肖俊副教授

肖俊,工学博士,副教授,博士生导师,求是青年学者

浙江大学计算机学院人工智能研究所

教育部-微软视觉感知重点实验室(浙江大学)

新加坡国立大学传感器增强社交媒体中心PI

浙大网新-浙江大学人工智能联合研究中心PI

浙江大学新型城镇化研究中心PI

浙江省疾控中心公共卫生研究院PI

中南卡通动漫多媒体省级高新技术企业研究开发中心PI

浙江中南卡通动漫产业研究院技术顾问

电话:0571-87951277,13867424906

E-mail:junx@cs.zju.edu.cn

 

浙江大学计算机学院人工智能研究所副教授、博士生导师,浙江省“151”人才工程第三层次培养人员,浙江大学求是青年学者,微软学者,教育部-微软视觉感知重点实验室(浙江大学)青年骨干教师

主要研究领域为大数据分析、多媒体计算及计算机动画等方面。参加工作以来,作为第一负责人先后承担了国家自然科学基金面上项目、国家自然科学基金青年基金项目、863项目、浙江省重大科技专项、浙江省自然科学基金重点项目、浙江省自然科学基金面上项目、浙江省公益技术应用研究项目、中国博士后科学基金特别资助项目、博士后科学基金等一批省部级科研项目,同时还作为项目骨干参加了国家自然科学基金重点项目、973项目、863项目以及国家科技支撑计划项目的研发工作。获得浙江省自然科学奖一等奖(排名第5),在TKDE、TVCG、TCB、Pattern Recognition、Information Science、Signal Processing、Neurocomputing、Multimedia Systems、Computer Animation and Virtual Worlds和CVPR、IJCAI、AAAI、ACM MM、CASA等国内外期刊和会议上新发表(录用)学术论文60余篇,与他人合作出版英文专著1部,获得国家发明专利授权32项,软件著作权20项。

 

