兴军亮

中国科学院自动化研究所

浏览次数

55

收藏次数

0

接洽次数

0

  • 兴军亮
  • 副研究员

简 历:

基本信息兴军亮,2012年毕业于清华大学计算机科学与技术系,获工学博士学位,同年进入中国科学院自动化研究所模式识别国家重点实验室工作,现为中国科学院自动化所副研究员,硕士研究生导师。2012年12月至2013年12月期间新加坡国立大学访问研究员,2015年4月至11月微软亚洲研究院网络媒体组“铸星计划”访问教授,美国电器与电子工程学会(IEEE)会员,中国计算机学会(CCF)会员,计算机视觉专委会委员。研究领域为计算机视觉、机器学习和人工智能。目前已在重要国际期刊如TPAMI、IJCV、TIP、TOMM以及重要国际会议上如ICCV、CVPR、ECCV、ACM Multimedia、AAAI上发表论文60多篇,出版计算机视觉译著2部,撰写深度学习著作1部。在攻读博士期间,曾获得清华大学计算机系学术新秀、清华大学优秀博士毕业论文、谷歌学者、清华大学综合一等奖学金等荣誉称号和奖励,带领学生完成的论文“Wow!You Are so Beautiful Today!”获得了2013年多媒体领域重要国际会议ACM Multimedia最佳论文奖。多次获得相关研究方向的国际和国内挑战赛冠军。目前作为项目负责人正在主持国家自然科学基金面上项目一项,作为项目实际负责人和核心骨干参与了973和863等多项国家重要研究课题,以及与惠普、英特尔、欧姆龙、富士通、华为等知名企业的多项合作研究课题。正在承担的研究课题主要包括人脸和人体视觉、网络敏感内容安全和大数据分析应用,关心的研究问题包括物体检测、跟踪和分割、图像识别检索以及大数据分析与建模等,关心的技术模型包括Boosting、支持向量机、稀疏表示和深度学习等。近年来重点围绕深度学习展开了深入的研究,在人工智能最前沿方向进行探索和研究。

研究领域模式识别 计算机视觉 机器学习 人工智能

研究方向物体检测、跟踪、配准、分割和识别 深度学习、强化学习、游戏AI和博弈论

教育背景 2012年12月~2013年12月 新加坡国立大学 电子与计算工程系 博士后研究员 2007年09月~2012年07月 清华大学 计算机科学与技术 工学博士 2003年09月~2007年07月 西安交通大学 计算机、应用数学 工学和理学双学士

工作经历2012年7月~至今 中国科学院自动化研究所模式识别国家重点实验室,先后任助理研究员、副研究员、项目研究员,硕导

专利与奖励 申请和授权专利共计数十项 曾获“谷歌学者”、微软“筑星计划”访问教授、国家重点实验室“优秀员工”等称号 2016年微软百万人脸识别挑战赛分项冠军 2015年全国特定视音频挑战赛检测分项冠军 2013年多媒体领域顶级国际会议ACM MM最佳论文奖

出版信息著作和译著书籍:讲述机器学习中最为重要一些模型机器学习,负责其中四章特别讲述最新深度学习相关模型。 谢剑斌,兴军亮等著,《机器学习二十讲》,清华大学出版社,2015年2月。 译著:两本译著分别为图像处理领域经典教材和计算机视觉领域最新专著。 兴军亮等译,《图像处理、分析与机器视觉(第4版)》,清华大学出版社,2016年1月。 艾海舟,兴军亮等译,《计算机视觉:算法与应用》,清华大学出版社,2012年1月。

