Guest Editors' Introduction to the Special Section on Award Winning Papers from the IEEE CS Conference on Computer Vision and Pattern Recognition (CVPR)
• O. Woodford, I. Reid, P. Torr, and A. Fitzgibbon, "Global Stereo Reconstruction under Second-Order Smoothness Priors." Winner of the Best Paper prize. This paper presents a method of stereo reconstruction using second-order priors on the smoothness of 3D surfaces to better model typical scenes. The resulting optimization is shown to be tractable.
• C.H. Lampert, M.B. Blaschko, and T. Hoffman, "Efficient Subwindow Search: A Branch and Bound Framework for Object Localization." Winner of the Best Paper prize. This paper presents a practical method of localizing objects using the branch-and-bound formalism. A large reduction in location search is shown while still ensuring no false negatives.
• B. Kulis, P. Jain, and K. Grauman, "Fast Similarity Search for Learned Metrics." Winner of the Best Student Paper prize. The paper presents a scalable image search using learned metrics by encoding the learned metric parameterization into randomized locality-sensitive hash functions leading to improved accuracy.
• K. Ni, A. Kannan, A. Criminisi, and J. Winn, "Epitomic Location Recognition." Best Student Paper runner-up. This paper presents a method of recognizing location classes using the epitome representation to capture the variations in appearance and shapes of a collection of images taken from a location.
• H. Schneiderman and T. Kanade, "Probabilistic Modeling of Local Appearance and Spatial Relationships for Object Recognition." This paper represented a significant advance in object recognition through probabilistic modeling and multiple-view training, yielding a state-of-the-art face detection technique.
• C. Bregler and J. Malik, "Tracking People with Twists and Exponential Maps." This was seen as an inspired application of kinematic modeling techniques from robotics to the challenge of tracking people in motion from a single camera view, including a memorable model-based analysis of the Muybridge motion study videos.
• K. Boyer is with the Department of Electrical, Computer, and Systems Engineering, Rensselaer Polytechnic Institute, 110 8th St./JEC 6049, Troy, NY 12180. E-mail: firstname.lastname@example.org.
• M. Shah is with School of Electrical Engineering and Computer Science, University of Central Florida, Orlando, FL 32816.
• T. Syeda-Mahmood is with the IBM Almaden Research Center, 650 Harry Road, San Jose, CA 95120. E-mail: email@example.com.
For information on obtaining reprints of this article, please send e-mail to: firstname.lastname@example.org.
Kim Boyer received the BSEE (with distinction), MSEE, and PhD degrees, all in electrical engineering, from Purdue University in 1976, 1977, and 1986, respectively. He is head of the Department of Electrical, Computer, and Systems Engineering at Rensselaer Polytechnic Institute. From 1977 through 1981, he was with Bell Laboratories, Holmdel, New Jersey; from 1981 through 1983, he was with Comsat Laboratories, Clarksburg, Maryland. From 1986-2007, he was with the Department of Electrical and Computer Engineering, The Ohio State University. He is a fellow of the IEEE, a fellow of the IAPR, and a former IEEE Computer Society Distinguished Speaker. Dr. Boyer is also a National Academies Jefferson Science Fellow at the US Department of State, spending 2006-2007 as Senior Science Advisor to the Bureau of Western Hemisphere Affairs. While at the State Department, he studied the impact of technological innovation on economic development in scientifically lagging and scientifically developing countries. He also developed policy recommendations for the use of science and engineering as instruments of diplomacy. He retains his fellowship as a consultant on science and technology policy for the State Department. Dr. Boyer's research interests include all aspects of computer vision and medical image analysis, including perceptual organization, structural analysis, graph theoretical methods, stereopsis in weakly constrained environments, optimal feature extraction, large modelbases, and robust methods. His current research activities include mapping the surface of the dynamic prelens tear film from interferometric video and intelligent illumination control for photoxicity mitigation in live cell imaging. Dr. Boyer is treasurer of the International Association for Pattern Recognition, as well as a US delegate to the Governing Board. He is a former associate editor of the IEEE Transactions on Pattern Analysis and Machine Intelligence, area editor of Computer Vision and Image Understanding, associate