西安电子科技大学人工智能学院导师教师师资介绍简介-梁雪峰

删除或更新信息，请邮件至freekaoyan#163.com(#换成@)

本站小编 Free考研考试/2021-07-10

基本信息
梁雪峰
陕西省创新长期计划
华山****
硕导，博导
博士学科：
计算机科学与技术(081200)
硕士学科：
计算机科学与技术(081200)
工作单位：人工智能学院

联系方式
通信地址：陕西省西安市太白南路2号
电子邮箱：xliang@xidian.edu.cn
办公电话：
办公地点：北校区主楼II区

个人简介
山东烟台人。于2003年从西安电子科技大学计算机专业获得硕士学位，之后东渡日本，在 Japan Advanced Institute of Science and Technology 的浅野哲夫教授指导下从事计算几何的理论研究和其在模式识别中的应用，期间多次获得石川县和学校的研究奖励金，2006 年获得博士学位。2006-2008 年间获得日本JST研究员项目资助，在日本产业综合技术研究所从事机器人视觉研究。2008 年同时加入英国伦敦大学学院（世界排名第7，QS排名）心理学系，伦敦玛丽女皇大学（世界排名第121）计算机学院从事视觉感知和视觉认知研究。2010 年受邀以副教授身份加入日本京都大学（世界排名第36）信息学院。2018 年4月受聘为华山****加入西安电子科技大学人工智能学院，同年入选陕西省创新长期计划。
研究领域集中在：视觉认知计算（心理学），计算机视觉，视觉大数据挖掘，智能算法等。
主持完成英国皇家学会(Royal Society)国际交流项目1项，日本国家学术振兴会 (JSPS) 项目2项，京都大学校长裁量项目1项，日本企业合作研发项目2项。组织或协同组织过多次国际会议，并为2个国际期刊的副主编，2个国际期刊特刊的客座主编。

新闻
我们的论文 "CALLip: Lipreading using Contrastive and Attribute Learning" 被顶会ACMMM2021录用，恭喜21级黄奕洋同学！
The 9th International Conference on Information Technology: IoT and Smart City国际会议ICIT 2021将在广州召开，欢迎投稿！
我们的论文 "Progressive Co-teaching for Ambiguous Speech Emotion Recognition" 被语音领域重要国际会议ICASSP2021录用，恭喜各位同学！
我们的论文 "Element-wise Feature Relation Learning Network for Cross-Spectral Image Patch Matching" 被IEEE Trans. on Neural Networks and Learning Systems录用，IF(8.793)。
我与京都大学合作利用AI技术研究心理认知的论文 "Putative Ratios of Facial Attractiveness in a Deep Neural Network" 被心理学期刊 Vision Research录用，这是近几年我最满意的研究工作之一。[Link]
我担任The 8th International Conference on Information Technology: IoT and Smart City国际会议主席，ICIT 2020 于2020年12月25-27日在西安召开。
我们的论文 "Jointly Discriminating and Frequent Visual Representation Mining" 被ACCV 2020录用，恭喜各位同学！
我们的两篇论文被ICCV 2019录用，其中 "AFD-Net: Aggregated Feature Difference Learning for Cross-Spectral Image Patch Matching" 录为Oral，恭喜各位同学！（Oral acceptance ratio4.3%）
受清华大学交叉研究院邀请，我于5月13日做学术报告。
我们两篇论文被国际会议 The 26^thIEEE International Conference on Image Processing (ICIP 2019) 录用。
我们的论文“Wide or Narrow? A Visual Attention Inspired Model for View-Type Classification”, 已被IEEE ACCESS, IF(4.098)录用.[Link]
我们的论文“Cross-spectral Image Patch Matching by Learning Features of the Spatially Connected Patches in a Shared Space”已被国际会议ACCV 2018录用！(Testing Code)
我们在国际期刊 Signal Processing Image Communication (Elsevier) 组织了特刊“The Deep Learning in Computational Photography”。
Our paper "An External Learning Assisted Self-examples Learning for Image Super-resolution" has been accepted by Neurocomputing(ELSEVIER),IF(4.072). [Link]
我们在人工智能国际顶级会议 IJCAI-ECAI2018 中组织了主题为“可解释的深度学习”的研讨会"Interpretable & Reasonable Deep Learning and its Applications (IReDLiA)".
本人被授予 日本京都府知事奖。
Our paper "A Deep Learning Framework for Remote Sensing Image Registration" has been accepted by ISPRS Journal of Photogrammetry and Remote Sensing (ELSEVIER), IF(6.942). [Link]
Our paper "How Does the Low-Rank Matrix Decomposition Help Internal and External Learnings for Super-Resolution" has been accepted by IEEE Transactions on Image Processing, IF(6.79). [Link]
I serve as an expert advisor for the Chinese AI Research Association (Japan).
Our paper "Robust coupled dictionary learning with ?1-norm coefficients transition constraint for noisy image super-resolution" has been accepted by Signal Processing (ELSEVIER), IF(4.086). [Link]

组织学术活动
The 7th International Conference on Information Technology: IoT and Smart City (ICIT 2019),20-23, 12月, 2019, 上海，中国。
The 2nd International Conference on Data Science and Information Technology, 19-21，7月，2019，首尔，韩国。
International workshope"Interpretable & Reasonable Deep Learning and its Applications (IReDLiA)"in conjunction with IJCAI-ECAI2018.
International Conference on Video and Image Processing. 27-29, 12月, 2017, 新加坡，南洋理工大学.
Kyoto University & Queen Mary University of London Joint Workshop, Intelligent Sensing on Media Data. 26~27，3月， 2015, 日本京都大学。
Kyoto University & University College London Workshop on Perception of Motion and Pattern. 12，3月，2013，日本京都大学。
Kyoto University & Queen Mary University of London Symposium on Intelligent Sensing. 18~20，3月，2013,日本京都大学。

受邀演讲
"Learning Features for Image Patch Matching", @ 南方科技大学，2019年10月，中国深圳。
"View Angles may Reveal Your Mood: A psychological explanation and an example in the real world"，清华大学交叉研究院，2019年5月，中国北京。
"View Angles may Reveal Your Mood: A psychological explanation and an example in the real world"，International Conference of Union of Mathematical Imaging (UMI2019)，2019年5月，中国北京。
"Learning the Shared Feature from Cross Domains for Vision Applications & Tackling Data Issues in the Real World Scenario", @ International Conference on Information Technology, 2018年12月，香港。
"Happier Mood Trigger Bigger Pictures", @ International Workshop on Bio-inspired Systems, Bio-electronics, Machine Intelligence, 2018年1月，台湾省。
"Viewing Bigger Pictures Promotes Happier Mood: a psychological explanation and an example in the wild", @ International Conference on Video and Image Processing, 2017年12月，新加坡。
"Visual Attention and Emotion", @ The 19th Academic Symposium of the Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, 2017年10月，中国。
"Studying Visual Attention in Image and Video", @ The 9th International Conference on Intelligent Robotics and Applications，2016年8月，日本。
"Modeling visual attention in image and video", @ Kyoto-Bordeaux mini-symposium, 2016年，2月，日本。
"How does Robot Understand the Visual Motion?", @ 京都大学-学术日，2015年，10月，日本。
"Motion Segmentation in Complex Video", @ 天津大学，2015年，8月，中国
"Salient Motion Detection from Complex Video using Potential Surface", @ 国立首尔大学，2013年，9月，韩国。
"Salient Information, from Static to Dynamic", @ 国立清华大学，2013年3月，台湾省。

科学研究
目前研究团队承担的科研项目：
大脑破译与人工智能基础理论研究（西安市科技创新项目，100万） 2019 ~ 2021
西电科研启动金 2018 ~ 2021
JSPS Grants-in-Aid for Science Research C, PI 2015 ~ 2017
JSPS Grant-in-Aid for Young Scientists B, PI 2013 ~ 2015
International Exchanges Scheme (Royal Society, UK), Joint, PI: Prof. Peter McOwan, Queen Mary University of London, 2012 ~ 2013