期刊论文[1].Junliang Xing, Zhiheng Niu, Junshi Huang, Weiming Hu, Xi Zhou, Shuicheng Yan. Towards Multi-view and Partially-occluded Face Alignment. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), accepted 2017.(模式识别和计算机视觉领域重要国际期刊) [2].Junliang Xing, Weiming Hu, Haizhou Ai, Shuicheng Yan. FatRegion: A Fast, Adaptive, Tree-structured Region Extraction Approach. IEEE Transactions on Circuits, System and Video Technology (TCSVT), accepted 2016. [3].Junliang Xing, Kai Li, Weiming Hu, Chunfeng Yuan, Haibin Ling. Diagnosing Deep Learning Models for High Accuracy Age Estimation from A Single Image. Pattern Recognition (PR), vol. 66, pp. 95-105, 2017. (模式识别领域重要国际期刊) [4].Weiming Hu, Jin Gao, Junliang Xing, Chao Zhang, and Steve Maybank, Semi-Supervised Tensor-Based Graph Embedding Learning and Its Application to Visual Discriminant Tracking, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), accepted, 2016. (模式识别和计算机视觉领域重要国际期刊) [5].Bin Li, Weihua Xiong, Weiming Hu, Brian Funt, and Junliang Xing, Multi-Cue Illumination Estimation via a Tree-Structured Group Joint Sparse Representation, International Journal on Computer Vision (IJCV), vol. 117, no. 1, pp. 21-47, March 2016. (计算机视觉领域重要国际期刊) [6].Luoqi Liu*, Junliang Xing*, Hui Xu, Si Liu, Xi Zhou, Shuicheng Yan. “Wow! You Are So Beautiful Today!” ACM Transactions Multimedia Computing, Communication, and Applications (ACM TOM), 2014. (多媒体领域重要国际期刊) [7].Liwei Liu, Junliang Xing, Haizhou Ai. Scene Transformation for Detector Adaptation. Pattern Recognition Letters (PRL), vol. 36, pp. 154-160. 2014. (模式识别领域重要国际期刊) [8].Junshi Huang, Si Liu, Junliang Xing, Tao Mei, Shuicheng Yan. Circle & Search: Attribute-aware Shoe Retrieval. ACM Transactions Multimedia Computing, Communication, and Applications (ACM TOM), 2014. (多媒体领域重要国际期刊) [9].Genquan Duan, Haizhou Ai, Junliang Xing, Song Cao and Shihong Lao, Scene Aware Detection and Block Assignment Tracking in Crowded Scenes, Image and Vision Computing (IVC), vol. 30, no. 4, pp. 292-305, May, 2012. (图像视觉计算领域重要国际期刊) [10].Junliang Xing, Haizhou Ai, Liwei Liu and Shihong Lao, Multiple Players Tracking in Sports Video: a Dual-Mode Two-Way Bayesian Inference Approach with Progressive Observation Modeling, IEEE Transactions on Image Processing (TIP), vol. 20, no. 6, pp. 1652-67, Jun, 2011. (图像处理领域重要国际期刊) 会议论文 [1].Sijie Song, Cuiling Lan, Junliang Xing, Wenjun Zeng, Jiaying Liu. An end-to-end spatio-temporal attention model for human action recognition from skeleton data. In AAAI Conference on Artificial Intelligence (AAAI), 2017. (人工智能领域重要国际会议) [2].Shengtao Xiao, Jiashi Feng, Junliang Xing, Hanjiang Lai, Shuicheng Yan, Ashraf Kassim. Robust Facial Landmark Detection via Recurrent Attentive-Refinement. In European Conference on Computer Vision (ECCV), 2016. (计算机视觉领域重要国际会议) [3].Chi Su, Shiliang Zhang, Junliang Xing, Wen Gao, Qi Tian, Ashraf Kassim. Deep Attributes Driven Person Re-identification. In European Conference on Computer Vision (ECCV), 2016. (计算机视觉领域重要国际会议) [4].Yanghao Li, Cuiling Lan, Junliang Xing, Wenjun Zeng, Chunfeng Yuan, Jiaying Liu. Online Human Action Detection using Joint Classification-Regression