Meet the Team
Arslan Basharat, Ph.D.
Director of Multimodal AI
Kitware New York
Clifton Park, NY
Ph.D. in Computer Science
University of Central Florida
M.S. in Computer Science
University of Central Florida
B.S. in Computer System Engineering
GIK Institute (GIKI)
Dr. Basharat serves as Director of Multimodal AI of the Computer Vision group at Kitware, which he joined in 2009 as an R&D Engineer. He has undertaken roles of research, software development, project management, business development, and personnel management over the years. He has served as a Principal Investigator (PI) or project lead on a variety of software research and development projects sponsored by government organizations including DARPA, AFRL, SOCOM, NGA, and ONR. He has performed research in various areas of computer vision, including object detection and tracking, anomaly detection, activity recognition, dynamical systems in videos, imagery forensics, and imagery retrieval.
Dr. Basharat has served as the overall PI on various projects. For instance, on the DARPA Media Forensics program, he is leading a team of five universities developing state-of-the-art technology for visual media forensics, defending against falsified images and videos like Deepfakes. He has also served as a PI on other efforts, like AFRL Multi-INT Enhanced Exploitation and Analysis Tools (E2AT), AFRL C4ISR Enterprise to the Edge (CETE), ONR Maritime Surveillance and a few SBIR projects. He has also led or contributed to other research projects big and small, including unique efforts like DARPA Probabilistic Programming for Advancing Machine Learning (PPAML), and Crowd Analysis seedling. Earlier in his tenure at Kitware, he led the research and development of object detection and tracking in aerial imagery through DARPA Video and Image Retrieval and Analysis Toolkit (VIRAT), Persistent Stare Exploitation and Analysis System (PerSEAS) and other related projects. Some of the software developed by him on these efforts is part of open source Kitware Image and Video Exploitation and Retrieval (KWIVER) toolkit. Dr. Basharat was a key contributor to the algorithms and software of the full-frame, real-time, multiobject tracker for Wide Area Motion Imagery that was successfully used in live operation.
Dr. Basharat received an M.S. and Ph.D. in Computer Science from the University of Central Florida in 2006 and 2009, respectively. Prior to that, he worked as a Software Design Engineer in Pakistan for two years after receiving a B.S. in Computer System Engineering from GIK Institute (GIKI), Pakistan in 2001. He regularly serves on the program committees of various premier conferences including Computer Vision and Pattern Recognition (CVPR), International Conference on Computer Vision (ICCV), European Conference on Computer Vision (ECCV), International Conference on Image Processing (ICIP), Association for the Advancement of Artificial Intelligence (AAAI) and Winter Conference on Applications of Computer Vision (WACV). He has also served as a reviewer for research journals including IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Pattern Recognition Letters, Machine Vision and Application (MVA), and EURASIP Journal on Advances in Signal Processing. He served as Local Arrangements Chair and Website Chair for the IEEE WACV 2016.
He has several research publications in the premier peer-reviewed conferences and journals. A list of his publications is provided below and on Google Scholar profile. Additional publications by his colleagues from the group are listed under Computer Vision Publications.
