Dr. Zsolt Kira is a senior research scientist and branch chief of the Machine Learning and Analytics group at the Georgia Tech Research Institute (GTRI). He received his M.S. in 2008 and Ph.D. in 2010 from Georgia Tech and B.S. from University of Miami in 2002. Subsequently he was a research scientist at SRI International Sarnoff, where he developed novel methods for using deep learning to detect objects at long ranges in near-real time and integrating a combination of several modalities (EO, IR, and LIDAR) into an end-to-end system capable of robust detections up to 25kph up to 50m.
At GTRI he conducts research in the areas of machine learning for sensor processing and perception, with emphasis on feature learning (especially using deep learning architectures) for object detection, video analysis, scene characterization, and clustering. Dr. Kira has developed novel formulations and cost functions to perform joint feature learning and clustering which have demonstrated state of art clustering and one-shot learning results, and deep learning fusion architectures for combining data from multiple sensor modalities. His current interests lie in joining these methods with knowledge graphs to incorporate spatio-temporal, geometric, and contextual cues from multiple sources and using both supervised and semi/unsupervised learning. Dr. Kira has over 25 publications in these areas, several best paper/student paper awards, and has been invited to speak at related workshops in both academia and the within the DoD. He has also taught the graduate-level Deep Learning course at Georgia Tech.