It is an impressive yet alarming fact that there is far more video being captured—by consumers, scientists, defense analysts, and others—than can ever be watched or browsed efficiently. The goal of my research is to develop efficient and scalable algorithms to summarize the visual world (i.e., videos and image collections).
My research interests are in Computer Vision, Machine Learning, Multimedia Computing and Pattern Recognition. Specifically, I am interested in exploring different machine learning techniques (Sparse Coding, Deep Learning and Graph Clustering) to solve several challenging problems in summarizing and segmenting videos.
I also worked on person re-identification in video surveillance, weakly supervised object localization and interesting defect/anomoly detection problems in non-destructive testing.