  • 承担的部分科研项目:
  1. 异构三维人体运动数据融合重用理论研究与应用, 浙江省自然科学基金重点项目, 2017-01至2020-12
  2. 多视图深度学习的RGBD人体行为识别与理解, 国家自然科学基金面上项目, 2016-01至2019-12
  3. 3D内容感知生成技术和系统, 863项目, 2012-01至2014-12
  4. 基于稀疏表达理论的三维人体运动表示及重用方法研究, 浙江省自然科学基金面上项目, 2013-01至2015-12
  5. RGB-D多模态特征融合与选择的人体行为识别技术研究, 浙江省公益技术研究社会发展项目, 2014-01至2015-12
  6. 基于张量分析及流形学习的三维人体运动参数化编辑与合成, 国家自然科学基金青年基金项目, 2010-01至2012-12
  7. 面向公共安全的跨媒体呈现与验证和示范平台, 973项目, 2012-01至2016-08
  8. 中国工程科技知识中心浙江大学运行测试平台, 中国工程院工程科技知识中心建设项目, 2013-01至2013-12
  • 论文及专著:
  1. Yueting Zhuang, Yunhe Pan and Jun Xiao. A Modern Approach to Intelligent Animation: Theory and Practice. Springer, 72万字, 2008 (本人负责30万字撰写)
  2. Long Chen, Hanwang Zhang, Jun Xiao*, Liqiang Nie, Jian Shao, Tat-seng Chua. SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning. Accepted CVPR 2017
  3. Yueting Zhuang, Hanqi Wang, Jun Xiao*, Fei Wu, Yi Yang, Weiming Lu, Zhongfei Zhang. Bag-of-Discriminative-Words (BoDW) Representation via Topic Modeling, IEEE Transactions on Knowledge and Data Engineering(online published: http://dx.doi.org/10.1109/TKDE.2017.2658571)
  4. Zhouzhou He, Xi Li, Zhongfei Zhang, Yaqing Zhang, Jun Xiao and Xue Zhou. Structure-Aware Slow Feature Analysis for Age Estimation. Accepted by IEEE Signal Processing Letters.
  5. Jun Song, Siliang Tang, Jun Xiao, Fei Wu, Zhongfei Zhang. LSTM-in-LSTM for generating long descriptions of images. Accepted by Computational Visual Media.
  6. Zhuhao Wang, Fei Wu, Weiming Lu, Jun Xiao*, Xi Li, Zitong Zhang, Yueting Zhuang. Diversely Image Captioning via GroupTalk. Accepted by the 25th International Joint Conference on Artificial Intelligence IJCAI 2016. (CCF A, Full Paper)
  7. Te Pi, Xi Li, Zhongfei Zhang, Deyu Meng, Fei Wu, Jun Xiao*, Yueting Zhuang. Self-Paced Boost Learning for Classification. Accepted by the 25th International Joint Conference on Artificial Intelligence IJCAI 2016. (CCF A, Full Paper)
  8. Zhao Wang, Yinfu Feng, Shuang Liu, Jun Xiao, Xiaosong Yang, Jun Zhang. A 3D human motion refinement method based on sparse motion bases selection. To appear in Computer Animation and Virtual Worlds. 2016 (SCI, IF: 0.43)
  9. Jun Xiao, Yinfu Feng, Mingming Ji, Yueting Zhuang. Fast View-based 3D Model Retrieval via Unsupervised Multiple Feature Fusion and Online Projection Learning. Signal Processing. 2016, 120: 702-713 (SCI, IF: 2.24)
  10. Yinfu Feng, Mingming Ji, Jun Xiao*, Xiaosong Yang, etc. Mining Spatial-temporal Patterns and Structural Sparsity for Human Motion Data Denoising. IEEE Transactions on Cybernetics. 2015, 45(12): 2168-2267 (CCF B, SCI, IF: 3.469)
  11. Jiageng Feng, Jun Xiao. View-invariant human action recognition via robust locally adaptive multi-view learning. Frontiers of Information Technology & Electronic Engineering. 2015, 16(11): 917-929 (SCI, IF: 0.3)
  12. Yinfu Feng, Jun Xiao*, Kang Zhou, Yueting Zhuang. A Locally Weighted Sparse Graph Regularized Non-negative Matrix Factorization Method. Neurocomputing. 2015, 169: 68-76 (SCI, IF: 2.0)
  13. Mingming Ji, Yinfu Feng, Jun Xiao*, Yueting Zhuang, etc. Efficient Semi-supervised Multiple Feature Fusion with Out-of-Sample Extension for 3D Model Retrieval. Neurocomputing. 2015, 169: 68-76 (SCI, IF: 2.0)
  14. Jun Xiao, Zhangpeng Tang, Yinfu Feng, Zhidong Xiao. Sketch-based Human Motion Retrieval via 2D Geometric Posture Descriptor. Signal Processing. 2015, 113: 1-8 (SCI, IF: 2.24)
  15. Jun Xiao, Yinfu Feng, Mingming Ji, Xiaosong Yang, etc. Sparse Motion Bases Selection for Human Motion Denoising. Signal Processing. 2015, 110: 108-122 (SCI, IF: 2.24)
  16. Hao Ye, Hiroyuki Kitagawa, Jun Xiao. Continuous Angle-based Outlier Detection on High-dimensional Data Streams. In Proceedings of the 19th International Database Engineering & Applications Symposium. 2015: 162-167
  17. Liming Zhao, Xi Li, Jun Xiao, Fei Wu, Yueting Zhuang. Metric Learning Driven Multi-Task Structured Output Optimization for Robust Keypoint Tracking. In Proceedings of AAAI 2015 (CCF A, Full Paper)
