I’m a first year PhD student in Computer Science at the Department of Electrical Engineering & Computer Sciences (EECS) at University of California, Berkeley where I’m jointly advised by Prof. Jitendra Malik and Prof. Yi Ma.
This summers, I’m a research intern at the Toyota Research Institute, Mountain View (TRI) working with Adrien Gaidon on problems around pedestrian behaviour modelling for self driving cars. Last year, I was a master’s student in Computer Science at Stanford University working on pedestrian locomotion forecasting as a Research Assitant with Prof. Juan Carlos in the Stanford Vision Lab.
I graduated summa cum laude from the Indian Institute of Technology, Kanpur majoring in Electrical Engineering and with a minor in Machine Learning. During my bachelors, I’ve had the good fortune of working with amazing mentors in computer vision labs across the world like Prof. Yoshua Bengio & Prof. Alain Tapp (MILA, Research Intern), Prof. Pascal Fua (EPFL, Semester Exchange Student), Prof. Yoichi Sato (University of Tokyo, Research Intern), Prof. Tanaya Guha (IITK, Undergraduate Project) and Prof. K S Venkatesh (IITK, Research Intern). Apart from my academic endeavours, I like reading philosophy and absolutely love an interesting book/chat/discussion on different viewpoints of rationality, ethics and recently, on the future of AI and how it is going to take over the world and destroy us ;-) You can find my CV here and papers or reports for all the above work in the publication section.
PhD in Computer Science
University of California, Berkeley [Ongoing]
Master's in Computer Science (AI track)
Stanford University, USA [Dropout]
Master's Semester Exchange, 2018
Btech. in Electrical Engineering (ML Minor), 2018
IIT Kanpur, India
* indicates submitted and pending review
For a complete list, kindly see my CV
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.
Web-app for course recommendation using recommendation engine and text analysis. Won OVERALL BEST PROJECT in Google DevFest 2016. See project page for details.
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.
Implemented various classfiers for human emotion detection in the Emotion Recognition in the Wild Challenge 2016 dataset to compare against results from CNN based approaches. Details on project page.
Deisgned and developed early prototypes of an onboard image processing pipeline capable of underwater object recognition and autonomous manoeuvre. The current updated code is available here.
Designed an algorithm for finding solutions to Non-Causal discrete difference equations (in context of discrete time systems) efficiently optimizing MATLAB in-built methods for the same. Applied spline interploation and sampling techniques for faster algoithm.
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
Implemented a recommendation engine pipeline for e-commerce products. For pre-processing, designed a PGM based procedure for feature selection based on IAMB algorithm and for recommendations, trained a Collaborative filtering based Restricted Boltzmann Machine on Amazon datasets. The corresponding code is confidential being a product of my work as Research intern at Busigence in winters 2016.
I have worked as a Academic mentor in Counselling Service, IITK for