Namrata Vaswani

Papers

Total Citations

H-Index

About

Namrata Vaswani is a leading figure in statistical signal processing and machine learning, renowned for her pioneering work in dynamic shape analysis and robust principal component analysis (PCA). Her research centers on developing mathematical frameworks to model and track non-stationary, high-dimensional data, with key contributions to change detection, activity recognition, and anomaly detection in complex systems. Vaswani’s early work, such as "Non-Stationary 'Shape Activities'" (2006), introduced novel methods for modeling moving and deforming shapes—like groups of people or articulated human bodies—as stochastic dynamical systems, enabling robust tracking and segmentation. Her 2004 paper on "Change Detection in Stochastic Shape Dynamical Models" laid the groundwork for abnormal activity detection, influencing fields from surveillance to robotics. With over 12,000 citations across her career, Vaswani’s impact is profound, particularly through her development of Recursive Robust PCA (RRPCA) and its applications in video surveillance and medical imaging. A recipient of multiple NSF CAREER awards and a Fellow of the IEEE, she is celebrated for bridging theory and practice, making her work indispensable for students and researchers tackling real-world challenges in dynamic data analysis.