学术论文
著书
现代神经网络教程，杨淑媛，焦李成，刘梦琨，赵进，刘芳，梁雪峰，西安电子科技大学出版社，2019。
期刊论文
Y.H. Cui, F. Liu, L.C. Jiao, Y.W. Guo, X.F. Liang, L.L. Li, S.Y. Yang, X.X. Qian, "Polarimetric Multipath Convolutional Neural Network for PolSAR Image Classification", IEEE Trans. on Geoscience and Remote Sensing, May. 2021. doi: 10.1109/TGRS.2021.**, IF(5.855).
D. Quan, S. Wang, N. Huyan, J. Chanussot, R.J. Wang, X.F. Liang, B. Hou, L.C. Jiao, "Element-wise Feature Relation Learning Network for Cross-Spectral Image Patch Matching'', IEEE Trans. on Neural Networks and Learning Systems, Jan. 2021. doi: 10.1109/TNNLS.2021.**, IF(8.793).
S. Tong, X.F. Liang, T. Kumada, S. Iwaki, "Putative Ratios of Facial Attractiveness in a Deep Neural Network", Vision Research, Vol. 178, pp. 86-99, Jan. 2021.IF(2.610) [Link]
C.X. Wu, B.B. Ju, Y. Wu, X. Lin, N. Xiong, G.Q. Xu, X.F. Liang, “UAV Autonomous Target Search Based on Deep Reinforcement Learning in Complex Disaster Scene”, IEEE ACCESS, Vol. 7, Issue 1, pp. 117227-117245, Dec. 2019. IF(4.098)
K.L. Zeng, T. Lu, X.F. Liang, K. Liu, H. Chen, Y.D. Zhang, “Face Super-resolution via Bil[ant]ayer Contextual Representation”, has been accepted bySignal Processing: Image Communication (ELSEVIER), Vol.75, pp. 147-157, July 2019.IF(2.814)
S. Tong, Y.P. Loh, X.F. Liang, T. Kumada, “Wide or Narrow? A Visual Attention Inspired Model for View-Type Classification”, IEEE ACCESS, Vol. 7, pp.48725- 48738, April, 2019.IF(4.098)
Y.P. Loh,X.F. Liang, C.S. Chan, "Low-light image enhancement using Gaussian Process for features retrieval" Signal Processing: Image Communication(ELSEVIER),Vol.74, pp. 175-190, May 2019. IF(2.814).
B. Yue, S. Wang,X.F. Liang, L.C. Jiao,"An External Learning Assisted Self-examples Learning for Image Super-resolution",Neurocomputing (ELSEVIER),Vol.312, No.27, pp. 107-119, Oct. 2018.IF(4.072).
S. Wang, D. Quan,X.F. Liang, M.D. Ning, Y.H. Guo, L.C. Jiao,“A Deep Learning Framework for Remote Sensing Image Registration”，ISPRS Journal of Photogrammetry and Remote Sensing (ELSEVIER),Vol. 145 A, pp. 148-164,Nov. 2018. IF(6.942).
S. Wang, B. Yue,X.F. Liang, L.C. Jiao,“How does the Low-Rank Matrix Decomposition Help Internal and External Learnings for Super-Resolution”,IEEE Transactions on Image Processing,Vol. 27, No. 3, pp. 1086-1099, Nov. 2017.(IF 6.79).
B. Yue, S. Wang,X.F. Liang, L.C. Jiao, “Robust coupled dictionary learning with ?1-norm coefficients transition constraint for noisy image super-resolution”,Signal Processing (ELSEVIER), Vol. 140, pp.177–189, Apr. 2017. (IF 4.086)
R. Iseki, S. Kajima, X. Zhao, X.F. Liang, S. Tsujimoto, “The Role of Presenter Actions in the Evaluation of Oral Presentations: Evidence from fMRI and Motion-Vector Analysis”,Psychologia, Vol. 59, No.4, Nov. 2016.
B. Yue, S. Wang,X.F. Liang, L.C. Jiao, C.J. Xu,“Joint Prior Learning for Visual Sensor Network Noisy Image Super-Resolution”,Sensors, Vol. 16, No. 3, pii. 288, Mar. 2016. (IF 3.031)
X.F. Liang, C.C. Zhang, T. Matsuyama, “A General Inlier Estimation for Moving Camera Motion Segmentation”,IPSJ Transactions on Computer Vision and Applications,Vol. 7, pp. 163 ~ 174, Dec. 2015. (Invited paper)
C.C. Zhang,X.F. Liang, T. Matsuyama, “Generic Learning based Ensemble Framework for Small Sample Size Face Recognition in Multi-Camera Networks”,Sensors, Vol. 14, No. 12, pp. 23509 ~ 23538, Dec. 2014. (IF 3.031)
C.C. Zhang,X.F. Liang, T. Matsuyama, “Mixed-Motion Segmentation using Helmholtz Decomposition”,IPSJ Transactions on Computer Vision and Applications,Vol. 5, pp. 55-59, 2013. (Invited paper)
X.F. Liang, P.W. McOwan, A. Johnston, “A Biologically Inspired Framework for Spatial and Spectral Velocity Estimations”,Journal of the Optical Society of America A, JOSA A., Vol. 28, Issue 4, pp. 713-723, Apr. 2011. (IF 1.861)
N.X. Xiong, L.T. Yang, J.H. Park,X.F. Liang, T.H. Kim, “Towards a Performance-based Resource Server Control in Grid Computing Environments”,Wireless Personal Communications(Springer), Vol. 51, No. 1, pp. 209-220, Oct. 2009.(IF 1.200)
K. Ohara, T. Sugawara, J.H. Lee, T. Tomizawa, H.M. Do,X.F. Liang, Y.S. Kim. B.K. Kim, Y. Sumi, T. Tanikawa. K. Ohba, “Visual Mark for Robot Manipulation and Its RT Middleware Component”,Advanced Robotics, Vol. 22, No. 6, pp. 633-655, 2008.(IF 1.104)
X.F. Liang, N.X. Xiong, L.T. Yang, H. Zhang, J.H. Park, “A Compensation Scheme of Fingerprint Distortion using Combined Radial Basis Function Model for Ubiquitous Services”,Computer Communications, Vol. 31, No. 18, pp. 4360-4366, Dec. 2008.(IF 2.766)
X.F. Liang, A. Bishnu, T. Asano, “A Robust Fingerprint Indexing Scheme Using Minutia Neighborhood Structure and Low-order Delaunay Triangle”,IEEE Trans. on Information Forensics and Security, Vol. 2, No. 4, pp. 721-733, Dec. 2007. (IF 6.211)
X.F. Liang, A. Bishnu, T. Asano, “A Combinatorial Approach to Fingerprint Binarization and Minutiae Extraction Using Euclidean Distance Transform”,International Journal of Pattern Recognition and Artificial Intelligence, Vol. 21, No. 7, pp. 1141-1158, Nov. 2007.
X.F. Liang, T. Asano, “A Linear Time Algorithm for Binary Fingerprint Image Denoising using Distance Transform”,IEICE Trans. on INF. & SYST., Vol.E89-D, No. 4, pp. 1534–1542, April 2006.(IF 1.11)
X.F. Liang, F. Liu, “A SVM Algorithm Based on Linear Combinatorial Kernels”, Computer Science, Vol. 29, pp. 361–363, 2002. (In Chinese)
X.F. Liang, F. Liu, “A SVM Algorithm Based on the minimal Support Vector Set”, Journal of Xidian University, Vol. 29, 2002. (In Chinese)
国际会议论文
Y.Y. Huang, X.F. Liang,C.W. Fang, "CALLip: Lipreading using Contrastive and Attribute Learning", Proc. the 29th ACM International Conference on Multimedia (ACMMM 2021), Chengdu, China, October, 2021.
Y.F Yin, Y, Gu, L.S. Yao, Y. Zhou, X.F. Liang, H. Zhang,"Progressive Co-teaching for Ambiguous Speech Emotion Recognition", Proc. Intl. Conf. on Acoustics, Speech and Signal Processing(ICASSP 2021), Toronto, Canada, June, 2021.
Q.N. Wang, Y. Zhou, Z.Y. Zhu, X.F. Liang, Yu. Gu, "Jointly Discriminating and Frequent Visual Representation Mining",Proc. Asian Conf. on Computer Vision(ACCV 2020), Kyoto, Japan, November, 2020.
Q.N. Wang, Z.Y. Zhu, X.F. Liang, H.W. Shi, P. Cao, "Deep Relevance Feature Clustering for Discovering Visual Representation of Tourism Destination", Proc. Chinese Conf. on Pattern Recognition and Computer Vision (PRCV 2020), Nanjing, China, October, 2020.
D. Quan, X.F. Liang, S. Wang, S.W. Wei, Y.F. Li, N. Huyan, L.C. Jiao, "AFD-Net: Aggregated Feature Difference Learning for Cross-Spectral Image Patch Matching",ICCV2019 (Oral Presentation, Acceptance rate: 4.3%), Seoul, Korea, October, 2019.
S. Wang, Y.F. Li, X.F. Liang, D. Quan, B.W. Yang, S.W. Wei, L.C. Jiao,"Better and Faster: Exponential Loss for Image Patch Matching",ICCV2019, Seoul, Korea, October, 2019.
X.F. Liang, S. Tong, T. Kumada, S. Iwaki, “Golden Ratio: The Attributes of Facial Attractiveness Learned by CNN”, Proc. Intl. Conf. on Image Processing (ICIP 2019), Taipei, Taiwan, September, 2019.
Y. Liu, X.F. Liang, S. Tong, T. Kumada, “Photo Shot-type Disambiguation by Multi-Classifier Semi-supervised Learning”, Proc. Intl. Conf. on Image Processing (ICIP 2019), Taipei, Taiwan, September, 2019.
X.F. Liang, S. Tong, T. Kumada, Y.P. Loh, "Understanding the Photo-shooting Patterns of Sightseeing", Proc. Intl. Conf. on Data Science and Information Technology Proceedings (DSIT 2019), Seoul, Korea, July, 2019.
S. Wang, L.G. Zhou, P. He, D. Quan, Q. Zhao, X.F. Liang, B. Hou, “An Improved Fully Convolutional Network for Learning Rich Building Features”, Proc. IEEE Intl. Geoscience and Remote Sensing Symposium (IGARSS 2019), Yokohama, Japan, July, 2019.
D. Quan, S. Fang, X.F. Liang,S. Wang, L.C. Jiao,"Cross-spectral Image Patch Matching by Learning Features of the Spatially Connected Patches in a Shared Space”Proc.14th Asian Conf. on Computer Vision (ACCV 2018), Perth, Australia, Dec, 2018.
D. Quan, S. Wang, X.F. Liang, R.J. Wang, S. Fang, B. Hou, L.C. Jiao, ``Deep Generative Matching Network for Optical and SAR Image Registration'', Proc. IEEE Intl. Geoscience and Remote Sensing Symposium (IGARSS 2018), (Oral presentation), Valencia, Spain, July, 2018.Download Paper
Y.P. Loh, S. Tong, X.F. Liang, T. Kumada, C.S. Chan, “Understanding Scenery Quality: A Visual Attention Measure and Its Computational Model”,ICCV2017Workshop on VSM: Web-Scale Vision and Social Media, Venice, Italy, October, 2017.
S. Tong, X.F. Liang, T. Kumada, S. Iwaki, “Learning the Cultural Consistent Facial Aesthetics by Convolutional Neural Network”,Proc. Intl. Conf. on Culture and Computing (ICCC 2017), (Oral presentation, Best paper candidate),Kyoto, Japan, September, 2017.
