Computer Vision
We develop algorithms to process and understand natural language to aid interaction between computers and humans.
We develop algorithms to process and understand natural language to aid interaction between computers and humans.
Convolutional Neural Networks have become the architecture of choice for modern computer vision applications. However, these networks are fairly large and deploying them on small devices is infeasible. We explore compute and energy efficient architectures for vision applications, specifically in the context of multi object tracking in videos. To this end we are currently working on model compression and model pruning techniques.
