I received my MS and PhD in 2010 and 2013 respectively from the University of Minnesota, Minneapolis, USA under Prof. Nikolaos Papanikolopoulos. Prior to that I was a software design engineer with Microsoft Corporation. I received my undergraduate (honors) degree in computer science and engineering from the National Institute of Technology (NIT), Calicut, India in 2002.
I have broad interests in a variety of topics in computer vision, machine learning, and robotics. My current research focus is on:
- Human pose estimation and activity recognition
- Human-Object/Human-Robot interaction modelling
- Scene understanding and context based reasoning
- Learning to generate image/video captions
- Large scale image/video search/retrieval
- Machine learning on matrix manifolds
My approaches are based on deep learning, probabilistic graphical models, manifold geometric optimization, and sparse coding.
More details regarding my projects and publications are here.