Z. Wang, S. Wang, C.J. Xu, C.Y. Li, B. Yue, X.F. Liang, “SAR Images Super-Resolution via Cartoon-Texture Image Decomposition and Jointly Optimized Regressors”,IEEE Intl. Geoscience and Remote Sensing Symposium (IGARSS 2017),Texas, USA, July, 2017.
B. Yue, S. Wang, X.F. Liang, L.C. Jiao, “Robust Noisy Image Super-Resolution using L1-norm Regularization and Non-local Constraint”,ACCV 2016 Workshop on NTIRE: New Trends in Image Restoration and Enhancement, (Oral presentation),Taipei, Taiwan, November, 2016.
S. Tong, Y.P. Loh, X.F. Liang, T. Kumada, “Visual Attention Inspired Distant View and Close-Up View Classification”,Proc. Intl. Conf. on Image Processing (ICIP 2016), Phoenix, USA, September, 2016.
S. Wang, S.P. Lin, X.F. Liang, B. Yue, L.C. Jiao, “External And Internal Learning For Single-Image Super-Resolution”,Proc. Intl. Conf. on Image Processing (ICIP 2015), Quebec, Canada, September, 2015.
C.Y. Zhuang, Q. Ma, X.F. Liang, M. Yoshikawa, “Discovering Obscure Sightseeing Spots by Analysis of Geo-tagged Social Images”,Proc. Intl. Conf. on Advances in Social Network Analysis and Mining (ASONAM 2015), Paris, France, August, 2015.
C.C. Zhang, X.F. Liang, X. Xiong, “Decision-Tree Based Hybrid Filter-Wrapping Method for Optimal Combination of Multiple Feature Sets”,Proc. 8th Intl. Conf. on Image and Graphics (ICIG 2015), Tianjin, China, August, 2015.
C.C. Zhang, X.F. Liang, T. Matsuyama, “Multi-Depth Deep Feature Learning for Face Recognition”,Proc. Intl. Conf. on Informatics, Networking and Intelligent Computing (INIC 2014), Shenzhen, China, November, 2014.
X.F. Liang, C.C. Zhang, T. Matsuyama, “Inlier Estimation for Moving Camera Motion Segmentation”,Proc. 12th Asian Conf. on Computer Vision (ACCV 2014), (Oral presentation, Acceptance rate: 3.8%), Singapore, November, 2014.
C.Y. Zhuang, Q. Ma, X.F. Liang, M. Yoshikawa, “Anaba: An Obscure Sightseeing Spots Discovering System”,Proc. IEEE Intl. Conf. on Multimedia and Expo (ICME 2014), Chengdu, China, July, 2014.
X.F. Liang, “Minutia Detail in Fingerprint Indexing”,Proc. 20th Korea-Japan Joint Workshop on Frontiers of Computer Vision (FCV 2014), Okinawa, Japan, February, 2014.
X.F. Liang, Xiangjun Li, “Intelligent Camera Network using Multi-functional Middleware”,Proc. 20th Korea-Japan Joint Workshop on Frontiers of Computer Vision (FCV 2014), Okinawa, Japan, February, 2014.
C.C. Zhang, X.F. Liang, T. Matsuyama, “Small Sample Size Face Recognition using Random Quad-Tree based Ensemble Algorithm”,Proc. The 5th International Conference on Imaging for Crime Detection and Prevention (ICDP 2013), London, UK, December, 2013.
C.C. Zhang, X.F. Liang, T. Matsuyama, “Mixed-Motion Segmentation using Helmholtz Decomposition”,Proc. 16th Meeting on Image Recognition and Understanding(MIRU 2013),Outstanding Paper Award, Tokyo, Japan, August, 2013.
C.C. Zhang, X.F. Liang, T. Matsuyama, “Multi-subregion Face Recognition using Coarse-to-fine Quad-tree Decomposition”,Proc. 21st Intl. Conf. on Pattern Recognition, (Oral presentation, Acceptance rate: 15%), Tsukuba, Japan, Nov. 2012.
C.C. Zhang, X.F. Liang, “A Minimum-Computational-Cost Method for the Parameterization of Quadric Surfaces”,Proc. The Computer Graphics International, Ottawa, Canada, June, 2011.
X.F. Liang, P. W. McOwan, A. Johnston, “A Color Neuromorphic Approach for Motion Estimation”,Proc. IEEE Winter Vision Meetings, Workshop on Motion and Video Computing, pp. 49–54, Snowbird Utah, USA, December, 2009.
X.F. Liang, Y. Sumi, B.K. Kim, H.M. Do, Y.S. Kim, T. Tomizawa, K. Ohara, T. Tanikawa, K. Ohba, “A Camera Array with Flexible Software Architecture in Intelligent Space”,IEEE/ASME Intl. Conf. on Advanced Intelligent Mechatronics2008 (Accepted).
X.F. Liang, Y. Sumi, B.K. Kim, H.M. Do, Y.S. Kim, T. Tomizawa, K. Ohara, T. Tanikawa, K. Ohba, “A Large Planar Camera Array for Multiple Automated Guided Vehicles Localization”,Proc. IEEE/ASME Intl. Conf. on Advanced Intelligent Mechatronics, pp. 608–613, Xian, China, July, 2008.
X.F. Liang, T. Tomizawa, H.M. Do, Y.S. Kim, K. Ohara, B.K. Kim, T. Tanikawa, K. Ohba, “Multiple Robots Localization Using Large Planar Camera Array for Automated Guided Vehicle System”,Proc. IEEE Intl. Conf. on Information and Automation, pp. 984–990, Zhangjiajie, China, June, 2008.
X.F. Liang, T. Tomizawa, J.H. Lee, H.M. Do, Y.S. Kim, K. Ohara, B.K. Kim, T. Tanikawa, K. Ohba, “Large Camera Array System for Real Time Surveillance”,ACCV’07 Workshop on Multi-dimensional and Multi-view Image Processing, Tokyo, Japan, September, 2007.
T.Tomizawa, K.Ohara, T.Sugawara, H.Onda, J.H.Lee, X.F. Liang, H.M.Do, Y.S.Kim, B.K.Kim, T.Tanikawa, K.Ohba, T.Sonoyama, “Introduction to Ubiquitous Space Related Japan Science and Technology Agency Projects at AIST”,IROS 2007, Workshop on Ubiquitous Robotic Space Design and Applications, San Diego, November, 2007.
H.M. Do, B.K. Kim, Y.S. Kim, J.H. Lee, K. Ohara, T. Sugawara, T. Tomizawa, X.F. Liang, T. Tanikawa, K. Ohba, “Development of Simulation Framework for Ubiquitous Robots Using RT-Middleware”,Proc. Intl. Conf. on Control, Automation and Systems, pp. 2483z2486, Korea, October, 2007.
Y.S. Kim, J.H. Lee, B.K. Kim, H.M. Do, T. Tomizawa, K. Ohba, X.F. Liang, K. Ohara, T. Sugawara, and T. Tanikawa, “Localization of Ubiquitous Environment Based Mobile Robot”,Proc. Intl. Conf. on Control, Automation and Systems, pp. 2355–2358, Korea, October, 2007.
X.F. Liang, T. Asano, H. Zhang, “A Combined RBF Model for Fingerprint Distortion”,Proc. 3rd Intl. Conf. on Image Analysis and Recognition (ICIAR 2006), Povoa de Varzim, Portugal, Lecture Notes in Computer Science LNCS 4142, edited by A. Campilho and M. Kamel, “Image Analysis and Recognition”, pp. 286–296, September, 2006.
X.F. Liang, A. Bishnu, T. Asano, “Fingerprint Matching Using Minutiae Polygons”,Proc. 18th Intl. Conf. on Pattern Recognition(ICPR 2006), (Oral presentation, Acceptance rate: 15%), pp. 1046–1049, HongKong, China, August, 2006.
X.F. Liang, A. Bishnu, T. Asano, “Distorted Fingerprint Indexing Using Delaunay Triangle and Minutiae Detail”,Proc. 3rd Intl. Sym. on Voronoi Diagrams in Science and Engineering(ISVD 2006), pp. 217–224, Banff, Canada, July, 2006.
H. Zhang, T.B. Ho, M.S. Lin, X.F. Liang, “Feature Extraction for Time Series Classification Using Discriminating Wavelet Coefficients”,Proc. 3rd Intl. Sym. on Neural Networks(ISNN06), Lecture Notes in Computer Science LNCS 3971–1394, pp. 1394–1399, Chengdu, China, May, 2006.
X.F. Liang, K. Kotani, T. Asano, “Automatically Choosing Appropriately-Sized Structuring Elements to Eliminate Useless Components in Fingerprint Image”,Proc. Visual communications and Image Processing2005 (Proc. Of SPIE, Vol. 5960), pp. 284–293, Beijing, China, July, 2005.
X.F. Liang, A. Bishnu, T. Asano, “A near-linear time algorithm for binarization of fingerprint images using distance transforms”,Proc. 10th Intl. Workshop on Combinatorial Image Analysis, Lecture Notes in Computer Science LNCS 3322, edited by R. Klette and J. Zunic, Combinatorial Image Analysis, pp. 197–208, Auckland, December, 2004.
X.F. Liang, T. Asano, “A fast denoising method for binary fingerprint image”,Proc. IASTED Conf. on Visualization, Imaging, and Image Processing, pp. 309–313, Marbella, Spain, September, 2004.
X.F. Liang, F. Liu, “Choosing Multiple Parameters for SVM Based on Genetic Algorithm”,Proc. 6th Intl. Conf. on Signal Processing, pp. 117–119, Beijing, China, August, 2002.
日本国内论文
S. Tong,X.F. Liang, “The Distant View and Close-up View Classification using DWT and PCANet”, Proc. 18th Meeting on Image Recognition and Understanding (MIRU 2015), Osaka, Japan, July, 2015.
C.Y. Zhuang, Q. Ma,X.F. Liang, M. Yoshikawa, “Discover Anaba Sightseeing Spots using Social Images”, 情報処理学会データベースシステム（DBS）研究会, July, 2013.
菅原隆行, 大原賢一, 李在勲, 冨沢哲雄, KIM YONG-SHIK,梁雪峰, Do Hyun Min, 金奉根,音田弘, 谷川民生, 角保志, 園山隆輔, 大場光太郎, “ロボットの作業を支援するための物理的環境構造化に関する研究”, 第8回システムインテグレーション部門講演会(SI2007), Dec. 2007.
金奉根,梁雪峰, Do Hyun Min, KIM YONG-SHIK, 李在勲, 冨沢哲雄, 大原賢一, 谷川民生, 大場光太郎, “Task Oriented Planning Algorithm for Multiple Mobile Robots in the Ubiquitous Robot Technology Space”, 第8回システムインテグレーション部門講演会(SI2007),Dec. 2007.
KIM YONG-SHIK, 李在勲, 金奉根, Do Hyun Min, 冨沢哲雄,梁雪峰, 谷川民生, 大場光太郎, “Localization of Mobile Robot in Ubiquitous Environment”, SICE SI 2007,Dec. 2007.
大原賢一, 菅原隆行, 李在勲, 冨沢哲雄,梁雪峰, Do Hyun Min, 金容稙, 金奉根, 角保志, 谷川民生, 音田弘, 園山隆輔, 大場光太郎, “人間とロボットの共存環境におけるビジュアルマークの提案”, SICE SI 2007,Dec. 2007.
Do Hyun Min, 金奉根,冨沢哲雄, KIM YONG-SHIK, 李在勲,梁雪峰, 谷川民生, 大場光太郎, “Coordination of Multiple Mobile Robots with Distributed Sensors in Ubiquitous Environment”, SICE SI2007,Dec. 2007.