  18. Yinfu Feng, Jun Xiao*, Yueting Zhuang, Xiaosong Yang, Jianjun Zhang and Rong Song. Exploiting Temporal Stability and Low-Rank Structure for Motion Capture Data Refinement. Information Science. 2014, Vol(277): 777-793 (CCF B, SCI, IF: 3.89)
  19. Tian Qi, Yinfu Feng, Jun Xiao*, Hanzhi Zhang, Yueting Zhuang, etc. A Human Motion Feature based on Semi-supervised Learning of GMM. Multimedia Systems. 2014, 1-9. (SCI, IF: 0.76)
  20. Tian Qi, Jun Xiao*, Yueting Zhuang, Hanzhi Zhang, etc. Real-time Motion Data Annotation via Action String. Computer Animation and Virtual Worlds. 2014, 25(2-4): 293-302 (SCI, IF: 0.43)
  21. Zhangpeng Tang, Jun Xiao*, Yinfu Feng, Xiaosong Yang, etc. Human Motion Retrieval Based on Freehand Sketch. Computer Animation and Virtual Worlds. 2014, 25(2-4): 273-281 (SCI, IF: 0.43)
  22. 张剑,何骅,詹小四,肖俊. 结合特征适配与拉普拉斯形变的3维人脸重建. 《中国图象图形学报》, 2014, 19(9): 1349-1359
  23. Zhang Liang, Yueting Zhuang, Yi Yang, Jun Xiao*. Retrieval-based cartoon gesture recognition and applications via semi-supervised heterogeneous classifiers learning. Pattern Recognition. 2013, 46: 412-423 (CCF B, SCI, IF: 3.096)
  24. Yang Liu, Jian Shao*, Jun Xiao, Fei Wu, Yueting Zhuang¸ Hypergraph Spectral Hashing for Image Retrieval with Heterogeneous Social Contexts, Neurocomputing. 2013, 119: 49-58 (SCI)
  25. Tian Qi, Yinfu Feng, Jun Xiao*, Yueting Zhuang, Xiaosong Yang and Jianjun Zhang. A Semantic Feature for Human Motion Retrieval. Computer Animation and Virtual Worlds. 2013, 24: 399-407 (SCI, IF: 0.43)
  26. 张剑, 何骅, 詹小四, 肖俊. 用 SIFT 词汇树实现的姿态无关的人脸识别. 《计算机辅助设计与图形学学报》,2013,25 (11):1694-1700 (EI)
  27. 齐天, 肖俊*, 庄越挺. 稀疏表达的运动数据压缩. 《中国图象图形学报》, 2013, 18(3): 311-317
  28. 冯家更, 肖俊*. 视点无关的行为识别综述. 《中国图象图形学报》, 2013, 18(2): 157-168
  29. Yinfu Feng, Jun Xiao*, Zhengjun Zha, Hong Zhang and Yi Yang. Active Learning for Social Image Retrieval using Locally Regressive Optimal Design. Neurocomputing. 95: 54-59, 2012 (SCI)
  30. Zhang Liang, Jun Xiao*, Yueting Zhuang. Synthesizing style-preserving cartoons via non-negative style factorization. Journal of Zhejiang University - Science C (Comput & Electron), 13(3): 196-207, 2012 (SCI)
  31. Weiming Lu, Jun Xiao*, Yueting Zhuang. An Interactive Method for Generating Spatial-Temporal Variations of Human Movement. Journal of Computational and Theoretical Nanoscience. 2012, 10(1):411-420 (SCI, IF: 1.34)
  32. 王翔宇,肖俊*,潘红. 表演驱动的矢量化二维表情动画. 《计算机辅助设计与图形学学报》 ,24(5):598-604,2012 (EI)
  33. 肖俊*,李文通. 视觉信息在行人群体仿真中的应用. 《计算机辅助设计与图形学学报》, 24(2):217-226, 2012 (EI)
  34. Yinfu Feng, Jun Xiao*, Yueting Zhuang and Xiaoming Liu. Adaptive Unsupervised Multi-View Feature Selection for Visual Concept Recognition. ACCV 2012
  35. Cheng Chen*, Yueting Zhuang, Feiping Nie, Yi Yang, Fei Wu and Jun Xiao. Learning a 3D Human Pose Distance Metric from Geometric Pose Descriptor. IEEE Transactions on Visualization and Computer Graphics, 17(11): 1676-1689, 2011 (CCF A, SCI)
  36. Jun Xiao, Yinfu Feng* and Wenyuan Hu. Predicting Missing Markers in Human Motion Capture using l1-sparse Representation. Journal of Computer Animation and Virtual Worlds, 22(2-3): 221-228, 2011 (SCI)
  37. Chunluan Zhou, Jun Xiao*. Cartoon capture by key-frame based contour tracking. Journal of Zhejiang University - Science C (Comput & Electron), 12(1): 36, 2011 (SCI)
  38. Zhang Liang, Jun Xiao*, Hong Pan. Retrieval Based Cartoon Synthesis via Heterogeneous Features Learning. Workshop on Digital Media and Digital Content Management (DMDCM), 125~131,2011 (EI)
  39. Jun Hu, Guangda Li, Zhen Lu, Jun Xiao and Richang Hong. Videoader: a video advertising system based on intelligent analysis of visual content. In Proceedings of ICIMCS 2011.
  40. Cheng Chen*, Yueting Zhuang and Jun Xiao. Silhouette representation and matching for 3D pose discrimination – A comparative study. Image and Vision Computing, 28: 654-667, 2010 (SCI)
