基本信息
韩志 男 硕导 沈阳自动化研究所
电子邮件:hanzhi@sia.cn
通信地址:辽宁省沈阳市沈河区南塔街114号
邮政编码:

招生信息

   
招生专业
081104-模式识别与智能系统
招生方向
计算机视觉,统计建模,数据挖掘

教育背景

2009-11--2011-11 加州大学洛杉矶分校 国家公派联合培养
2007-09--2012-09 西安交通大学 博士
2005-09--2007-07 西安交通大学 硕士
2001-09--2005-07 西安交通大学 学士

工作经历

   
工作简历
2015-01--今 中国科学院沈阳自动化研究所 副研究员
2012-09--2014-12 中国科学院沈阳自动化研究所 助理研究员

出版信息

   
发表论文
[1] Siquan Yu, Jiaxin Liu, Zhi Han, Yong Li, Yandong Tang, Chengdong Wu. Representation Learning Based on Autoencoder and Deep Adaptive Clustering for Image Clustering. MATHEMATICAL PROBLEMS IN ENGINEERING[J]. 2021, 2021: https://doaj.org/article/604c77aabe564c94ad30a4e08d213aa2.
[2] 张少杰, 罗琼, 韩志, 唐延东. 基于边信息的高光谱图像恢复模型. 计算机应用研究. 2021, 38(10): 3166-3171, http://lib.cqvip.com/Qikan/Article/Detail?id=7105718287.
[3] Zhao, Qian, Rui, Xiangyu, Han, Zhi, Meng, Deyu. Multilinear Multitask Learning by Rank-Product Regularization. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS[J]. 2020, 31(4): 1336-1350, http://dx.doi.org/10.1109/TNNLS.2019.2919774.
[4] Han Zhi, Yu Siquan, Lin ShaoBo, Zhou DingXuan. Depth Selection for Deep ReLU Nets in Feature Extraction and Generalization. 2020, http://arxiv.org/abs/2004.00245.
[5] Jianjiang Zhu, Siquan Yu, Lei Gao, Zhi Han, Yandong Tang. Saliency-Based Diver Target Detection and Localization Method. Mathematical Problems in Engineering[J]. 2020, 2020: https://doaj.org/article/47cbd429946045ecb32e4506e16751c6.
[6] Han Zhi. Neural network equivalent model for highly efficient massive data classification. Science China Information Sciences. 2020, [7] Zhu, Jianjiang, Yu, Siquan, Han, Zhi, Tang, Yandong, Wu, Chengdong. Underwater Object Recognition Using Transformable Template Matching Based on Prior Knowledge. Mathematical Problems in Engineering[J]. 2019, 2019: http://ir.sia.cn/handle/173321/24253.
[8] Ma, Zilu, Liu, Shiqi, Meng, Deyu, Zhang, Yong, Lo, SioLong, Han, Zhi. On Convergence Properties of Implicit Self-paced Objective. INFORMATION SCIENCES[J]. 2018, 462: 132-140, http://119.78.100.139/handle/173321/22104.
[9] Shen, Guiping, Han, Zhi, Chen, Xiai, Tang, Yandong. Robust video denoising with sparse and dense noise modelings. SCIENCE CHINA-INFORMATION SCIENCESnull. 2018, 61(1): https://www.webofscience.com/wos/woscc/full-record/WOS:000416050500004.
[10] 唐延东, 张杨, 韩志. Color image denoising based on low-rank tensor train. 2018 10th international conference on graphics and image processing (icgip 2018)null. 2018, http://ir.sia.cn/handle/173321/23847.
[11] 沈贵萍, 张杨, 唐延东, 陈希爱, 韩志. Background reconstruction via low rank tensor factorization. 2018 10th international conference on graphics and image processing (icgip 2018)null. 2018, http://ir.sia.cn/handle/173321/23845.
[12] Tian, Jiandong, Han, Zhi, Ren, Weihong, Chen, Xiai, Tang, Yandong. Snowflake Removal for Videos via Global and Local Low-Rank Decomposition. IEEE TRANSACTIONS ON MULTIMEDIA[J]. 2018, 20(10): 2659-2669, https://www.webofscience.com/wos/woscc/full-record/WOS:000444903000010.
[13] 韩志, 杨秀义, 韩建达, 唐延东. A experimental study to invariance of several groups action to the input of residual networks. Proceeding of the 2018 ieee international conference on information and automation (ieee-icia 2018)null. 2018, 1273-1277, http://ir.sia.cn/handle/173321/23839.