荣誉获奖
日本京都府知事奖，2017年11月。
Recognition Award: @ the 9th Int. Conf. on Intelligent Robotics and Applications, 日本东京，2016年8月。.
Outstanding Paper Award: C.C. Zhang, X.F. Liang, T. Matsuyama, "Mixed-Motion Segmentation using Helmholtz Decomposition" @ the 16th Meeting on Image Recognition and Understanding, Tokyo, Japan, August, 2013.
Outstanding Research Award: C.C. Zhang, X.F. Liang, T. Matsuyama, "What are you looking for on faces？" @ Kyoto University ICT innovation 2013.

科研团队
如果你的人生规划和他/她们相似，可以来找我谈谈。
在读学生
国内学生
博士：张松，周颖
研3：石慧文，姚龙山，刘子寒，杨晓慧，尹易飞
研2：梁智辉，刘星宇，雷国栋，张霄嵩，林坚，王晨阳，韩迎萍
研1：黄奕洋，马祎繁，陈伟烨，曹畅，玄慧君，楼佳庆，郑仕权
国外学生
Song Tong 博3 2015，8月 ~ . @Kyoto University

访问学生
ZhengAn Zhu 博1 2017，8月 ~ 10月 @ 国立成功大学
毕业学生
2021年
王倩楠华为西研所
朱照延小米手机摄像部门
-----------------------------------------------------------------------------------
Ran Wang 2020~ 日本Amazon
Yang Liu 2019~ 日本京都大学读博
Xiangyue Zhao 2018~ 日本Google
YuenPeng Loh 2018 ~ 马来西亚大学讲师
Cuicui Zhang 2015 ~ 天津大学讲师

课程教学
英文授课
1. Cognitive Science in AI （人工智能中的认知科学）-- 研究生
2. The Graph Theory in AI （人工智能中的图论） -- 研究生
双语授课
3. Cognitive Computing （认知计算） -- 本科、研究生
4. 科学信息素养（通识课） -- 本科、
以往授课
Fundamentals of Machine Vision 2014 ~ 2018, @Kyoto Univ.
Information Literacy for Academic Study 2014 ~ 2018, @Kyoto Univ.
Pattern Recognition (Advanced), 2011 ~ 2018, @Kyoto Univ.
Computer Vision, 2010 ~ 2017, @Kyoto Univ.
Advanced Approaches in Machine Vision, 2011 ~ 2013, @Kyoto Univ.
Introduction to Information Science, 2010 ~ 2014, @Kyoto Univ.
Computer Graphics LEC (DCS314) 2009 ~ 2010, @Queen Mary Univ. of London.

