Developed a novel deep architecture for predicting future locations of people observed in first-person videos. Released a new dataset on human locomotion seen in FPV. Paper under review at CVPR’18.
Designed a novel algorithm to extend application of cellular automaton based image processing methods to grayscale images. Paper published at 28th Irish Signal and Systems Conference 2017
Designed a knowledge distillation procedure aimed for compressing Fully Convolutional Network (FCN) with skip connections such as U-net and Stacked Hourglass Network. Achieved ~100x model compression.
We aimed to develop a measure for synchrony measurement between speakers in one on one conversations. It was ndergraduate Research project for junior year under Prof. Tanaya Guha IIT Kanpur