[14] Shen, Guiping, Han, Zhi, Chen, Xiai, Tang, Yandong. Robust video denoising with sparse and dense noise modelings. SCIENCE CHINA-INFORMATION SCIENCESnull. 2018, 61(1): https://www.webofscience.com/wos/woscc/full-record/WOS:000416050500004.
[15] Chen, Xiai, Han, Zhi, Wang, Yao, Zhao, Qian, Meng, Deyu, Lin, Lin, Tang, Yandong. A Generalized Model for Robust Tensor Factorization With Noise Modeling by Mixture of Gaussians. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS[J]. 2018, 29(11): 5380-5393, https://www.webofscience.com/wos/woscc/full-record/WOS:000447832200017.
[16] 高雷, 林扬, 唐延东, 韩志. 基于多传感器的水下小目标自主探测与识别方法. 水中兵器[J]. 2018, 1-5, 11, http://ir.sia.cn/handle/173321/23808.
[17] Ma, Zilu, Liu, Shiqi, Meng, Deyu, Zhang, Yong, Lo, SioLong, Han, Zhi. On Convergence Properties of Implicit Self-paced Objective. INFORMATION SCIENCES[J]. 2018, 462: 132-140, http://119.78.100.139/handle/173321/22104.
[18] Han, Zhi, Shen, Guiping, Yu, Siquan, Ding, Naida, Tian, Jiandong, Tang, Yandong. Active Trace: A Sparse Spatiotemporal Representation for Videos. IEEE ACCESS[J]. 2017, 5: 22433-22442, https://doaj.org/article/064040604361442e858a5481d571c6bf.
[19] Han, Zhi, Tian, Jiandong, Qu, Liangqiong, Tang, Yandong. A New Intrinsic-Lighting Color Space for Daytime Outdoor Images. IEEE TRANSACTIONS ON IMAGE PROCESSING[J]. 2017, 26(2): 1031-1039, http://ir.sia.cn/handle/173321/20242.
[20] Yao Wang, Xiai Chen, Zhi Han, Shiying He. Hyperspectral Image Super-Resolution via Nonlocal Low-Rank Tensor Approximation and Total Variation Regularization. REMOTE SENSING[J]. 2017, 9(12): https://doaj.org/article/ca82688af62f4c8eb7192548fbddede4.
[21] 李冰锋, 唐延东, 韩志. 基于超图直推非负矩阵分解的图像标注法研究. 计算机仿真. 2017, 34(2): 380-384, http://lib.cqvip.com/Qikan/Article/Detail?id=671296821.
[22] 王尧, 陈希爱, 韩志, 沈贵萍, 唐延东. Robust tensor factorization with MRF under complex noise. 7th Annual IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems (IEEE-CYBER 2017)null. 2017, 37-41, http://ir.sia.cn/handle/173321/21351.
[23] Han Zhi. Tensor robust principal component analysis with complex noise. International Conference on Computer Vision. 2017, [24] Ren, Weihong, Tian, Jiandong, Han, Zhi, Chan, Antoni, Tang, Yandong, IEEE. Video Desnowing and Deraining Based on Matrix Decomposition. 30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)null. 2017, 2838-2847, [25] 李冰锋, 唐延东, 韩志. 基于改进的NMF人脸识别算法研究. 计算机仿真[J]. 2016, 428-432, http://lib.cqvip.com/Qikan/Article/Detail?id=668338138.
[26] Chen, Xiai, Han, Zhi, Wang, Yao, Tang, Yandong, Yu, Haibin. Nonconvex plus quadratic penalized low-rank and sparse decomposition for noisy image alignment. SCIENCE CHINA-INFORMATION SCIENCES[J]. 2016, 59(5): http://www.irgrid.ac.cn/handle/1471x/1045533.
[27] Chen, Xiai, Han, Zhi, Wang, Yao, Tang, Yandong, Yu, Haibin. Nonconvex plus quadratic penalized low-rank and sparse decomposition for noisy image alignment. SCIENCE CHINA-INFORMATION SCIENCES[J]. 2016, 59(5): http://www.irgrid.ac.cn/handle/1471x/1045533.
[28] Li, Bingfeng, Tang, Yandong, Han, Zhi. Robust Structure Preserving Nonnegative Matrix Factorization for Dimensionality Reduction. MATHEMATICAL PROBLEMS IN ENGINEERING[J]. 2016, 2016: http://www.irgrid.ac.cn/handle/1471x/1142394.