招生要求
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
研究生招生信息：
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2022学术博士1名（欢迎已发表过主流会议或期刊的优秀硕士生联系！！），工程博士1名（人工智能方向）。
2022硕士6名（保研名额充足），中外联合培养硕士1名（与日本京都大学联合培养，要求英语和科研能力较高）。
本人事业的重要部分之一是为社会培养优秀人才，欢迎有理想、有热情、主动的学子报考我的博士/硕士研究生，与我一起奋斗、共同进步。
优秀博士生在读期间均有与世界知名大学长/短期交流访问的机会！！！
招生专业为 “人工智能交叉研究方向”， “计算机应用技术”，“模式识别与智能系统”，“电路与系统”。?

具备以下能力之一者优先考虑：
1. 良好的数学基础、热爱编程（Python、MATLAB、C/C++）；
2. 参加过数学建模竞赛、或者程序设计竞赛，并取得较好成绩；
3. 对数据分析、数学建模、算法研究有浓厚兴趣，计算机视觉方面有一定经验（硕士）；
对数据分析、数学建模、算法研究、计算机视觉方面有较丰富的经验（博士）；
4. 具有良好的中英文表达能力（阅读、写作和交流能力）、积极主动的性格、坚韧不拔的毅力。对于博士最好已发表过重要会议或期刊论文。
代为我的研究合作者日本京都大学（世界排名第36）信息学教授每年招收<=3 硕士/博士生。
具体要求：对视觉心理认知具有强烈兴趣；对计算机视觉有丰富经验；211，985毕业；托福成绩100以上；本科生需以第1或2作者发表过CCF B类以上的国际会议或期刊论文，硕士生需以第1或2作者发表过CCF A类国际会议或期刊论文；对日语没有要求，全英文指导。

Profile
Professor Xuefeng Liang
School of Artifical Intelligent

Contact Information
Address: Main Building, Zone II, 419
Email: xliang@xidian.edu.cn
Tel:

Introduction
I am currently with the School of Artificial Intelligence, Xidian University, China. In general, my research interests are visual perception & cognition, computer vision and intelligent algorithms. I received my Ph.D. from Japan Advanced Institute of Science and Technology in 2006. During the three-year program, I explored computational geometry algorithms on a variety of vision problems. Afterward, I moved to National Institute of Advanced Industrial Science and Technology at Tsukuba, and worked on robotics vision. From 2008, I simultaneously worked at University College London & Queen Mary University of London for the research of visual perception on motion. From 2010, I was assigned as Associate Professor at Graduate School of Informatics, Kyoto University. In 2018, I joined Xidian University.

News
Our paper “CALLip: Lipreading using Contrastive and Attribute Learning"has been accepted by ACMMM2021,Congratulations, my student!
The 9th International Conference on Information Technology: IoT and Smart City, ICIT 2021willtake place in Guangzhou, China.
Our paper “Progressive Co-teaching for Ambiguous Speech Emotion Recognition” has been accepted by ICASSP2020,Congratulations, my students!
Our paper``Element-wise Feature Relation Learning Network for Cross-Spectral Image Patch Matching'', has been accepted byIEEE Trans. on Neural Networks and Learning Systems, IF(8.793).
My collaboratingresearch with Kyoto University"Putative Ratios of Facial Attractiveness in a Deep Neural Network" has been accepted byVision Research. It is one of my representative works in recent years. [Link]
I serve as the conference chair ofThe 8th International Conference on Information Technology: IoT and Smart City, ICIT 2020willtake place onDecember 25-27, 2020inXi'an, China.
Our paper “Jointly Discriminating and Frequent Visual Representation Mining” has been accepted by ACCV2020,Congratulations, my students!
Our paper “UAV Autonomous Target Search Based on Deep Reinforcement Learning in Complex Disaster Scene”has been accepted byIEEE ACCESS, IF(4.098), 2019.
Our two papers have been accepted byICCV2019，where"AFD-Net: Aggregated Feature Difference Learning for Cross-Spectral Image Patch Matching" is accepted as Oral, Congratulations, my students! (Oral ratio4.3%)
Our two papers have been accepted byThe 26^thIEEE International Conference on Image Processing (ICIP 2019) !!
Our paper “Face Super-resolution via Bil[ant]ayer Contextual Representation” has been accepted bySignal Processing: Image Communication (ELSEVIER), IF(2.814), 2019.
Our paper “Wide or Narrow? A Visual Attention Inspired Model for View-Type Classification” has been accepted byIEEE ACCESS, IF(4.098), 2019.[Link]
Our paper “Low-light image enhancement using Gaussian Process for features retrieval” has been accepted bySignal Processing: Image Communication (ELSEVIER), IF(2.814), 2019. [Link]
Our paper “Cross-spectral Image Patch Matching by Learning Features of the Spatially Connected Patches in a Shared Space” has been accepted by ACCV 2018! (Testing Code)
We organize a special issue “The Deep Learning in Computational Photography” in Signal Processing: Image Communication (ELSEVIER).
Our paper "An External Learning Assisted Self-examples Learning for Image Super-resolution" has been accepted by Neurocomputing (ELSEVIER), IF(4.072). [Link]
We orgnize a workshop "Interpretable & Reasonable Deep Learning and its Applications (IReDLiA)" in conjunction with IJCAI-ECAI 2018.
I received an academic Award of Governors of Kyoto Prefecture, Japan.
I serve as an expert advisor for the Chinese AI Research Association (Japan).

Academic Events Orgnization
The 7th International Conference on Information Technology: IoT and Smart City (ICIT 2019),December 20-23, 2019inShanghai, China.
The 2nd International Conference on Data Science and Information Technology, July 19-21, 2019, inSeoul, Korea.
International workshope "Interpretable & Reasonable Deep Learning and its Applications (IReDLiA)" in conjunction with IJCAI-ECAI 2018.
International Conference on Video and Image Processing. December 27-29, 2017, at Nanyang Technological University.
Kyoto University & Queen Mary University of London Joint Workshop, Intelligent Sensing on Media Data. March 26~27, 2015, at Kyoto University.
Kyoto University & University College London Workshop on Perception of Motion and Pattern. March 12, 2013, at Kyoto University.
Kyoto University & Queen Mary University of London Symposium on Intelligent Sensing. March 18~20, 2013, at Kyoto University.

Talks
"Learning Features for Image Patch Matching", Southern University of Science and Technology, Oct. 2019, Shenzhen, China.
"View Angles may Reveal Your Mood: A psychological explanation and an example in the real world"，Tsinghua University, Institute for Interdisciplinary Information Science, May, 2019, Beijing, China.
"View Angles may Reveal Your Mood: A psychological explanation and an example in the real world", International Conference of Union of Mathematical Imaging (UMI2019), May, 2019, Beijing, China.
"Learning the Shared Feature from Cross Domains for Vision Applications & Tackling Data Issues in the Real World Scenario", @ International Conference on Information Technology, HongKong, (Dec. 2018).
"Happier Mood Trigger Bigger Pictures", @ International Workshop on Bio-inspired Systems, Bio-electronics, Machine Intelligence, Taiwan, (Jan, 2018). [Link]
"Viewing Bigger Pictures Promotes Happier Mood: a psychological explanation and an example in the wild", @ International Conference on Video and Image Processing, Singapore, (Dec. 2017). [Link]
"Visual Attention and Emotion", @ The 19th Academic Symposium of the Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, China, (Oct. 2017). [Link]
"Studying Visual Attention in Image and Video", @ The 9th International Conference on Intelligent Robotics and Applications (Aug. 2016). [Link]
"Modeling visual attention in image and video", @ Kyoto-Bordeaux mini-symposium, Japan (Feb. 2016).
"How does Robot Understand the Visual Motion?", @ AcademicDay, Japan (Oct. 2015)
"Motion Segmentation in Complex Video", @ Tianjin University, China (Aug. 2015).
"Dynamic saliency detection", @ Xi\\\\\\\\\\'dian University, China (Jul. 2014).
"Salient Motion Detection from Complex Video using Potential Surface", @ Seoul National University, Korea (Sept.2013).
"Salient Information, from Static to Dynamic", @ National TsingHua University, Taiwan (Mar. 2013).

