中科院计算所视觉信息处理与学习组
中科院计算所视觉信息处理与学习组
李亮

职 称:副研究员

研究方向:计算机视觉、多媒体内容分析、跨媒体智能

 李亮,1986年出生,博士,副研究员。主要从事多媒体内容分析、计算机视觉和跨媒体智能等方面的研究,在计算机视觉和多媒体领域的国际顶级期刊和会议IEEE TMM, IEEE TNNLS, IEEE CVPR, IJCAI, DCC, ACM Multimedia等上发表和录用论文40余篇,获国际会议最佳论文奖1次, ESI高被引文章1篇,编写译著1部。是IEEE会员、ACM会员、CCF和CAAI会员,担任多个国际学术会议的组织委员会成员。获2017年计算所“学术百星”、2015年 ACM ICIMCS杰出服务奖、2014年Gamenets最佳论文奖、2013年中科院院长优秀奖、2012年计算所所长特别奖等。

学术服务
刊物服务
  • Multimedia Technology and Application (MTAP) 客座编辑
  • IEEE TIP, IEEE TNNLS, IEEE TMM, IEEE CSVT, IEEE T-SMC, PR, Neurocomputing, JVCIR, MTAP等国际期刊审稿人
会议服务
  • IEEE GlobalSIP2017 Symposium of Knowledge-based Multimedia Computing, General Co-chair
  • International Conference on Internet Multimedia Computing and Service (ICIMCS) 2017 Special Session Chair
  • Pacific Rim Conference on Multimedia (PCM) 2017 Local Chair
  • International Conference on Internet Multimedia Computing and Service (ICIMCS) 2015 Orginazating Chair
  • IEEE TMM, IEEE TSMC, PR, Neurocomputing, ACM Multimedia, CVPR, ICME, ICIP, ICIMCS, PCM等国际期刊和会议审稿人
经历
教育经历
  • 2008.9~2013.6 中国科学院计算技术研究所 中科院智能信息处理重点实验室 计算机应用技术专业 工学博士
  • 2004.9~2008.7 西安交通大学 信息工程专业
学术经历
  • ACM SIGMM China Chapter高校合作联系人
科研项目

1.   面向高层语义的跨媒体特征表达机制研究

项目类型:国家自然科学基金面上项目
项目时间:2017.1-2020.12
项目负责人:李亮

2.   基于多任务稀疏特征学习的海量图像理解方法研究

项目类型:国家自然科学基金青年基金
项目时间:2015.01-2017.12
项目负责人:李亮

3.   基于深度学习和多任务稀疏特征的海量图像理解方法

项目类型:中国博士后科学基金特别资助
项目时间:2014.06-2015.12
项目负责人:李亮

4.   基于混合范式正则化的海量图像理解方法

项目类型:中国博士后科学基金面上一等资助
项目时间:2013.10-2015.07
项目负责人:李亮
著论

著作

1.   《CUDA C编程权威指南》【美】 John Cheng, Max Grossman, Ty McKercher 著. 颜成钢,殷建,李亮 译. 北京:机械工业出版社,2017年6月. ISBN:9787111565475 【pdf】

