I am currently a research scientist at IBM Research, Tokyo working on learning algorithms for vision-based robotic control and multi-modal generative learning. My research interests are in computer vision, robotics, and deep learning. Previously, I was a researcher at NEC Central Research Labs, Japan, where I worked on applying deep learning techniques for detecting cracks on concrete surfaces from images and videos, to estimate the structural integrity of bridges and roads. I also worked on learning end-to-end fully convolutional networks (FCNs) for image restoration problems like image denoising and inpainting. To know more please visit my research and publications page.
Before joining NEC, I received my master's degree in Electrical Engineering from IIT Bombay where I worked with Prof. Subhasis Chaudhuri in the field of computer vision, graphics and human-computer interaction(haptics). I received my bachelor's degree in Electrical Engineering from Jadavpur University under the guidance of Prof. Amitava Chatterjee. My bachelor's project was on vision based door detection for mobile robot navigation.