Research
Xidian University Start Up grant PI 2018 ~ 2021
JSPS Grants-in-Aid for Science Research C, PI 2015 ~ 2017
JSPS Grant-in-Aid for Young Scientists B, PI 2013 ~ 2015
International Exchanges Scheme (Royal Society, UK), Joint, PI: Prof. Peter McOwan, Queen Mary University of London, 2012 ~ 2013

Papers
Books
Modern Neural Network, S.Y. Yang, L.C. Jiao, M.K. Liu, J.Zhao, F. Liu, X.F. Liang, Xidian University Press, 2019.
Journal Papers
Y.H. Cui, F. Liu, L.C. Jiao, Y.W. Guo, X.F. Liang, L.L. Li, S.Y. Yang, X.X. Qian, "Polarimetric Multipath Convolutional Neural Network for PolSAR Image Classification", IEEE Trans. on Geoscience and Remote Sensing, May. 2021. doi: 10.1109/TGRS.2021.**, IF(5.855).
D. Quan, S. Wang, N. Huyan, J. Chanussot, R.J. Wang, X.F. Liang, B. Hou, L.C. Jiao, ``Element-wise Feature Relation Learning Network for Cross-Spectral Image Patch Matching'', IEEE Trans. on Neural Networks and Learning Systems, Jan. 2021. doi: 10.1109/TNNLS.2021.**, IF(8.793).
S. Tong, X.F. Liang, T. Kumada, S. Iwaki,"Putative Ratios of Facial Attractiveness in a Deep Neural Network",Vision Research, Vol. 178, pp. 86-99, Jan. 2021.IF(2.610) [Link]
C.X. Wu, B.B. Ju, Y. Wu, X. Lin, N. Xiong, G.Q. Xu, X.F. Liang, “UAV Autonomous Target Search Based on Deep Reinforcement Learning in Complex Disaster Scene”, IEEE ACCESS, Vol. 7, Issue 1, pp. 117227-117245, Dec.2019. IF(4.098)
K.L. Zeng, T. Lu, X.F. Liang, K. Liu, H. Chen, Y.D. Zhang, “Face Super-resolution via Bilayer Contextual Representation”, has been accepted bySignal Processing: Image Communication (ELSEVIER), Vol.75, pp. 147-157, July 2019.IF(2.814)
S. Tong, Y.P. Loh, X.F. Liang, T. Kumada, “Wide or Narrow? A Visual Attention Inspired Model for View-Type Classification”, IEEE ACCESS, Vol. 7, pp.48725- 48738, April, 2019.IF(4.098)
Y.P. Loh,X.F. Liang, C.S. Chan, "Low-light image enhancement using Gaussian Process for features retrieval" Signal Processing: Image Communication(ELSEVIER),Vol.74, pp. 175-190, May 2019. IF(2.814).
B. Yue, S. Wang,X.F. Liang, L.C. Jiao,"An External Learning Assisted Self-examples Learning for Image Super-resolution",Neurocomputing (ELSEVIER),Vol.312, No.27, pp. 107-119, Oct. 2018.IF(4.072).
S. Wang, D. Quan,X.F. Liang, M.D. Ning, Y.H. Guo, L.C. Jiao,“A Deep Learning Framework for Remote Sensing Image Registration”，ISPRS Journal of Photogrammetry and Remote Sensing (ELSEVIER),Vol. 145 A, pp. 148-164,Nov. 2018. IF(6.942).
S. Wang, B. Yue,X.F. Liang, L.C. Jiao,“How does the Low-Rank Matrix Decomposition Help Internal and External Learnings for Super-Resolution”,IEEE Transactions on Image Processing,Vol. 27, No. 3, pp. 1086-1099, Nov. 2017.(IF 6.79).
B. Yue, S. Wang,X.F. Liang, L.C. Jiao, “Robust coupled dictionary learning with ?1-norm coefficients transition constraint for noisy image super-resolution”,Signal Processing (ELSEVIER), Vol. 140, pp.177–189, Apr. 2017. (IF 4.086)
R. Iseki, S. Kajima, X. Zhao, X.F. Liang, S. Tsujimoto, “The Role of Presenter Actions in the Evaluation of Oral Presentations: Evidence from fMRI and Motion-Vector Analysis”,Psychologia, Vol. 59, No.4, Nov. 2016.
B. Yue, S. Wang,X.F. Liang, L.C. Jiao, C.J. Xu,“Joint Prior Learning for Visual Sensor Network Noisy Image Super-Resolution”,Sensors, Vol. 16, No. 3, pii. 288, Mar. 2016. (IF 3.031)
X.F. Liang, C.C. Zhang, T. Matsuyama, “A General Inlier Estimation for Moving Camera Motion Segmentation”,IPSJ Transactions on Computer Vision and Applications,Vol. 7, pp. 163 ~ 174, Dec. 2015. (Invited paper)
C.C. Zhang,X.F. Liang, T. Matsuyama, “Generic Learning based Ensemble Framework for Small Sample Size Face Recognition in Multi-Camera Networks”,Sensors, Vol. 14, No. 12, pp. 23509 ~ 23538, Dec. 2014. (IF 3.031)
C.C. Zhang,X.F. Liang, T. Matsuyama, “Mixed-Motion Segmentation using Helmholtz Decomposition”,IPSJ Transactions on Computer Vision and Applications,Vol. 5, pp. 55-59, 2013. (Invited paper)
X.F. Liang, P.W. McOwan, A. Johnston, “A Biologically Inspired Framework for Spatial and Spectral Velocity Estimations”,Journal of the Optical Society of America A, JOSA A., Vol. 28, Issue 4, pp. 713-723, Apr. 2011. (IF 1.861)
N.X. Xiong, L.T. Yang, J.H. Park,X.F. Liang, T.H. Kim, “Towards a Performance-based Resource Server Control in Grid Computing Environments”,Wireless Personal Communications(Springer), Vol. 51, No. 1, pp. 209-220, Oct. 2009.(IF 1.200)
K. Ohara, T. Sugawara, J.H. Lee, T. Tomizawa, H.M. Do,X.F. Liang, Y.S. Kim. B.K. Kim, Y. Sumi, T. Tanikawa. K. Ohba, “Visual Mark for Robot Manipulation and Its RT Middleware Component”,Advanced Robotics, Vol. 22, No. 6, pp. 633-655, 2008.(IF 1.104)
X.F. Liang, N.X. Xiong, L.T. Yang, H. Zhang, J.H. Park, “A Compensation Scheme of Fingerprint Distortion using Combined Radial Basis Function Model for Ubiquitous Services”,Computer Communications, Vol. 31, No. 18, pp. 4360-4366, Dec. 2008.(IF 2.766)
X.F. Liang, A. Bishnu, T. Asano, “A Robust Fingerprint Indexing Scheme Using Minutia Neighborhood Structure and Low-order Delaunay Triangle”,IEEE Trans. on Information Forensics and Security, Vol. 2, No. 4, pp. 721-733, Dec. 2007. (IF 6.211)
X.F. Liang, A. Bishnu, T. Asano, “A Combinatorial Approach to Fingerprint Binarization and Minutiae Extraction Using Euclidean Distance Transform”,International Journal of Pattern Recognition and Artificial Intelligence, Vol. 21, No. 7, pp. 1141-1158, Nov. 2007.
X.F. Liang, T. Asano, “A Linear Time Algorithm for Binary Fingerprint Image Denoising using Distance Transform”,IEICE Trans. on INF. & SYST., Vol.E89-D, No. 4, pp. 1534–1542, April 2006.(IF 1.11)
X.F. Liang, F. Liu, “A SVM Algorithm Based on Linear Combinatorial Kernels”, Computer Science, Vol. 29, pp. 361–363, 2002. (In Chinese)
X.F. Liang, F. Liu, “A SVM Algorithm Based on the minimal Support Vector Set”, Journal of Xidian University, Vol. 29, 2002. (In Chinese)
International Conferences
Y.Y. Huang, X.F. Liang,C.W. Fang, "CALLip: Lipreading using Contrastive and Attribute Learning", Proc. the 29th ACM International Conference on Multimedia (ACMMM 2021), Chengdu, China, October, 2021.
Y.F Yin, Y.Gu, L.S. Yao, Y. Zhou, X.F.Liang, H. Zhang,"Progressive Co-teaching for Ambiguous Speech Emotion Recognition", Proc. Intl. Conf. on Acoustics, Speech and Signal Processing(ICASSP 2021), Toronto, Canada, June, 2021.
Q.N. Wang, Y. Zhou, Z.Y. Zhu, X.F. Liang, Yu. Gu, "Jointly Discriminating and Frequent Visual Representation Mining",Proc. Asian Conf. on Computer Vision(ACCV 2020), Kyoto, Japan, November, 2020.
Q.N. Wang, Z.Y. Zhu, X.F. Liang, H.W. Shi, P. Cao, "Deep Relevance Feature Clustering for Discovering Visual Representation of Tourism Destination", Proc. Chinese Conf. on Pattern Recognition and Computer Vision (PRCV 2020), Nanjing, China, October, 2020.
D. Quan, X.F. Liang, S. Wang, S.W. Wei, Y.F. Li, N. Huyan, L.C. Jiao, "AFD-Net: Aggregated Feature Difference Learning for Cross-Spectral Image Patch Matching",ICCV2019 (Oral Presentation, Acceptance rate: 4.3%), Seoul, Korea, October, 2019.
S. Wang, Y.F. Li, X.F. Liang, D. Quan, B.W. Yang, S.W. Wei, L.C. Jiao,"Better and Faster: Exponential Loss for Image Patch Matching",ICCV2019, Seoul, Korea, October, 2019.
X.F. Liang, S. Tong, T. Kumada, S. Iwaki, “Golden Ratio: The Attributes of Facial Attractiveness Learned by CNN”, Proc. Intl. Conf. on Image Processing (ICIP 2019), Taipei, Taiwan, September, 2019.
Y. Liu, X.F. Liang, S. Tong, T. Kumada, “Photo Shot-type Disambiguation by Multi-Classifier Semi-supervised Learning”, Proc. Intl. Conf. on Image Processing (ICIP 2019), Taipei, Taiwan, September, 2019.
X.F. Liang, S. Tong, T. Kumada, Y.P. Loh, "Understanding the Photo-shooting Patterns of Sightseeing", Proc. Intl. Conf. on Data Science and Information Technology Proceedings (DSIT 2019), Seoul, Korea, July, 2019.
S. Wang, L.G. Zhou, P. He, D. Quan, Q. Zhao, X.F. Liang, B. Hou, “An Improved Fully Convolutional Network for Learning Rich Building Features”, Proc. IEEE Intl. Geoscience and Remote Sensing Symposium (IGARSS 2019), Yokohama, Japan, July, 2019.
D. Quan, S. Fang, X.F. Liang,S. Wang, L.C. Jiao,"Cross-spectral Image Patch Matching by Learning Features of the Spatially Connected Patches in a Shared Space” Proc.14th Asian Conf. on Computer Vision (ACCV 2018), Perth, Australia, Dec, 2018.
D. Quan, S. Wang, X.F. Liang, R.J. Wang, S. Fang, B. Hou, L.C. Jiao, "Deep Generative Matching Network for Optical and SAR Image Registration'',Proc. IEEE Intl. Geoscience and Remote Sensing Symposium (IGARSS 2018),(Oral presentation), Valencia, Spain, July, 2018.
Y.P. Loh, S. Tong, X.F. Liang, T. Kumada, C.S. Chan, “Understanding Scenery Quality: A Visual Attention Measure and Its Computational Model”,ICCV2017Workshop on VSM: Web-Scale Vision and Social Media, Venice, Italy, October, 2017.