  41. Jun Xiao*, Yueting Zhuang, Fei Wu, Tongqiang Guo and Zhang Liang. A group of novel approaches and a toolkit for motion capture data reusing. Springer Journal of Multimedia Tools and Applications, 47: 379-408, 2010 (SCI)
  42. Jun Xiao and Tongqiang Guo*. A script engine for realistic human motion generation. International Journal of Computer Applications and Technology, 38: 55-63, 2010 (EI)
  43. Cheng Yao, Jun Xiao*, Tongqiang Guo and Liang Xia. Real-time digitised shadow play performance method based on multi-point interactive controlling method. International Journal of Computer Applications and Technology, 38: 86-92, 2010 (EI)
  44. 王宇杰,肖俊*,魏宝刚. 基于非线性流行学习的3维人体运动合成. 《中国图象图形学报》,15(6):936-943, 2010
  45. Cheng Chen*, Yueting Zhuang, Jun Xiao and Zhang Liang. Perceptual 3D pose distance estimation by boosting relational geometric features. Computer Animation and Virtual Worlds, 20: 267-277, 2009 (SCI)
  46. Zhang Liang, Jun Xiao*, Yueting Zhuang and Cheng Chen. Competitive motion synthesis based on hybrid control. Computer Animation and Virtual Worlds, 20: 225-235, 2009 (SCI)
  47. Cheng Chen, Yueting Zhuang, Jun Xiao*. Example based 3D motion recovery by searching with compact and discriminative silhouette feature. Asian Conference on Computer Vision (ACCV), 2009 demo.
  48. 陈成,庄越挺,肖俊*. 相机运动条件下的视频前景提取. 《浙江大学学报(工学版)》,43(6):973-982, 2009 (EI)
  49. 陈成,肖俊*,庄越挺. 单目视频人体三维运动高效恢复. 《计算机辅助设计与图形学学报》, 21(8):1118-1126,2009 (EI)
  50. 潘红,肖俊*,吴飞,郭同强. 基于关键帧的三维人体运动检索. 《计算机辅助设计与图形学学报》,21(2):214-222,2009 (EI)
  51. Yanan Liu, Fei Wu*, Yueting Zhuang, Jun Xiao, Active Post-refined Multi-modality Video Semantic Concept Detection with Tensor Representation, Proceedings of the 2008 ACM International Conference on Multimedia (ACM Multimedia), p.91-100, 2008 (CCF A, FULL Paper)
  52. Yueting Zhuang, Jun Yu*, Jun Xiao and Cheng Chen. Perspective-aware cartoon clips synthesis. Computer Animation and Virtual Worlds, 19(3): 355-364, 2008 (SCI)
  53. Cheng Chen*, Yueting Zhuang, Jun Xiao and Fei Wu. Adaptive and compact shape descriptor by progressive feature combination and selection with boosting. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), 2008. (CCF A, EI)
  54. Yueting Zhuang, Yushun Wang*, Jun Xiao, Yujie Wang. Expressive 3D Face Synthesis by Multi-Space Modeling. In Proceedings of First IEEE International Conference on Ubi-media Computing, p.207-212, 2008 (EI)
  55. 肖俊,庄越挺,吴飞*. 三维人体运动特征可视化与交互式运动分割. 《软件学报》,19(8): 1995-2003,2008(EI)
  56. 肖俊*,庄越挺,吴飞. 计算机视觉与机器学习技术在三维人体动画中的应用综述. 《计算机辅助设计与图形学学报》,20(3): 281-290,2008(EI)
  57. 王玉顺,肖俊*,庄越挺,王宇杰. 基于运动传播和Isomap分析的三维人脸动画编辑与合成. 《计算机辅助设计与图形学学报》,2008,20(12):1590-1595 (EI)
  58. Jun Yu*, Yueting Zhuang, Jun Xiao and Cheng Chen. Adaptive Control in Cartoon Data Reusing. Computer Animation and Virtual Worlds, 18(5): 571-582, 2007 (SCI)
  59. Yushun Wang*, Yueting Zhuang, Jun Xiao and Fei Wu. A Piece-Wise Learning Approach to 3D Facial Animation. In Proceedings of ICWL 2007, p.416-427, 2007 (EI)
  60. Jun Xiao*, Yueting Zhuang, Tao Yang and Fei Wu. An Efficient Keyframe Extraction from Motion Capture Data. In Proceedings of Computer Graphics International Conference, p.494-501, 2006(SCI)
  61. 杨涛,肖俊*,吴飞,庄越挺. 基于分层曲线简化的运动捕获数据关键帧提取. 《计算机辅助设计与图形学学报》,18(11):1691-1697, 2006 (EI)
  62. Jun Xiao*, Yueting Zhuang, Fei Wu. Getting Distinct Movements from Motion Capture Data. In Proceedings of CASA 2006.
  63. Cheng Chen, Yueting Zhuang, Jun Xiao*. Towards Robust 3D Reconstruction of Human Motion from Monocular Video. In Proceedings of ICAT 2006, p.594-603, 2006
  64. 姚琤,肖俊*,庄越挺. 基于影像美学原理的虚拟相机自动拍摄生成方法. 《系统仿真学报》,18(10):2852-2855, 2006
  65. Yueting Zhuang, Jun Xiao*, Yizi Wu, Tao Yang and Fei Wu. Automatic generation of human animation based on motion programming. Computer Animation and Virtual Worlds, 16: 305, 2005 (SCI)
  66. 肖俊*,庄越挺,吴飞. 基于细节层次与最小生成树的三维地形识别与检索. 《软件学报》,14(2):1148-1158, 2003 (EI)
  67. 肖俊*,吴飞,庄越挺,张引. 基于支持向量机与细节层次的三维地形识别与检索. 《计算机辅助设计与图形学学报》,15(4):410-415, 2003 (EI)