论文

[1] Shijie Yang, Liang Li, Shuhui Wang, Weigang Zhang and Qingming Huang, A Graph Regularized Deep Neural Network for Unsupervised Image Representation Learning, IEEE CVPR 2017 
[2] Xinge Zhu, Liang Li, Weigang Zhang, Tianrong Rao, Min Xu, Qingming Huang, Dong Xu, Dependency Exploitation: A Unified CNN-RNN Approach for Visual Emotion Recognition, IJCAI 2017 
[3] Chunjie Zhang, Jian Cheng, Liang Li, Changsheng Li, Qi Tian, Object Categorization Using class-specific Representations, IEEE TNNLS, 2017 
[4] Liang Li, Chenggang Yan, Xin Chen, Chunjie Zhang, Jian Yin, Baochen Jiang, Qingming Huang. Distributed image understanding with semantic dictionary and semantic expansion. Neurocomputing2016 
[5] Liang Li, Wen Ji, Shuqiang Jiang, Qingming Huang. LSH-based semantic dictionary learning for large scale image understanding. JVCIR2015 
[6] Liang Li, Chenggang Yan, Xing Chen, Bo Wu, Shuqiang Jiang, Seungmin Rho, Jian Yin, Baochen Jiang and Qingming Huang. Large scale image understanding with non-convex multi-task learning, 5th International Conference on Game Theory for Networks 2014 
[7] Liang Li, Shuqiang Jiang, Zheng-Jun Zha, Zhipeng Wu and Qingming Huang, Partial-Duplicate Image Retrieval via Saliency-guided Visually Matching, IEEE Multimedia 2013 
[8] Liang Li, Shuqiang Jiang and Qingming Huang, Learning hierarchical semantic description via mixed-norm regularization for image understanding, IEEE TMM2012 
[9] Liang Li, Shuqiang Jiang and Qingming Huang, Learning Vicept Description via Mixed-Norm Regularization for Large-scale Semantic Image Search, IEEE CVPR2011 
[10] Liang Li, Zhipeng Wu, Zheng-Jun Zha, Shuqiang, Matching Content-based Saliency Region for Partial Duplicate Image Detection, IEEE ICME2011 
[11] Liang Li, Shuqiang Jiang and Qingming Huang, Online Vicept Extension for Web-scale Image Understanding, IEEE ICIP2011 
[12] Liang Li, S. Jiang and Q. Huang, Multi-description of local interest point for partial duplicate image retrieval, IEEE ICIP10 
[13] Xingjie Yu, Zhan Wang, Yingjiu Li, Liang Li, Wentao Zhu, Li Song. EvoPass: evolvable graphical password against shoulder-surfing attacks. Elsevier Computers & Security 2017. 
[14] Binbin Lv, Liang Li and Chenggang Yan, 3D Laser Scanning under the Pin-hole Camera with Lens Distortion, MVA2017 
[15] Shijie Yang, Liang Li, Shuhui Wang, Weigang Zhang and Qingming Huang, Multi-view Subspace Learning with Diversity Enforced Skeleton Embedding, IEEE Bigmm 2017 
[16] Minfeng Zhan, Liang Li, Qingming Huang, Cross-media Retrieval with Semantic Clustering and Enhancement, IEEE ICME 2017 
[17] Hongyang Yu, Lei Qin, Hongxun Yao, Liang Li, Qingming Huang, Online Multi-target Tracking Via Depth Range Segmentation, IEEE GlobalSIP17. 
[18] Chunjie Zhang, Chao Liang, Liang Li, Jing Liu, Qingming Huang, Qi Tian, Fine-grained image classification via low-rank sparse coding with general and class-specific codebooks, IEEE Transactions on Neural Networks and Learning Systems, 2016 
[19] Hongrun Ma, Liang Li, Yongquan Liang, Junpeng Chen and Jian Yin. Efficient virtual network transmission using correlated equilibrium on Xen-based platform, JVCIR2016 
[20] Fei Tao, Junbiao Pang, Chunjie Zhang, Liang Li, Weigang Zhang, Qingming Huang, Guiping Su, Robust Latent Poisson Deconvolution From Multiple Imperfect Features For Web Topic Detection, IEEE ICME 2016 
[21] Zhiyi Wang, Liang Li, Qingming Huang. Cross-media Topic Detection with Refined CNN based Image-Dominant Topic Model, ACM Multimedia2015 
[22] Zhiyi Wang, Liang Li, Chunjie Zhang, Qingming Huang, Image-regulated Graph Topic Model for Cross-media Topic Detection, ACM ICIMCS2015 
[23] Chunjie Zhang, Liang Li, Yifan Zhang, Jing Liu, Qingming Huang, Qi Tian. Joint image representation and classification in random semantic spaces. Neurocomputing 2015 
[24] Chenggang Yan, Liang Li, Shuqiang Jiang, et al.: Fusing multi-cues description for partial-duplicate image retrieval. JVCIR2014
[25] Xinhang Song, Shuqiang Jiang, Shuhui Wang, Liang Li, Qingming Huang . Polysemious Visual Representation Based on Feature Aggregation for Large Scale Image Applications. Multimedia Tools and Application, 2014 
[26] Chenggang Yan, Yongdong Zhang, Jizheng Xu, Feng Dai, Liang Li, Qionghai Dai and Feng Wu, A Highly Parallel Framework for HEVC Coding Unit Partitioning Tree Decision on Many-core Processors, IEEE Signal Process. Lett. 2014 
[27] Zhan Wang, Jiwu Jing and Liang Li, “Time Evolving Graphical Password for Securing Mobile Devices”, ACM Symposium on Information, Computer and Communications Security, Asia CCS2013 
[28] Chenggang Yan, Yongdong Zhang, Feng Dai and Liang Li, Highly Parallel Framework for HEVC Motion Estimation on Many-core Platform, Data Compress Conference, DCC2013 
[29] Zhipeng Wu, Qianqian Xu, Shuqiang Jiang, Qingming Huang, Peng Cui and Liang Li. Adding Affine Invariant Geometric Constraint for Partial Duplicate Image Retrieval, IEEE ICPR2010 
[30] Zhipeng Wu, Shuqiang Jiang, Liang Li, Peng Cui, Qingming Huang and Wen Gao, Vicept: Link Visual Features to Concepts for Large-scale Image Understanding, ACM MM2010 

视觉信息处理和学习组
  • 单位地址:北京海淀区中关村科学院南路6号
  • 邮编:100190
  • 联系电话:010-62600514
  • Email:yi.cheng@vipl.ict.ac.cn
  • Valse

  • 深度学习大讲堂

版权所有 @ 中科院计算所视觉信息处理与学习组 京ICP备05002829号 京公网安备1101080060