S. Tong, X.F. Liang, T. Kumada, S. Iwaki, “Learning the Cultural Consistent Facial Aesthetics by Convolutional Neural Network”,Proc. Intl. Conf. on Culture and Computing (ICCC 2017),(Oral presentation, Best paper candidate),Kyoto, Japan, September, 2017.
Z. Wang, S. Wang, C.J. Xu, C.Y. Li, B. Yue, X.F. Liang, “SAR Images Super-Resolution via Cartoon-Texture Image Decomposition and Jointly Optimized Regressors”,IEEE Intl. Geoscience and Remote Sensing Symposium (IGARSS 2017),Texas, USA, July, 2017.
B. Yue, S. Wang, X.F. Liang, L.C. Jiao, “Robust Noisy Image Super-Resolution using L1-norm Regularization and Non-local Constraint”,ACCV 2016 Workshop on NTIRE: New Trends in Image Restoration and Enhancement,(Oral presentation),Taipei, Taiwan, November, 2016.
S. Tong, Y.P. Loh, X.F. Liang, T. Kumada, “Visual Attention Inspired Distant View and Close-Up View Classification”,Proc. Intl. Conf. on Image Processing (ICIP 2016), Phoenix, USA, September, 2016.
S. Wang, S.P. Lin, X.F. Liang, B. Yue, L.C. Jiao, “External And Internal Learning For Single-Image Super-Resolution”,Proc. Intl. Conf. on Image Processing (ICIP 2015), Quebec, Canada, September, 2015.
C.Y. Zhuang, Q. Ma, X.F. Liang, M. Yoshikawa, “Discovering Obscure Sightseeing Spots by Analysis of Geo-tagged Social Images”,Proc. Intl. Conf. on Advances in Social Network Analysis and Mining (ASONAM 2015), Paris, France, August, 2015.
C.C. Zhang, X.F. Liang, X. Xiong, “Decision-Tree Based Hybrid Filter-Wrapping Method for Optimal Combination of Multiple Feature Sets”,Proc. 8th Intl. Conf. on Image and Graphics (ICIG 2015), Tianjin, China, August, 2015.
C.C. Zhang, X.F. Liang, T. Matsuyama, “Multi-Depth Deep Feature Learning for Face Recognition”,Proc. Intl. Conf. on Informatics, Networking and Intelligent Computing (INIC 2014), Shenzhen, China, November, 2014.
X.F. Liang, C.C. Zhang, T. Matsuyama, “Inlier Estimation for Moving Camera Motion Segmentation”,Proc. 12th Asian Conf. on Computer Vision (ACCV 2014),(Oral presentation, Acceptance rate: 3.8%), Singapore, November, 2014.
C.Y. Zhuang, Q. Ma, X.F. Liang, M. Yoshikawa, “Anaba: An Obscure Sightseeing Spots Discovering System”,Proc. IEEE Intl. Conf. on Multimedia and Expo (ICME 2014), Chengdu, China, July, 2014.
X.F. Liang, “Minutia Detail in Fingerprint Indexing”,Proc. 20th Korea-Japan Joint Workshop on Frontiers of Computer Vision (FCV 2014), Okinawa, Japan, February, 2014.
X.F. Liang, Xiangjun Li, “Intelligent Camera Network using Multi-functional Middleware”,Proc. 20th Korea-Japan Joint Workshop on Frontiers of Computer Vision (FCV 2014), Okinawa, Japan, February, 2014.
C.C. Zhang, X.F. Liang, T. Matsuyama, “Small Sample Size Face Recognition using Random Quad-Tree based Ensemble Algorithm”,Proc. The 5th International Conference on Imaging for Crime Detection and Prevention (ICDP 2013), London, UK, December, 2013.
C.C. Zhang, X.F. Liang, T. Matsuyama, “Mixed-Motion Segmentation using Helmholtz Decomposition”,Proc. 16th Meeting on Image Recognition and Understanding(MIRU 2013),Outstanding Paper Award, Tokyo, Japan, August, 2013.
C.C. Zhang, X.F. Liang, T. Matsuyama, “Multi-subregion Face Recognition using Coarse-to-fine Quad-tree Decomposition”,Proc. 21st Intl. Conf. on Pattern Recognition,(Oral presentation, Acceptance rate: 15%), Tsukuba, Japan, Nov. 2012.
C.C. Zhang, X.F. Liang, “A Minimum-Computational-Cost Method for the Parameterization of Quadric Surfaces”,Proc. The Computer Graphics International, Ottawa, Canada, June, 2011.
X.F. Liang, P. W. McOwan, A. Johnston, “A Color Neuromorphic Approach for Motion Estimation”,Proc. IEEE Winter Vision Meetings, Workshop on Motion and Video Computing, pp. 49–54, Snowbird Utah, USA, December, 2009.
X.F. Liang, Y. Sumi, B.K. Kim, H.M. Do, Y.S. Kim, T. Tomizawa, K. Ohara, T. Tanikawa, K. Ohba, “A Camera Array with Flexible Software Architecture in Intelligent Space”,IEEE/ASME Intl. Conf. on Advanced Intelligent Mechatronics2008 (Accepted).
X.F. Liang, Y. Sumi, B.K. Kim, H.M. Do, Y.S. Kim, T. Tomizawa, K. Ohara, T. Tanikawa, K. Ohba, “A Large Planar Camera Array for Multiple Automated Guided Vehicles Localization”,Proc. IEEE/ASME Intl. Conf. on Advanced Intelligent Mechatronics, pp. 608–613, Xian, China, July, 2008.
X.F. Liang, T. Tomizawa, H.M. Do, Y.S. Kim, K. Ohara, B.K. Kim, T. Tanikawa, K. Ohba, “Multiple Robots Localization Using Large Planar Camera Array for Automated Guided Vehicle System”,Proc. IEEE Intl. Conf. on Information and Automation, pp. 984–990, Zhangjiajie, China, June, 2008.
X.F. Liang, T. Tomizawa, J.H. Lee, H.M. Do, Y.S. Kim, K. Ohara, B.K. Kim, T. Tanikawa, K. Ohba, “Large Camera Array System for Real Time Surveillance”,ACCV’07 Workshop on Multi-dimensional and Multi-view Image Processing, Tokyo, Japan, September, 2007.
T.Tomizawa, K.Ohara, T.Sugawara, H.Onda, J.H.Lee, X.F. Liang, H.M.Do, Y.S.Kim, B.K.Kim, T.Tanikawa, K.Ohba, T.Sonoyama, “Introduction to Ubiquitous Space Related Japan Science and Technology Agency Projects at AIST”,IROS 2007, Workshop on Ubiquitous Robotic Space Design and Applications, San Diego, November, 2007.
H.M. Do, B.K. Kim, Y.S. Kim, J.H. Lee, K. Ohara, T. Sugawara, T. Tomizawa, X.F. Liang, T. Tanikawa, K. Ohba, “Development of Simulation Framework for Ubiquitous Robots Using RT-Middleware”,Proc. Intl. Conf. on Control, Automation and Systems, pp. 2483z2486, Korea, October, 2007.
Y.S. Kim, J.H. Lee, B.K. Kim, H.M. Do, T. Tomizawa, K. Ohba, X.F. Liang, K. Ohara, T. Sugawara, and T. Tanikawa, “Localization of Ubiquitous Environment Based Mobile Robot”,Proc. Intl. Conf. on Control, Automation and Systems, pp. 2355–2358, Korea, October, 2007.
X.F. Liang, T. Asano, H. Zhang, “A Combined RBF Model for Fingerprint Distortion”,Proc. 3rd Intl. Conf. on Image Analysis and Recognition (ICIAR 2006), Povoa de Varzim, Portugal, Lecture Notes in Computer Science LNCS 4142, edited by A. Campilho and M. Kamel, “Image Analysis and Recognition”, pp. 286–296, September, 2006.
X.F. Liang, A. Bishnu, T. Asano, “Fingerprint Matching Using Minutiae Polygons”,Proc. 18th Intl. Conf. on Pattern Recognition(ICPR 2006),(Oral presentation, Acceptance rate: 15%), pp. 1046–1049, HongKong, China, August, 2006.
X.F. Liang, A. Bishnu, T. Asano, “Distorted Fingerprint Indexing Using Delaunay Triangle and Minutiae Detail”,Proc. 3rd Intl. Sym. on Voronoi Diagrams in Science and Engineering(ISVD 2006), pp. 217–224, Banff, Canada, July, 2006.
H. Zhang, T.B. Ho, M.S. Lin, X.F. Liang, “Feature Extraction for Time Series Classification Using Discriminating Wavelet Coefficients”,Proc. 3rd Intl. Sym. on Neural Networks(ISNN06), Lecture Notes in Computer Science LNCS 3971–1394, pp. 1394–1399, Chengdu, China, May, 2006.
X.F. Liang, K. Kotani, T. Asano, “Automatically Choosing Appropriately-Sized Structuring Elements to Eliminate Useless Components in Fingerprint Image”,Proc. Visual communications and Image Processing2005 (Proc. Of SPIE, Vol. 5960), pp. 284–293, Beijing, China, July, 2005.
X.F. Liang, A. Bishnu, T. Asano, “A near-linear time algorithm for binarization of fingerprint images using distance transforms”,Proc. 10th Intl. Workshop on Combinatorial Image Analysis, Lecture Notes in Computer Science LNCS 3322, edited by R. Klette and J. Zunic, Combinatorial Image Analysis, pp. 197–208, Auckland, December, 2004.
X.F. Liang, T. Asano, “A fast denoising method for binary fingerprint image”,Proc. IASTED Conf. on Visualization, Imaging, and Image Processing, pp. 309–313, Marbella, Spain, September, 2004.
X.F. Liang, F. Liu, “Choosing Multiple Parameters for SVM Based on Genetic Algorithm”,Proc. 6th Intl. Conf. on Signal Processing, pp. 117–119, Beijing, China, August, 2002.
Japanese Papers
S. Tong,X.F. Liang, “The Distant View and Close-up View Classification using DWT and PCANet”, Proc. 18th Meeting on Image Recognition and Understanding (MIRU 2015), Osaka, Japan, July, 2015.
C.Y. Zhuang, Q. Ma,X.F. Liang, M. Yoshikawa, “Discover Anaba Sightseeing Spots using Social Images”,情報処理学会データベースシステム（DBS）研究会, July, 2013.
菅原隆行,大原賢一,李在勲,冨沢哲雄, KIM YONG-SHIK,梁雪峰, Do Hyun Min,金奉根,音田弘,谷川民生,角保志,園山隆輔,大場光太郎, “ロボットの作業を支援するための物理的環境構造化に関する研究”,第8回システムインテグレーション部門講演会(SI2007), Dec. 2007.
金奉根,梁雪峰, Do Hyun Min, KIM YONG-SHIK,李在勲,冨沢哲雄,大原賢一,谷川民生,大場光太郎, “Task Oriented Planning Algorithm for Multiple Mobile Robots in the Ubiquitous Robot Technology Space”,第8回システムインテグレーション部門講演会(SI2007),Dec. 2007.
KIM YONG-SHIK,李在勲,金奉根, Do Hyun Min,冨沢哲雄,梁雪峰,谷川民生,大場光太郎, “Localization of Mobile Robot in Ubiquitous Environment”, SICE SI 2007,Dec. 2007.
大原賢一,菅原隆行,李在勲,冨沢哲雄,梁雪峰, Do Hyun Min,金容稙,金奉根,角保志,谷川民生,音田弘,園山隆輔,大場光太郎, “人間とロボットの共存環境におけるビジュアルマークの提案”, SICE SI 2007,Dec. 2007.
Do Hyun Min,金奉根,冨沢哲雄, KIM YONG-SHIK,李在勲,梁雪峰,谷川民生,大場光太郎, “Coordination of Multiple Mobile Robots with Distributed Sensors in Ubiquitous Environment”, SICE SI2007,Dec. 2007.

