Research Interests

Conference Paper
[8]	Pei Yin, Thad Starner, Harley Hamilton, Irfan Essa, James M. Rehg, Learning Basic Units in American Sign Language Using Discriminative Segmental Feature Selection, in IEEE Conference on Accoustics, Speech, and Signal Processing (ICASSP 2009), Apr. 2009. (pdf) (bibtex) (project page)
[7]	Pei Yin, Irfan Essa, Thad Starner, James M. Rehg, Discriminative Feature Selection for Hidden Markov Models Using Segmental Boosting, in IEEE Conference on Accoustics, Speech, and Signal Processing (ICASSP 2008), Mar. 2008. (pdf) (bibtex) (project page)
[6]	Pei Yin, Antonio Criminisi, John Winn, Irfan Essa, Tree-based Classifiers for Bilayer Video Segmentation, in IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2007), June 2007. (pdf) (bibtex)
[5]	Cha Zhang, Pei Yin, Yong Rui, Ross Cutler, Paul Viola, Boosting-Based Multimodal Speaker Detection for Distributed Meetings, Proc. of IEEE MMSP 2006, Oct. 3-6, 2006. (pdf) (bibtex)
[4]	Pei Yin, Irfan Essa, James M. Rehg, "Asymmetrically Boosted HMM for Speech Reading". in IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2004), II755-761, June 2004 (pdf) (bibtex)
[3]	Pei Yin, Irfan Essa, James M. Rehg, "Boosted Audio-Visual HMM for Speech Reading". in Proc. IEEE International Workshop on Analysis and Modeling of Faces and Gestures (AMFG 2003), pp68-73, Oct. 2003/held in conjunction with ICCV-2003. A version of this paper also appears in Proc. Asilomar Conference on Signals, Systems, and Computers, pp 2013-2018, Nov. 2003 as an invited paper. (pdf) (bibtex)
[2]	Xian-Sheng Hua, Pei Yin, Hong-Jiang Zhang, "Efficient Video Text Recognition Using Multiple Frame Integration," 2002 International Conference on Image Processing (ICIP 2002), pp II: 397-400, Sept. 2002. (pdf) (bibtex)
[1]	Pei Yin, Xian-Sheng Hua, Hong-Jiang Zhang, "Automatic Time Stamp Extraction System for Home Videos," 2002 IEEE International Symposium on Circuits and Systems, Theme: Circuits and Systems for Ubiquitous Computing(ISCAS 2002) , pp II: 73-76, May 2002. (pdf) (bibtex)

Research Experience
May 2006- Aug. 2006	Machine Learning and Perception Group Microsoft Research Cambridge, UK Mentor: Dr. Antonio Criminisi
May 2005- Aug. 2005	Communication Collaboration Systems Group Microsoft Research Redmond, USA Mentor: Dr. Yong Rui
Aug. 2002-Present	Computational Perception Lab, Georgia Tech, USA Advisor: Prof. Irfan Essa
Mar. 2001-July 2002	State Key Laboratory of Intelligent Technology and Systems Tsinghua University, China Advisor: Prof. Bo Zhang, Prof. Fu-Zong Lin
Apr. 2001-July 2002	National Engineering Research Center for CAD Supporting Software, Tsinghua University, China Advisor: Prof. Shi-Min Hu
June 2001-Aug. 2002	Media Computing Group, Microsoft Research Asia, China Mentor: Dr. Xian-Sheng Hua

Journal Paper
[2]	Cha Zhang, Pei Yin, Yong Rui, Ross Cutler, Paul Viola, Xinding Sun, Nelson Pinto, Zhengyou Zhang, "Boosting-Based Multimodal Speaker Detection for Distributed Meeting Videos," IEEE Trans. on Multimedia. Vol. 10, No. 8, 1541-1552, 2008.
[1]	Song-Hai Zhang, Pei Yin, Shi-Min Hu, "Error propagation in Geometric Transformation," Journal of Computer Aided Design And Computer Graphics. Vol. 15, No. 5, 537-540, 2003. A version of this paper also appears in Proc. CSIAM Geometric Design And Computing, pp 100-105, June 2002 as an invited paper. (bibtex)

Technical Report
[2]	Xian-Sheng Hua, Pei Yin, Huajian Wang, Junfeng Chen, Lie Lu, Mingjing Li, Hong-Jiang Zhang, "MSR-Asia at TREC-11 Video Track", in Proc. NIST TREC-VID, Nov. 2002. (pdf) (bibtex)
[1]	Pei Yin, (Advisor: Bo Zhang, Fu-Zong Lin) "SVM Active Learning in Text Classification" (Bachelor's Thesis), Tsinghua University, 2002.