask linear discriminant analysis for view invariant action recognition[J]. IEEE transactions on image processing, 2014, 23(12): 5599-5611.
[5] SUN Yaoqi, LI Liang, ZHENG Liang, et al. Image classification base on PCA of multi-view deep representation[J]. Journal of visual communication and image representation, 2019, 62: 253-258.
[6] BLASCHKO M B, LAMPERT C H. Correlational spectral clustering[C]//2008 IEEE Conference on Computer Vision and Pattern Recognition. Anchorage, USA, 2008: 1-8.
[7] ZHANG Yanyan, ZHANG Jianchun, Pan Zhisong, et al. Multi-view dimensionality reduction via canonical random correlation analysis[J]. Frontiers of computer science, 2016, 10(5): 856-869.
[8] SUN Tingkai, CHEN Songcan, Yang Jingyu, et al. A novel method of combined feature extraction for recognition[C]//2008 Eighth IEEE International Conference on Data Mining. Pisa, Italy, 2008: 1043-1048.
[9] 杨健, 杨静宇, 叶晖. Fisher线性鉴别分析的理论研究及其应用[J]. 自动化学报, 2003, 29(4): 481-493.YANG Jian, YANG Jingyu, YE Hui. Theory of Fisher linear discriminant analysis and its application[J]. Acta automatica sinica, 2003, 29(4): 481-493.
[10] LUO Yong, TAO Dacheng, RAMAMOHANARAO K, et al. Tensor canonical correlation analysis for multi-view dimension reduction[J]. IEEE transactions on knowledge and data engineering, 2015, 27(11): 3111-3124.
[11] SHARMA A, JACOBS D W. Bypassing synthesis: PLS for face recognition with pose, low-resolution and sketch[C]//CVPR 2011. Colorado Springs, USA, 2011: 593-600.
[12] XIA Tian, TAO Dacheng, MEI Tao, et al. Multiview spectral embedding[J]. IEEE transactions on systems, man, and cybernetics, part B (cybernetics), 2010, 40(6): 1438-1446.
[13] LIN Y Y, LIU T L, FUH C S. Multiple kernel learning for dimensionality reduction[J]. IEEE transactions on pattern analysis and machine intelligence, 2011, 33(6): 1147-1160.
[14] ZHANG Changqing, FU Huazhu, HU Qinghua, et al. Flexible multi-view dimensionality co-reduction[J]. IEEE transactions on image processing, 2017, 26(2): 648-659.
[15] BEN X, GONG C, ZHANG P, et al. Coupled patch alignment for matching cross-view gaits[J]. IEEE transactions on image processing, 2019, 28(6): 3142-3157.
[16] NIE Feiping, CAI Guohao, LI Xuelong. Multi-view clustering and semi-supervised classification with adaptive neighbours[C]//Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence. San Francisco, USA, 2017: 2408-2414.
[17] WEINLAND D, RONFARD R, BOYER E. Free viewpoint action recognition using motion history volumes[J]. Computer vision and image understanding, 2006, 104(2/3): 249-257.
[18] OJALA T, PIETIKAINEN M, MAENPAA T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[J]. IEEE transactions on pattern analysis and machine intelligence, 2002, 24(7): 971-987.
[19] LADES M, VORBRUGGEN J C, BUHMANN J, et al. Distortion invariant object recognition in the dynamic link architecture[J]. IEEE transactions on computers, 1993, 42(3): 300-311.
[20] WINN J, JOJIC N. Locus: learning object classes with unsupervised segmentation[C]//Tenth IEEE International Conference on Computer Vision. Beijing, China, 2005: 756-763.
[21] WU Baoyuan, ZHANG Yifan, HU Baogang, et al. Constrained clustering and its application to face clustering in videos[C]//2013 IEEE Conference on Computer Vision and Pattern Recognition. Portland, USA, 2013: 3507-3514.
[22] ABDI H, WILLIAMS L J. Principal component analysis[J]. WIREs: computational statistics, 2010, 2(4): 433-459.
[23] NIE Feiping, CAI Guohao, LI Jing, et al. Auto-weighted multi-view learning for image clustering and semi-supervised classification[J]. IEEE transactions on image processing, 2018, 27(3): 1501-1511.
[24] YAN Shuicheng, XU Dong, ZHANG Benyu, et al. Graph embedding and extensions: a general framework for dimensionality reduction[J]. IEEE transactions on pattern analysis and machine intelligence, 2007, 29(1): 40-51.

相似文献/References:

[1]胡娜,马慧,湛涛.融合LBP纹理特征与B2DPCA技术的手指静脉识别方法[J].智能系统学报,2019,14(3):533.[doi:10.11992/tis.201801014]
 HU Na,MA Hui,ZHAN Tao.Finger vein recognition method combining LBP texture feature and B2DPCA technology[J].CAAI Transactions on Intelligent Systems,2019,14(5):533.[doi:10.11992/tis.201801014]
[2]徐慧敏,陈秀宏.图正则化稀疏判别非负矩阵分解[J].智能系统学报,2019,14(6):1217.[doi:10.11992/tis.201811021]
 XU Huimin,CHEN Xiuhong.Graph-regularized, sparse discriminant, non-negative matrix factorization[J].CAAI Transactions on Intelligent Systems,2019,14(5):1217.[doi:10.11992/tis.201811021]
[3]陈丽,马楠,逄桂林,等.多视角数据融合的特征平衡YOLOv3行人检测研究[J].智能系统学报,2021,16(1):57.[doi:10.11992/tis.202010003]
 CHEN Li,MA Nan,PANG Guilin,et al.Research on multi-view data fusion and balanced YOLOv3 for pedestrian detection[J].CAAI Transactions on Intelligent Systems,2021,16(5):57.[doi:10.11992/tis.202010003]
[4]李顺勇,王改变.一种新的最大相关最小冗余特征选择算法[J].智能系统学报,2021,16(4):649.[doi:10.11992/tis.202009016]
 LI Shunyong,WANG Gaibian.New MRMR feature selection algorithm[J].CAAI Transactions on Intelligent Systems,2021,16(5):649.[doi:10.11992/tis.202009016]

备注/Memo

备注/Memo:
收稿日期:2021-05-13。
基金项目:国家自然科学基金项目(U19B2039,61906011);北京市自然科学基金项目(4204086)
作者简介:尹宝才,教授,博士生导师,国家杰出青年科学基金获得者,多媒体与智能软件技术北京市重点实验室主任,北京人工智能研究院院长,中国计算机学会人工智能与模式识别专业委员会委员,ACM 北京分会副主席。主要研究方向为多媒体技术、跨媒体智能、视频编码。主持国家973项目、国家自然科学基金重大项目、国家自然科学基金重点项目、北京市自然科学基金重点项目等10余项。发表学术论文60余篇。张超辉,硕士研究生,主要研究方向为机器学习、数据挖掘;胡永利,教授,博士生导师,主要研究方向为模式识别、计算机视觉、跨媒体智能和智能交通。入选北京市百千万人才工程、北京市高层次创新人才支持计划领军人才、北京市高等学校创新团队?交通大数据处理学术创新团队。主持国家自然科学基金联合基金重点项目、面上项目等10余项。发表学术论文30余篇。
通讯作者:胡永利.E-mail:huyongli@bjut.edu.cn
更新日期/Last Update: 1900-01-01