Siwei Lyu
Associate Professor
Computer Science
University at Albany
United States of America
Biography
Dr. Lyu's research interests include natural image statistics, digital image forensics, machine learning and computer vision. He leads the Machine Learning and Vision Lab (MLVL) at UAlbany. MLVL has focused on in the area of video analysis, and on-going projects include fusing 3D scene reconstruction with live tracking for optimal event representation, unsupervised data-driven machine learning methods for video event categorization, and supervised learning methods using side information. Prior to joining UAlbany's faculty, Lyu served as a research scientist at Microsoft Research, where he helped develop techniques to render and recognize digital inks. He holds four patents. He also previously worked with the Center for Neurosciences at New York University. Dr. Lyu graduated from Dartmouth College with Ph.D. degree in Computer Science in 2005, and from Beijing University with M.S. degree in Computer Science and B.S. degree in Information Science in 2000 and 1997, respectively.
Research Interest
Dr. Lyu's main research interests include digital image forensics, computer vision and machine learning.
Publications
-
Honggang Qi, Andrew Pulver, and Siwei Lyu, “Using 3D Face Model for Forensic Analysis of Lighting Environment,†in IEEE Workshop on Information Forensics and Security (WIFS), Abu Dabhi, UAE, 2016.
-
Longyin Wen, Zhen Lei, Ming-Ching Chang, Honggang Qi, and Siwei Lyu, “Multi-Camera Multi-Target Tracking with Space-Time-View Hyper-graph,†International Journal of Computer Vision, 2016.
-
Dawei Du, Honggang Qi, Longyin Wen, Qingming Huang, Tian Qi, and Siwei Lyu, “Geometric Hypergraph Learning for Visual Tracking,†IEEE Transactions on Cybernetics, vol. (to appear), 2017.
-
Yang Yang, Longyin Wen, Siwei Lyu, and Stan Z. Li, “Learning Multi-Level Descriptors for Person Re-Identification,†in 31st AAAI Conference on Artificial Intelligence (AAAI-17), San Francisco, CA, 2017.
-
Andrew Pulver and Siwei Lyu, “LSTM with Working Memory,†in International Joint Conference on Neural Networks (IJCNN), Anchorage, AK, 2017.
