Issue No. 12 - December (2006 vol. 28)
As long time subscribers to TPAMI may have noticed, the journal is filling up the bookshelf faster then ever before.
Indeed, the issues are getting thicker. Likewise, the number of submissions to TPAMI has been steadily rising and, as of the end of August 2006 when this is being written, we've received 629 submissions in contrast to the 749 received in all of 2005. Our Associate Editors are tireless in overseeing the reviews of all these papers. After serving for four years, we would like to thank Ronen Basri, Sankar Pal, Anand Rangarajan, Stefano Soatto, Tieniu Tan, and Camillo J. Taylor who are retiring from the Editorial Board. Your dedication and judgment is truly appreciated.
With more submissions, TPAMI is also increasing the size of the Editorial Board, and we are pleased to introduce our new Associate Editors: LÃ©on Bottou, Stefan Carlsson, Wolfgang Förstner, Thomas Hofmann, David Hogg, Jiebo Luo, Patrick Perez, and Eric Saund.
Léon Bottou will be overseeing the reviews of papers on machine learning theory and applications that are relevant for pattern recognition including vision and speech recognition. Stefan Carlsson will be considering papers on object and action recognition, motion capture and analysis, and shape analysis. Wolfgang Förstner will handle the review process for papers on image processing, feature extraction, grouping and segmentation, camera calibration, multiview geometry, stereo, registration, surface fitting, range data, performance and quality analysis, and object recognition. Thomas Hofmann will be taking on papers in machine learning, graphical models, content-based retrieval, and object recognition. David Hogg will oversee papers in object recognition and scene understanding, learning in computer vision, tracking, and motion understanding. Jiebo Luo will be handling papers on image and video understanding, content-based multimedia retrieval, applications of pattern recognition, and image processing within vision. Patrick Perez will be responsible for papers in probabilistic models and motion analysis. Eric Saund will oversee papers in perceptual organization and document image analysis. Their brief biographies appear below.
Welcome to TPAMI's editorial board, and we look forward to working with you.
David J. Kriegman, Editor-in-Chief
David Fleet, Associate Editor-in-Chief
For information on obtaining reprints of this article, please send e-mail to: firstname.lastname@example.org.
Léon Bottou received the Diplôme degree from the École Polytechnique, Paris, in 1987, the Magistre en Mathématiques Fondamentales et Appliquées et Informatiques degree from the école Normale Supérieure, Paris, in 1988, and the PhD degree in computer science from Université de Paris-Sud in 1991. He was at AT&T Bell Labs from 1991 to 1992 and AT&T Labs from 1995 to 2002. From 1992 and 1995, he was chairman of Neuristique in Paris, a small company pionneering machine learning tools for data mining applications. He has been with NEC Labs America in Princeton since 2002. His primary research interest is machine learning. His contributions to this field includes theory, algorithms, and large scale applications. His secondary research interest is data compression and coding. His best known contribution in this field is the DjVu document compression technology (http://www.djvuzone.org). He has published more than 60 papers and served on the board of the Journal of Machine Learning Research. He also serves on the scientific advisory board of Kxen Inc. (http://www.kxen.com).
Stefan Carlsson received the PhD degree in communication theory from the Royal Institute of Technology (KTH) in 1986. He is currently a professor of computer science and director of the lab for Computer Vision and Active Perception (CVAP) at KTH. He is a member of the editorial board of the International Journal of Computer Vision. He has previously worked on a range of problems in image analysis and computer vision, especially data compression, geometry, and 3D reconstruction from multiple views. His research interests today focus on problems of object and action recognition.
Wolfgang Förstner studied geodesy from 1967-1971 at Stuttgart University. During his work in the Department for Automation at the Survey Department of Northrhine Westfalia in Bonn, he received the PhD degree in 1976 from Stuttgart University. From 1977 to 1989, he was an assistant professor at the Insitute for Photogrammetry at Stuttgart University. Since 1990, he is director of the Department for Photogrammetry, now part of the Institute for Geodesy and Geoinformation at the University of Bonn. He has supervised more than 100 bachelor and master/diplom theses and more than 20 PhD theses in the area of geodesy, statistics, photogrammetry, geoinformation, image processing, and image interpretation. He has published more than 100 papers in the areas of geodesy, photogrammetry, and computer vision. From 1993 to 2002, he was vice president of the German Association for Pattern Recognition. For the period 2004-2008, he is president of Commission III Photogrammtric Computer Vision and Image Analysis of the International Society for Photogrammetry and Remote Sensing. In 2004, he received the Fairchild Award of the American Society for Photogramemtry and Remote Sensing for his contributions to establish the increasingly important ties between photogrammetry, digital image processing, and computer vision.
