Curriculum Vita
Curriculum Vita (last update 5/26/2021). Google Scholar Profile
One Paragraph Bio. (last updated 11/24/2020)
Dr. Beveridge received his Ph.D. in Computer Science from the University of Massachussetts in 1993. He is presently a Professor in the Department of Computer Science at Colorado State University working broadly in the area of Computer Vision. He has published over 150 refereed papers which have been cited over 9,000 times. Professor Beveridge, working closely with Jonathon Phillips at NIST, pioneered new approaches to characterizing how human face recognition algorithm performance varies with demographics attributes such as age, race and gender. Professor Beveridge's current work is motivated by the promise of visually aware agents. Working jointly with colleagues at Brandeis University he has overseen the development of an AI agent able to interact with a person using both speech and sight. The agent responds to visual cues, including facial expressions and gestures, and engages in conversation related to a shared physical problem solving task ; see the first video on this page for an example. Under Professor Beveridge's direction the CSU Vision Lab has a long tradition of releasing open source software. This work includes the 2013 Challenge of Face Recognition From Digital Point-and-Shoot Cameras, and older legacy work supplying open source tools such as the CSU Face Identification Evaluation System. This legacy system, released in 2001, along with other more recently released open source software packages. Together, these tools have been downloaded by over 30,000 users.
Short Bio. (last updated 11/12/2019)
J. Ross Beveridge received his B.S. degree in Applied Mechanics and Engineering Science from the University of California at San Diego in 1980 and his M.S. and Ph.D. degrees in Computer Science from the University of Massachusetts in 1987 and 1993 respectively. He has been in the Computer Science Department at Colorado State University since 1993, where he was an Assistant Professor from 1993 to 2000, an Associate Professor from 2000 to 2010, and where he is currently a Full Professor.
Dr. Beveridge is a member of the IEEE Computer Society as well as the ACM. He has served as an Associate Editor for the IEEE Transactions on Pattern Recognition and Machine Intelligence (PAMI), Pattern Recognition and Image and Vision Computing. He is General Co-Chair for the The 14th IEEE International Conference on Automatic Face and Gesture Recognition to be held in Lille France in May 2019. He served as General Co-Chair for The International Joint Conference on Biometrics held in Denver, Colorado in October 2017. He was Program Co-Chair for the 2015 IEEE Seventh International Conference on Biometrics: Theory, Applications and Systems He was Program Co-Chair for the 1999 IEEE Conference on Computer Vision and Pattern Recognition and frequently serves on numerous workshop and conference Program Committees. He is an author on over 150 publications in computer vision and related fields. He oversees open-source software distributions dating back to 2002 which have been downloaded by over 30,000 users world wide.
Dr. Beveridge's most recent research focus is on the role of vision to improve how computers and humans communicate and jointly solve problems. This work is being carried out as part DARPA's Communicating with Computers program. Past accomplishments include playing a key role in constructing and making public the Point-and-Shoot Face Recognition Challenge (PaSC) and releasing reference implementations of standard human face recognition algorithms. This work dates back to the release in 2001 of the CSU Face Identification Evaluation System, an open source tool that has been downloaded over 24,000 times since its introduction in 2001.
Dr. Beveridge, working with colleagues Bruce Draper, Dr. Geof Givens in Statistics and P. Jonathon Phillips at NIST, pioneered evaluation protocols for face recognition that included covariate analysis and demonstrated these protocols on state-of-the-art face recognition algorithms. Dr. Beveridge's PhD student, David Bolme, released in 2009 an open source face recognition system, FaceL, that is still available for download and may be used to illustrate face labeling over a live video stream.
From 1993 through 1998, Dr. Beveridge developed novel 3D object recognition algorithms that fused sensor data through a 3D model and iteratively refine an instantiated scene model through repeated rendering and matching between images and model. In the context of Automatic Target Recognition, these algorithms were tested against a data set jointly collected by Colorado State and Lockheed Martin. This "Fort Carson Data Set" was the first ever publicly release data of military vehicles simultaneously recorded in thermal, visible light and depth/LADA.
Other past areas of research include optimal matching of geometric features, genetic algorithms and evolutionary computation, the use of reconfigurable embedded hardware for image processing, behavior learning for unmanned air vehicles and severe weather prediction in GOES-R sounder data.