 

  • 发明专利:
  1. 一种基于草绘图的三维模型检索方法,发明专利,中国,2.28, ZL 201410074654.9
  2. 一种三维人体姿态投影的特征提取方法, 发明专利, 中国, 8, ZL 201410064670.X
  3. 基于相关性几何特征的运动相似性评估方法,授权日期:3.30,ZL 201310084753.0
  4. 保持时序平稳与低秩结构特性的三维人体运动数据补全方法,授权日期:3.30,ZL 201310558212.7
  5. 一种基于稀疏表达的运动数据压缩方法,授权日期:10.07,ZL 2012104666120
  6. 基于稀疏表达的三维人体运动数据补全方法,授权日期:08.26,ZL2012103613094
  7. 一种基于关键标记点的人体姿态稀疏重建方法,授权日期:08.26,ZL2013100478911
  8. 一种基于手绘图的三维模型检索的方法,授权日期:08.26,ZL2013100893469
  9. 一种数据驱动和稀疏表达的三维人体运动去噪方法,授权日期:04.29,ZL201210462761X
  10. 基于动作捕获数据驱动的二维卡通表情动画制作方法,授权日期:05.07,ZL2011104025752
  11. 基于异构特征降维的二维角色卡通生成方法,授权日期:04.16,ZL2011101070991
  12. 基于样例的区分式三维运动恢复方法,授权日期:07.25,ZL2010101278567
  13. 一种基于非线性流形学习的三维人体运动合成方法,授权日期:06.06,ZL2009101002183
  14. 基于关键帧的卡通角色轮廓跟踪方法,授权日期:05.09,ZL2010101311832
  15. 二维卡通角色形变方法,授权日期:12.07,ZL2010101331573
  16. 人体运动数据片段提取方法,授权日期:01.19,ZL2009100969762
  17. 竞技性交互式动画生成方法,授权日期:01.19,ZL2009100969758
  18. 基于关键帧的三维人体运动数据检索方法,授权日期:10.13,ZL200810059128X
  19. 基于背景视图合成卡通动画的方法,授权日期:07.21,ZL2008100632650
  20. 基于快速图像配准的视角变化条件下视频前景提取方法,授权日期:01.20,ZL2008100591241
  21. 一种基于模板匹配的视点无关的人体动作识别方法,授权日期:01.20,ZL2008100591294
  22. 基于自然视频的实时智能监控方法,授权日期:01.20,ZL2008100624832
  23. 基于视频提取和重用的卡通动画制作方法,授权日期:01.20,ZL2008100591415
  24. 基于子空间技术的风格化人体运动生成与编辑方法,授权日期:01.20,ZL2006100534061
  25. 一种基于区域分割和分段学习的三维人脸动画制作的方法,授权日期:11.25,ZL2008100591260
  26. 基于侧影和末端节点的视频人体三维运动恢复方法,授权日期:09.16,ZL2006100534057
  27. 基于运动脚本的三维人体动画自动生成方法,授权日期:10.22,ZL2006100533961
  28. 一种基于网格拓扑建模的三维人脸动画制作方法,授权日期:09.03,ZL2006100533891
  29. 基于视频流的三维动态人脸表情建模方法,授权日期:09.03,ZL2006100533938
  30. 一种基于轮廓时空特征的视频对象标注方法,授权日期:08.20,ZL2006100533980
  31. 三维人体运动数据关键帧提取方法,授权日期:07.16,ZL2006100533995
  32. 一种基于视频流的人脸表情幻想方法,授权日期:07.16,ZL2006100533942