Recurrent Neural Networks. In IEEE European Conference on Computer Vision (ECCV), 2016. (计算机视觉领域重要国际会议) [5].Xinchu Shi, Haibing Lin, Weiming Hu, Junliang Xing, and Yanning Zhang. Tensor Power Iteration for Multi-Graph Matching. IEEE International Conference Computer Vision Pattern Recognition (CVPR), 2016. (计算机视觉和模式识别领域重要国际会议) [6].Wentao Zhu, Cuiling Lan, Junliang Xing, Wenjun Zeng, Yanghao Li, Li Shen, Xiaohui Xie. Co-occurrence Feature Learning for Skeleton based Action Recognition using Regularized Deep LSTM Networks. AAAI Annual Conference Artificial Intelligence (AAAI), 2016. (人工智能领域重要国际会议) [7].Lin Ma, Xiaoqin Zhang, Weiming Hu, Junling Xing, Jiwen Lu, Jie Zhou. Local Subspace Collaborative Tracking. IEEE International Conference Computer Vision (ICCV), 2015. (计算机视觉领域重要国际会议) [8].Shaoxin Li, Junliang Xing, Zhiheng Niu, Shiguang Shan, Shuicheng Yan. Shape Driven Kernel Adaptation in Convolutional Neural Network for Robust Facial Traits Recognition. IEEE International Conference Computer Vision Pattern Recognition (CVPR), 2015. (计算机视觉和模式识别领域重要国际会议) [9].Mengdan Zhang, Junliang Xing, Jin Gao and Weiming Hu. Robust visual tracking using joint scale-spatial correlation filters. IEEE International Conference on Image Processing (ICIP), 2015. (图像处理领域重要国际会议) [10].Yabo Fan, Junliang Xing, and Weiming Hu. Load-balanced locality-sensitive hashing: A new method for efficient near duplicate image detection. IEEE International Conference on Image Processing (ICIP), 2015. (图像处理领域重要国际会议) [11].Junliang Xing, Liwei Liu, Haizhou Ai and Shihong Lao. Robust Crowd Counting Using Detection Flow, IEEE International Conference on Image Processing (ICIP), 2011. (图像处理领域重要国际会议) [12].Mengdan Zhang, Junliang Xing, Jin Gao, Xinchu Shi, Qiang Wang, and Weiming Hu. Joint Scale-Spatial Correlation Tracking With Adaptive Rotation Estimation. IEEE International Conference Computer Vision Workshops (ICCVW), 2015. [13].Jin Gao, Haibin Lin, Weiming Hu, Junliang Xing. Transfer Learning Based Visual Tracking with Gaussian Process Regression. IEEE Eur. Conference Computer Vision (ECCV), 2014. (计算机视觉领域三大重要国际会议之一) [14].Junliang Xing, Zhiheng Niu, Junshi Huang, Weiming Hu, Shuicheng Yan. Towards Multi-view and Partially-occluded Face Alignment. IEEE International Conference Computer Vision Pattern Recognition(CVPR), 2014. (计算机视觉和模式识别领域重要国际会议) [15].Xinchu Shi, Haibin Lin, Weimign Hu, Chunfeng Yuan, Junliang Xing. Multi-target Tracking with Motion Context in Tensor Power Iteration. IEEE International Conference Computer Vision Pattern Recognition (CVPR), 2014. (计算机视觉和模式识别领域重要国际会议) [16].Junliang Xing, Jin Gao, Bin Li, Weiming Hu, Shuicheng Yan. Robust Object Tracking with Online Multi-lifespan Dictionary Learning. IEEE International Conference Computer Vision (ICCV), 2013.(计算机视觉领域重要国际会议) [17].Jin Gao, Junliang Xing, Weiming Hu. Discriminant Tracking Using Tensor Representation with Semi-supervised Improvement. IEEE International Conference Computer Vision (ICCV), 2013.