[29] Tian, Jiandong, Duan, Zhigang, Ren, Weihong, Han, Zhi, Tang, Yandong. Simple and effective calculations about spectral power distributions of outdoor light sources for computer vision. OPTICS EXPRESS[J]. 2016, 24(7): 7266-7286, http://www.irgrid.ac.cn/handle/1471x/1045542.
[30] Chen, Xiai, Han, Zhi, Wang, Yao, Zhao, Qian, Meng, Deyu, Tang, Yandon, IEEE. Robust Tensor Factorization with Unknown Noise. 2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)null. 2016, 5213-5221, http://www.irgrid.ac.cn/handle/1471x/1142478.
[31] Chen, Xiai, Han, Zhi, Tang, Yandong, IEEE. Manifold Mapping Learning by Regression Tree Boosting. 2015 IEEE INTERNATIONAL CONFERENCE ON CYBER TECHNOLOGY IN AUTOMATION, CONTROL, AND INTELLIGENT SYSTEMS (CYBER)null. 2015, 1579-1583, http://www.irgrid.ac.cn/handle/1471x/1008471.
[32] 古楠楠, 樊明宇, 王迪, 韩志. 流形学习若干关键问题与算法研究. 2015, 192页-, http://ir.sia.ac.cn/handle/173321/17495.
[33] Qu Liangqiong, Duan Zhigang, Tian Jiandong, Han Zhi, Tang Yandong, Zha H, Chen X, Wang L, Miao Q. Object Color Constancy for Outdoor Multiple Light Sources. COMPUTER VISION, CCCV 2015, PT IInull. 2015, 547: 369-378, [34] Cao, Wenfei, Wang, Yao, Yang, Can, Chang, Xiangyu, Han, Zhi, Xu, Zongben. Folded-concave penalization approaches to tensor completion. NEUROCOMPUTING[J]. 2015, 152: 261-273, http://dx.doi.org/10.1016/j.neucom.2014.10.069.
[35] Han, Zhi, Xu, Zongben, Zhu, SongChun. Video Primal Sketch: A Unified Middle-Level Representation for Video. JOURNAL OF MATHEMATICAL IMAGING AND VISION[J]. 2015, 53(2): 151-170, http://www.irgrid.ac.cn/handle/1471x/934141.
[36] Qu, Liangqiong, Tian, Jiandong, Han, Zhi, Tang, Yandong. Pixel-wise orthogonal decomposition for color illumination invariant and shadow-free image. OPTICS EXPRESS[J]. 2015, 23(3): 2220-2239, http://www.irgrid.ac.cn/handle/1471x/934146.
[37] Han, Zhi, Wang, Jianjun, Jing, Jia, Zhang, Hai. A Simple Gaussian Measurement Bound for Exact Recovery of Block-Sparse Signals. DISCRETE DYNAMICS IN NATURE AND SOCIETY[J]. 2014, 2014: http://www.irgrid.ac.cn/handle/1471x/921580.
[38] Shen, Guiping, Han, Zhi, Tang, Yandong, IEEE. Robust Video Denoising by Low-rank Decomposition and Modeling Noises with Mixture of Gaussian. 2014 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND BIOMIMETICS IEEE-ROBIO 2014null. 2014, 2226-2231, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000380399500371.
[39] 韩志, 孟德宇, 徐宗本, 古楠楠. Incremental Alignment Manifold Learning. 计算机科学技术学报:英文版. 2011, 26(1): 153-165, http://lib.cqvip.com/Qikan/Article/Detail?id=36339549.
[40] 韩志, 朱旭, 徐宗本. 基于度分析的广义胞映射分析方法. 应用数学学报[J]. 2011, 34(2): 240-252, http://lib.cqvip.com/Qikan/Article/Detail?id=37231182.
[41] 朱旭, 韩志. 求解大规模TSP问题的混合算法. 工程数学学报[J]. 2007, 24(5): 923-926, http://lib.cqvip.com/Qikan/Article/Detail?id=25532689.

科研活动

   
科研项目
( 1 ) 视频的中层视觉表达和高层行为识别研究, 主持, 国家级, 2014-01--2016-12
( 2 ) 多层视觉统一视频表达及其应用, 主持, 国家级, 2015-01--2016-12
( 3 ) 低秩矩阵复原的Schatten-q(0( 4 ) 脊柱微创手术环境研究, 参与, 国家级, 2014-01--2018-12
( 5 ) 小目标自主检测识别技术, 主持, 部委级, 2017-01--2018-12
( 6 ) 基于低秩张量特性的图像视频表达建模及其算法应用研究, 主持, 国家级, 2018-01--2021-12
( 7 ) 基于类生命孪生的机器人智能学习方法, 主持, 国家级, 2020-11--2023-10