 

  • 软件著作权:
  1. 人体运动压缩系统,2015SR228629
  2. 人体运动标注系统,2015SR229825
  3. 三维人体运动渲染编辑软件‍系统,2015SR000500
  4. 基于草绘图的三维模型检索系统软件‍,2015SR000499
  5. 基于手绘草图的运动检索系统,2015SR000755
  6. 基于关键标记点的三维人体运动生成系统,2015SR001138
  7. 三维场景搭建系统,2014SR036351
  8. 基于Kinect的多视角数据采集系统软件,2014SR039363
  9. 基于可拖拽二维草图的运动检索系统,2014SR039076
  10. 人脸运动捕获数据处理系统软件,3,中国,2012SR001753
  11. 基于异构特征的角色卡通综合应用系统,6,中国,2011SR035588
  12. 二维卡通动画素材重用系统,2,中国,2011SR008721
  13. 基于近红外相机的运动捕获系统,5,中国,2010SR025850
  14. 多相机三维姿态恢复系统,5,中国,2010SR025851
  15. 交互式三维人体运动合成软件系统,9,中国,2009SR038159
  16. 智能交互式动画生成系统软件,9,中国,2009SR040611
  17. 人体运动语义片段自动提取系统软件,9,中国,2009SR040609
  18. 基于栅格的人员逃生模拟系统软件,2,中国,2008SR03421
  19. 人体运动数据编辑处理系统软件,2,中国,2008SR03420
  20. 基于视频流的人体动画系统软件0,2007.1,中国,2007SR00746