(计算机视觉领域重要国际会议) [18].Xinchu Shi, Haibin Ling, Junliang Xing, Weiming Hu. Multi-target Tracking by Rank-1 Tensor Approximation. IEEE International Conference Computer Vision Pattern Recognition (CVPR), 2013. (计算机视觉和模式识别领域重要国际会议) [19].Luoqi Liu, Hui Xu, Junliang Xing, Si Liu, Xi Zhou, Shuicheng Yan. “Wow! You Are So Beautiful Today!” ACM International Conference Multimedia (ACM MM), 2013. (多媒体领域重要国际会议,大会唯一最佳论文奖) [20].Junliang Xing, Haizhou Ai and Shihong Lao, Multi-Object Tracking through Occlusions by Local Tracklets Filtering and Global Tracklets Association with Detection Responses, IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), 2009. (计算机视觉领域重要国际会议) [21].Junliang Xing, Haizhou Ai and Shihong Lao, Multiple Human Tracking Based on Multi-View Upper-Body Detection and Discriminative Learning, IEEE International Conference on Pattern Recognition (ICPR), 2010. (模式识别领域重要国际会议) [22].Junliang Xing, Liwei Liu, Haizhou Ai and Shihong Lao. Robust Crowd Counting Using Detection Flow, IEEE International Conference on Image Processing (ICIP), 2011. (图像处理领域重要国际会议) [23].Junliang Xing, Liwei Liu and Haizhou Ai, Background Subtraction through Multiple Life Span Modeling, IEEE International Conference on Image Processing (ICIP), 2011. (图像处理领域重要国际会议) [24].Junliang Xing, Haizhou Ai and Shihong Lao. Hierarchical Pedestrian Segmentation in Video, IEEE Asian Conference on Pattern Recognition (ACPR), 2011. [25].Jin Gao, Junliang Xing, Weiming Hu, Xiaoqin Zhang. Graph Embedding Based Semi-Supervised Discriminative Tracker. IEEE International Conference Computer Vision Workshops (ICCVW), 2013. [26].Jin Gao, Junliang Xing, Weiming Hu, Xiaoqin Zhang, Ruiguang Hu. Multi-object Tracking under Occlusion Using Dual-Mode Graph Embedding. Asian Conference on Pattern Recognition (ACPR), 2013. [27].Jun Li, Shan Zhou, Junliang Xing, Changyin Sun, Weiming Hu. An Efficient Approach to Web Near-Duplicate Image Detection. Asian Conference on Pattern Recognition (ACPR), 2013. [28].Liwei Liu, Junliang Xing, Haizhou Ai. Online Structure Learning for Robust Object Tracking. IEEE International Conference Image Processing (ICIP), 2013. (图像处理领域重要国际会议) [29].Lin Ma, Junliang Xing, Xiaoqin Zhang, Weiming Hu. Adaptive Cooperative Tracking Based on Multi-Graph Embedding and Markov Random Field. IEEE International Conference Acoust., Speech, Signal Processing (ICASSP), 2013. (语音信号处理领域重要国际会议) [30].Lin Ma, Junliang Xing, Xiaoqin Zhang, Weiming Hu. Distance Map of Various Weights: a New Feature for Adaptive Object Tracking. IEEE International Conference Acoust., Speech, Signal Processing (ICASSP), 2013. (语音信号处理领域重要国际会议) [31].Liwei Liu, Junliang Xing, Haizhou Ai, Xiang Ruan. Hand posture recognition using finger geometric feature. IEEE International Conference Pattern Recognition (ICPR), 2012. (模式识别领域重要国际会议) [32].Liwei Liu, Junliang Xing, Haizhou Ai, Shihong Lao. Semantic superpixel based vehicle tracking. IEEE International Conference Image Processing (ICPR), 2012. (模式识别领域重要国际会议) [33].Lei Sun, Junliang Xing, Haizhou Ai, Shihong Lao. A tracking based fast online complete video synopsis approach. IEEE International Conference Pattern Recognition (ICPR), 2012. (模式识别领域重要国际会议)

科研活动IEEE会员,CCF会员,CCF计算机视觉专委会委员

合作情况与新加坡国立大学、微软亚洲研究院、北京大学等国内外知名机构保持密切合作关系。

社会任职:研究方向:承担科研项目情况:代表论著:获奖及荣誉: