S. Kevin Zhou

Email: s.kevin.zhou AT gmail.com
Web:  http://www.cfar.umd.edu/~shaohua/

Home

Research

Teaching

Publications

Source Codes

Books

	My edited book entitled "Analysis and Modeling of Faces and Gestures", a proceeding for an international workshop, has been published by Springer as LNCS 4778.
	My book entitled "Unconstrained Face Recognition" has been published by Springer as a part of the International Series on Biometrics. ISBN: 0-387-26407-8.
	My book entitled "Recognition of Humans and Their Activities Using Video" has been published by Morgan & Claypool Publishers as a part of the Synthesis Lectures on Image, Video, and Multimedia Processing. ISBN: 1598290061.

Papers (listed in a reverse chronological order)

Most representative

• S.  Zhou, V. Krueger, and R. Chellappa. Probabilistic recognition of human faces from video. Computer Vision and Image Understanding (CVIU) (special issue on Face Recognition), Vol. 91, pp. 214-245, 2003.
  [Comment]: The first approach in the literature that systematically investigates the role of temporal information in vide-based face recognition.
  [Journal paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• S.  Zhou, R. Chellappa, and B. Moghaddam. Visual tracking and recognition using appearance-adaptive models in particle filters. IEEE Transactions on Image Processing (TIP), Vol. 11, pp. 1434-1456, November 2004.
  [Comment]: The importance of adaptive models to appearance changes, both the state-transition and observation models in visual tracking.
  [Journal paper]: [html] - [pdf] -[ps] - [doc] - [ppt]
   
• S. Zhou, B. Georgescu, X. Sean Zhou, and D. Comaniciu. Image based regression using boosting method. IEEE International Conference on Computer Vision (ICCV), Beijing, China, October 2005.
  [Comment]: A recipe of learning a nonlinear multivariate multiple regressor via selecting image features using boosting.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• S. Zhou and R. Chellappa. From sample similarity to ensemble similarity: Probabilistic distance measures in reproducing kernel Hilbert space. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 28. No. 6, pp. 917-929, June 2006.
  [Comment]: A pure machine learning (kernel method) paper that addresses the similarity between two sets or ensembles.
  [Journal paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• S. Zhou, J. Shao, B. Georgescu, and D. Comaniciu. BoostMotion: Boosting a discriminative similarity function for motion estimation. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), New York City, June 2006.
  [Comment]: Learning a similarity function that matches two images.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• S. Zhou, G. Aggarwal, R. Chellappa, and D. Jacobs. Appearance characterization of linear Lambertian objects, generalized photometric stereo and illumination-invariant face recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 29. No. 2, pp. 230-245, February 2007.
  [Comment]: 99.1% recognition accuracy on the PIE database (the illumination variation part).
  [Journal paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• S. Zhou and D. Comaniciu. Shape regression machine. Information Processing in Medical Imaging (IPMI), The Netherlands, July 2007.
  [Comment]: How regression can be invoked to solve shape detection and segmentation? 112ms for a fully automatic segmentation of left ventricle from echocardiogram.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• S. Zhou, F. Guo, J.H. Park, G. Carneiro, J. Jackson, M. Brendel, C. Simopoulos, J. Otsuki, and D. Comaniciu. A probabilistic, hierarchical, and discriminant (PHD) framework for rapid and accurate detection of deformable anatomic structure. International Conference on Computer Vision (ICCV), Rio de Janeiro, October 2007.
  [Comment]: A nicely-crafted algorithm that does fast and accurate detection of deformable structure.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   

Year 2008

• J. Li, S. Zhou, and R. Chellappa. Appearance modeling using a geometric transform. IEEE Transactions on Image Processing, 2008. (In press)
  [Journal paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• H. Ling, S. Zhou, Y. Zheng, B. Georgescu, M. Suehling, and D. Comaniciu. Hierarchical, learning-based automatic liver segmentation. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), Anchorage, Alaska, June 2008.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• J. Zhang, S. Zhou, D. Comaniciu, and L. McMillan. Conditional density learning via regression with application to deformable shape segmentation. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), Anchorage, Alaska, June 2008.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• S. Zhou, R. Chellappa, and G. Aggarwal. Face tracking and recognition from video. The Essential Guide to Video Processing, A. Bovic (Ed.), Academic Press.
  [Book chapter]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• S. Zhou, R. Chellappa, and R. Ramanathan. Unconstrained face recognition from still image. The Essential Guide to Image Processing}, A. Bovic (Ed.), Academic Press.
  [Book chapter]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• S. Zhou. Appearance modeling for visual tracking. USTC 50th Golden Anniversary Book: Computer Vision, J. Luo and X. Tang (Eds.), USTC Press.
  [Book chapter]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• S. Zhou, J. Shao and D. Comaniciu. Similarity learning for motion estimation. Semantic Mining Technologies for Multimedia Database, D. Tao, D. Xu, and X. Li (Eds.), IGI
  Publishing.
  [Book chapter]: [html] - [pdf] - [ps] - [doc] - [ppt]

Year 2007

• S. Zhou, W. Zhao, X. Tang, and S. Gong (Eds.). Analysis and modeling of faces and gestures. Springer, LNCS 4778, 2007.
  [Edited book]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• S. Zhou, F. Guo, J.H. Park, G. Carneiro, J. Jackson, M. Brendel, C. Simopoulos, J. Otsuki, and D. Comaniciu. A probabilistic, hierarchical, and discriminant (PHD) framework for rapid and accurate detection of deformable anatomic structure. International Conference on Computer Vision (ICCV), Rio de Janeiro, October 2007.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• J.H. Park, S. Zhou, C. Simopoulos, J. Otsuki, and D. Comaniciu. Automatic cardiac view classification of echocardiogram. International Conference on Computer Vision (ICCV), Rio de Janeiro, October 2007.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• H. Wu, R. Chellappa, and A. Sankaranarayanan and S. Zhou. Robust visual tracking using the time-reversibility constraint. International Conference on Computer Vision (ICCV), Rio de Janeiro, October 2007.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• A. Tsymbal, M. Huber, S. Zillner, T. Hauer, and S.Zhou. Visualing patient similarity in clinical decision support. International Workshop on Knowledge and Experience Management (FGWM), 2007.
  [Workshop paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• S. Zhou and D. Comaniciu. Shape regression machine. Information Processing in Medical Imaging (IPMI), The Netherlands, July 2007.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• S. Zhou, J. Zhou, and D. Comaniciu. A boosting regression approach to medical anatomy detection. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), Minneapolis, Minnesota, June 2007.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• J. Zhang, S. Zhou, L. McMillan and D. Comaniciu. Joint real-time object detection and pose estimation using probabilistic boosting network. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), Minneapolis, Minnesota, June 2007.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• X. Mei, S. Zhou, and F. Porikli. Probabilistic visual tracking via robust template matching and incremental subspace update. IEEE International Conference on Multimedia and Expo (ICME), Beijing, China, 2007.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• S. Zhou, G. Aggarwal, R. Chellappa, and D. Jacobs. Appearance characterization of linear Lambertian objects, generalized photometric stereo and illumination-invariant face recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 29. No. 2, pp. 230-245, February 2007.
  [Journal paper]: [html] - [pdf] - [ps] - [doc] - [ppt]

Year 2006

• S. Zhou, R. Chellappa and W. Zhao. Unconstrained face recognition. Springer, 2006. (ISBN: 0-387-26407-8)
  [Research monograph]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• V. Krueger, S. Zhou, and R. Chellappa. Integrating video information over time. Example: Face recognition from video. Cognitive Vision Systems: Sampling the Spectrum of Approaches, H.I. Christensen, H. Nagel (Eds.), Springer Berlin/Heidenlberg, 2006.
  [Book chapter]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• S. Zhou and R. Chellappa. From sample similarity to ensemble similarity: Probabilistic distance measures in reproducing kernel Hilbert space. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 28. No. 6, pp. 917-929, June 2006.
  [Journal paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• S. Zhou, J. Shao, B. Georgescu, and D. Comaniciu. Pairwise active appearance model and it application to echocardiography tracking. International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), Copenhagen, Denmark, October 2006.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• S. Zhou, J. Shao, B. Georgescu, and D. Comaniciu. BoostMotion: Boosting a discriminative similarity function for motion estimation. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), New York City, June 2006.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• S. Zhou, J.H. Park, B. Georgescu, C. Simopoulos, J. Otsuki, and D. Comaniciu. Image-based multiclass boosting and echocardiographic view classification. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), New York City, June 2006.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• Y. Zheng, X. Zhou, B. Georgescu, S. Zhou and D. Comaniciu. Example-based non-rigid shape detection. European Conference on Computer Vision (ECCV), Graz, Austria, May 2006.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• X. Mei, S. Zhou and H. Wu. Integrated detection, tracking, and recognition for IR video-based vehicle classification. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Toulouse, France, May 2006.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]

Year 2005

• R. Chellappa, A. Roy-Chowdhury, and S. Zhou. Recognition of humans and their activities using videos. Morgan & Claypool Publishers, 2005. (ISBN: 1598290061)
  [Research monograph]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• S. Zhou and R. Chellappa. Beyond a single still image: Face recognition from multiple still images and videos. Face Processing: Advanced Modeling and Methods, W. Zhao and R. Chellappa (Eds.), Academic Press, 2005.
  [Book chapter]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• R. Chellappa, A. Roy Chowdhury, and S. Zhou. Human Identification using gait and face. The Electrical Engineering Handbook, 3rd Edition, M. Delores (Ed.), CRC Press, 2005. (To appear)
  [Book chapter]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• S. Zhou and R. Chellappa. Face recognition from still images and videos. Handbook of Image and Video Processing, 2nd Edition, A. Bovik (Ed.), Academic Press, 2005.
  [Book chapter]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• S.  Zhou and R. Chellappa. Image-based face recognition under illumination and pose variations. Journal of the Optical Society of America (JOSA), A,Vol. 22, pp. 217-229, February 2005.
  [Journal paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• S. Zhou, B. Georgescu, X. Sean Zhou, and D. Comaniciu. Image based regression using boosting method. IEEE International Conference on Computer Vision (ICCV), Beijing, China, October 2005.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• J. Li, S. Zhou, and R. Chellappa. Appearance modeling under geometric context. IEEE International Conference on Computer Vision (ICCV), Beijing, China, October 2005.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• S. Zhou. A binary decision tree implementation of a boosted strong classifier. IEEE International Workshop on Analysis and Modeling of Faces and Gestures (AMFG), Beijing, China, October 2005.
  [Workshop paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• S. Zhou. Matrix-based kernel subspace methods. SCR Technical Report SCR-05-TR-773.
  [Technical report]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• J. Shao, S. Zhou, and R. Chellappa. Tracking algorithm using background-foreground motion models and multiple cues. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Philadelphia, USA, March 2005. 
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• M. Ramachandran, S. Zhou, D. Jhalani, and R. Chellappa. A method for converting smiling face to a neutral face with applications to face recognition. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Philadelphia, USA, March 2005.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• X. Mei, M. Ramachandran, and S. Zhou. Video background retrieval using mosaic images. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Philadelphia, USA, March 2005.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]

Year 2004

• S. Zhou. Unconstrained Face Recognition. Ph.D. Dissertation, University of Maryland, 2004.
  [Ph.D. Dissertation]: [html] - [pdf] - [ps] - [doc] - [ppt]
  　 
• R. Chellappa and S. Zhou. Face tracking and recognition from video. Handbook of Face Recognition, S. Li and A. K. Jain (Eds.), Springer, 2004.
  [Book chapter]: [html] - [pdf] - [ps] - [doc] - [ppt]
  　
• S.  Zhou, R. Chellappa, and B. Moghaddam. Visual tracking and recognition using appearance-adaptive models in particle filters. IEEE Transactions on Image Processing (TIP), Vol. 11, pp. 1434-1456, November 2004.
  [Journal paper]: [html] - [pdf] -[ps] - [doc] - [ppt]
   
• S. Zhou. Face recognition using more than one image: What is more? Sinobiometrics, Guangzhou, China, December 2004.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• J. Shao, S. Zhou, and R. Chellappa. Simultaneous background and foreground modeling for tracking in surveillance video. International Conference on Image Processing (ICIP), Singapore, October 2004.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• S. Zhou and R. Chellappa. Multiple-exemplar discriminant analysis for face recognition. International Conference on Pattern Recognition (ICPR), Cambridge, UK, August 2004.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• J. Shao, S. Zhou, and Q. Zheng. Robust appearance-based tracking of moving object from moving platform. International Conference on Pattern Recognition (ICPR), Cambridge, UK, August 2004.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• S. Zhou and R. Chellappa. Probabilistic identity characterization for face recognition. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), Washington D.C., USA, June 2004.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• S. Zhou and R. Chellappa. Illuminating light field: Image-based face recognition across illuminations and poses. IEEE International Conference on Automatic Face and Gesture Recognition (FGR), Seoul, Korea, May 2004.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• S. Zhou, R. Chellappa, and B. Moghaddam. Intra-personal kernel space for face recognition. IEEE International Conference on Automatic Face and Gesture Recognition (FGR), Seoul, Korea, May 2004.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• Z. Yue, S. Zhou, and R. Chellappa. Robust two-camera visual tracking with homography. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Montreal, Canada, May 2004.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• J. Shao, S. Zhou, and R. Chellappa. Appearance-based visual tracking and recognition with trilinear tensor. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Montreal, Canada, May 2004.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• J. Li and S. Zhou. Probabilistic face recognition with compressed imagery. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Montreal, Canada, May 2004.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• S. Zhou, R. Chellappa and D. Jacobs, Characterization of human faces under illumination variations using rank, integrability, and symmetry constraints. European Conference on Computer Vision (ECCV), Prague, Czech Republic, May 2004.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• S. Zhou, R. Chellappa and B. Moghaddam. Appearance tracking using adaptive models in a particle filter. Asian Conference on Computer Vision (ACCV), Jeju Island, Korea, January 2004.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]

Year 2003

• S.  Zhou, V. Krueger, and R. Chellappa. Probabilistic recognition of human faces from video. Computer Vision and Image Understanding (CVIU) (special issue on Face Recognition), Vol. 91, pp. 214-245, 2003.
  [Journal paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• S. Zhou. Probabilistic analysis of kernel principal components: mixture modeling and classification. CfAR Technical Report, CAR-TR-993, 2003.
  [Technical report]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• S. Zhou and R. Chellappa. Rank constrained recognition from unknown illuminations. IEEE International Workshop on Analysis and Modeling of Faces and Gestures (AMFG), Nice, France, October 2003.
  [Workshop paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• S. Zhou, R. Chellappa and B. Moghaddam. Adaptive visual tracking and recognition using particle filters. IEEE International Conference on Multimedia & Expo (ICME), Baltimore, USA, July 2003.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• S. Zhou and R. Chellappa. Simultaneous tracking and recognition of human faces from video. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Hongkong, China, April 2003.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• J. Li, S. Zhou and C. Shekhar. A comparison of subspace analysis for face recognition. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Hongkong, China, April 2003.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]

Year 2002

• S. Zhou, V. Krueger, and R. Chellappa. Probabilistic recognition of human faces from video. CfAR Technical Report, CAR-TR-976, 2002.
  [Technical report]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• S. Zhou, Y. V. Venkatesh, and C. C. Ko. Synthesis of visual textures and perceptual asymmetry of visual texture perception. International Conference on Control, Automation, Robotics and Vision (ICCARV), Singapore, December 2002.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• R. Chellappa, V. Krueger, and S. Zhou. Probabilistic recognition of human faces from video. IEEE International Conference on Image Processing (ICIP), Rochester, New York, USA, September 2002.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• S. Zhou and R. Chellappa. A robust algorithm for probabilistic human recognition from video. International Conference on Pattern Recognition (ICPR), Quebec City, Canada, August 2002.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• V. Krueger and S. Zhou. Exemplar-based face recognition from video. European Conference on Computer Vision (ECCV), Copenhagen, Denmark, May 2002.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• S. Zhou and R. Chellappa. Probabilistic human recognition from video. European Conference on Computer Vision (ECCV), Copenhagen, Denmark, May 2002.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• R. Chellappa, S. Zhou and B. Li. Bayesian methods for face recognition from video. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Orlando, Florida, USA, May 2002.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• S. Zhou, V. Krueger, and R. Chellappa. Face recognition from video: A condensation approach. IEEE International Conference on Automatic Face and Gesture Recognition (FG), Washington D.C., USA, May 2002.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]

Year 2000

• S. Zhou. Wavelet-based texture retrieval and modeling visual texture perception. M.E. dissertation, National University of Singapore, 2000.
  [M.E. dissertation]: [html] - [pdf] - [ps] - [doc] - [ppt]
   
• S. Zhou, Y. V. Venkatesh, and C. C. Ko. Texture retrieval using tree-structured wavelet transform. International Conference on Computer Vision, Pattern Recognition, and Image Processing (CVPRIP), March 2000.
  [Conference paper]: [html] - [pdf] - [ps] - [doc] - [ppt]