Honors
Shaanxi, Thousand Talents Program (Long term),2018.
Award of Governors of Kyoto Prefecture, Kyoto, Japan, November, 2017.
Recognition Award: X.F. Liang, at the 9th Int. Conf. on Intelligent Robotics and Applications, Tokyo, Japan, August, 2016.
Outstanding Paper Award: C.C. Zhang, X.F. Liang, T. Matsuyama, "Mixed-Motion Segmentation using Helmholtz Decomposition" at the 16th Meeting on Image Recognition and Understanding, Tokyo, Japan, August, 2013.
Outstanding Research Award: C.C. Zhang, X.F. Liang, T. Matsuyama, "What are you looking for on faces？" at Kyoto University ICT innovation 2013.

Team
Current Students
Song Tong D4 Aug. 2015 ~ . @Kyoto University
Ran Wang M2 April, 2018 ~ . @Kyoto University
Zhou Ying M1 Sept., 2018~ . @Xidian University
Wang QianNan M1 Sept., 2018~ . @Xidian University
Zhu ZhaoYan M1 Sept., 2018~ . @Xidian University

Graduated Students
Yang Liu @Kyoto University (PhD student) 2016 ~ 2018
Xiangyue Zhao @ Google Japan (R&D) 2016 ~ 2018
ZhengAn Zhu @ National Chung Cheng University Aug. ~ Oct. 2017 (visiting student, D1)
YuenPeng Loh @ University of Malaya.(Lecturer) Dec. 2015 ~ Jun. 2016 (visiting student, D2)
Cuicui Zhang @ Tianjin University, China (Lecturer) Ph.D. 2012 ~ 2015

Teaching
Current Teaching
1. Cognitive Science in AI for Graduate Students
2. The Math in AI for Graduate Students
3. Cognitive Computing for Undergraduate and Graduate Students
4. ScientificInformation Literacy for UndergraduateStudents
Past Teaching
Fundamentals of Machine Vision 2014 ~ 2018, @Kyoto Univ.
Information Literacy for Academic Study 2014 ~ 2018, @Kyoto Univ.
Pattern Recognition (Advanced), 2011 ~ 2018, @Kyoto Univ.
Computer Vision, 2010 ~ 2017, @Kyoto Univ.
Advanced Approaches in Machine Vision, 2011 ~ 2013, @Kyoto Univ.
Introduction to Information Science, 2010 ~ 2014, @Kyoto Univ.
Computer Graphics LEC (DCS314) 2009 ~ 2010, @Queen Mary Univ. of London.

Admission
I welcome intelligent students, who have interests in visual perception, cognition, and computer vision, to join our Ph.D/Master programs.
There are a few vacant positions, especially for Ph.D applicants.
Applicants should be good at
1. Math, Programming (Python, Matlab, C/C++).
2. Reading, Scientific writing, Team work.