Thomas Hofmann received the PhD degree in computer science from the Rheinische Friedrich-Wilhelms-University Bonn, Germany, in 1997 and held postdoctoral positions at the Massachusetts Institute of Technology and the International Computer Science Institute at Berkeley. He joined Brown University as an assistant professor in 1999 and was promoted to associate professor of computer science in 2004. From 2004-2006, was a professor of computer science at the Technical University of Darmstadt, Germany. During that time, he also served as the director of the Fraunhofer Institute for Integrated Publication and Information Systems. Parallel to his academic career, he cofounded Recommind Inc., where he served as chief scientist from 2000-2006. Currently, he is the director of engineering at Google, Zurich. He is the author of more than 60 peer-reviewed research publications and several patents. He currently serves on the editorial boards of the Data Mining and Knowledge Discovery journal, the Journal for Machine Learning Research, Pattern Recognition Letters, and the Journal of Artificial Intelligence. His range of research interests include statistical machine learning, pattern recognition, information retrieval, natural language processing, and computer vision. Special topics include data clustering, graphical models, and semisupervised learning.
David Hogg received the BSc degree in applied mathematics from the University of Warwick, the MSc degree in computer science from the University of Western Ontario, and the DPhil degree from the University of Sussex. He was on the faculty of the School of Cognitive and Computing Sciences at the University of Sussex from 1984 until 1990, when he was appointed a full professor of artificial intelligence at the University of Leeds, where he now heads the Computer Vision Group. He was head of the School of Computing from 1996 to 1999 and a pro-vice-chancellor of the university from 2000 to 2004. During 1999-2000, he was a visiting professor at the MIT Media Lab in Cambridge. His current research is on the development and application of spatio-temporal models within computer vision, dealing especially with learning, stochastic processes, and the integration of qualitative and quantitative representations. He is a member of the IEEE Computer Society.
Jiebo Luo received the BSc degree in electrical engineering in 1989 from the University of Science and Technology of China and the PhD degree from the University of Rochester in 1995. He is currently a senior principal scientist with the Kodak Research Laboratories, Rochester, New York. He has authored more than 100 technical papers and holds more than 40 granted US patents. Dr. Luo has actively participated in numerous international conferences and workshops as a chair, an organizing committee member, and a program committee member. Currently, he is on the editorial boards of the IEEE Transactions on Multimedia, Pattern Recognition, and the Journal of Electronic Imaging. His research interests include pattern recognition, computer vision, image processing, medical imaging, and multimedia communication. Dr. Luo is a Kodak Distinguished Inventor and a senior member of the IEEE.
Patrick Perez received the engineering degree from the École Centrale Paris in 1990 and the PhD degree from the University of Rennes in 1993. After one year as a postdoctoral researcher in the Department of Applied Mathematics at Brown University, he was appointed at INRIA in 1994 as a full time researcher. From March 2000 to February 2004, he was with Microsoft Research, Cambridge, United Kingdom. During this time, he also served as an associate editor of the IEEE Transactions on Image Processing. In 2004, he became a senior researcher at INRIA and he is now with the Vista research group at IRISA/INRIA-Rennes. His research interests concern probabilistic models for understanding, analyzing, and manipulating still and moving images.
Eric Saund received the BS degree in engineering and applied science from the California Institute of Technology and the PhD degree in cognitive science from the Massachusetts Institute of Technology. He is the manager of the Perceptual Document Analysis area in the Intelligent Systems Laboratory at the Palo Alto Research Center. His research is in the field of computational vision, specializing in perceptual organization in the domain of document images. Applications of this work include ubiquitous document imaging, diagrammatic user interfaces, and perceptually supported image editing, as well as classical document recognition. He has has been awarded 23 patents to date and has received best conference paper awards for his work in perceptually supported image editing and inference from opponent betting behavior in poker.