editor of Machine Vision and Applications, chair of the first two IEEE Computer Society Workshops on Perceptual Organization, was a charter member of the DARPA IUE Technical Advisory Committee, and was a member of the initial ORD RADIUS Technical Oversight Committee. With Kuntal Sengupta, he won the Siemens Best Paper Award at CVPR '93. In 1995, a student team co-directed by Professor Boyer won the International Unmanned Ground Vehicle Competition for its vision-guided Autonomous Robotic Transporter. In 2002, he was a program chair for Computer Vision and Robotics at ICPR, Quebec. He is a former chair of the IEEE Computer Society Technical Committee on Pattern Analysis and Machine Intelligence. He was the keynote speaker for the 2004 SIBGRAPI conference in Curitiba, Brazil. He was a program chair for CVPR '08 in Anchorage and is technical chair for both ICPR '10 in Istanbul, Turkey, and ICPR '12 in Tsukuba, Japan. Dr. Boyer has published five books and more than 100 scientific papers. He has lectured in nearly 30 countries around the world. His books include Computing Perceptual Organization in Computer Vision (World Scientific, 1994, with Sudeep Sarkar), Perceptual Organization for Artificial Vision Systems (Kluwer Academic Publishers, 2000, with Sudeep Sarkar), and Robust Range Image Registration: Using Genetic Algorithms and the Surface Interpenetration Measure (2005, with Luciano Silva and Olga Bellon).
Mubarak Shah the Agere Chair Professor of Computer Science, is the founding director of the Computer Visions Lab at the University of Central Florida (UCF). He is a coauthor of three books ( Motion-Based Recognition (1997) and Video Registration (2003), and A utomated Multi-Camera Surveillance: Algorithms and Practice (2008)), all published by Springer. Dr. Shah is a fellow of the IEEE, IAPR, and SPIE. In 2006, he was awarded a Pegasus Professor award, the highest award at UCF, given to a faculty member who has made a significant impact on the university, has made an extraordinary contribution to the university community, and has demonstrated excellence in teaching, research, and service. He was an IEEE Distinguished Visitor speaker for 1997-2000 and received the IEEE Outstanding Engineering Educator Award in 1997. He received the Harris Corporations Engineering Achievement Award in 1999, the TOKTEN awards from UNDP in 1995, 1997, and 2000; Teaching Incentive Program award in 1995 and 2003, Research Incentive Award in 2003, Millionaires Club awards in 2005 and 2006, University Distinguished Researcher award in 2007, honorable mention for the ICCV '05 Where Am I? Challenge Problem, and was nominated for the best paper award at the ACM Multimedia Conference in 2005. He is an editor of an international book series on video computing; editor-in-chief of Machine Vision and Applications, and an associate editor of ACM Computing Surveys. He was an associate editor of the IEEE Transactions on Pattern Analysis and Machine Intelligence and a guest editor of the special issue of the International Journal of Computer Vision on video computing.
Tanveer Syeda-Mahmood graduated from the Massachusetts Institue of Technology Artificial Intelligence Lab in 1993 with the PhD degree in computer science. She is a research manager at the IBM Almaden Research Center, where she heads a program on multimodal mining for healthcare data. She worked as a research staff member at the Xerox Webster Research Center, Webster, New York, before joining IBM in 1998. Dr. Syeda-Mahmood led the image indexing program at Xerox Research and was one of the early originators of the field of content-based image and video retrieval. Currently, she is working on applications of content-based retrieval in healthcare. Over the past 25 years, her research interests have been in a variety of areas relating to artificial intelligence, including computer vision, image and video databases, medical image analysis, bioinformatics, and signal processing. She has more than 100 refereed publications and more than 40 issued patents. Dr. Syeda-Mahmood has chaired numerous workshops and conferences including several early workshops that helped established the field of content-based retrieval and event recognition (Event '01-'04). She was the program cochair of CVPR '08. She has received several gold medals for academic excellence, including the Sir Akber Hyderi Gold Medal from Osmania University for undergraduate education. She received the prestigious IBM fellowship during graduate school. She has received numerous awards for outstanding contributions to IBM Research over the years. She is a senior member of the IEEE.