Uday Kusupati

I am a first year computer science Masters student at the University of Texas at Austin, where I am working with Prof. Qixing Huang.

I did my Bachelor's in CS with a minor in mathematics at the IIT Bombay where I worked with Prof. Siddhartha Chaudhuri on scene graphs and Prof. Arjun Jain on Human Pose Estimation.

Email  /  Google Scholar  /  LinkedIn  /  GitHub

Research

I'm interested in computer vision pertinent to 3D objects and leveraging machine learning for efficient representations of the same. I am currently working on analysing possible topology aware methods for 3D reconstruction from single image. I am also looking forward to explore if language supervision aids human pose estimation this spring.

Learning 3D Human Pose from Structure and Motion
Rishabh Dabral, Anurag Mundhada, Uday Kusupati, Safeer Afaque, Abhishek Sharma, Arjun Jain
ECCV, 2018

We propose two anatomically inspired loss functions and use them with a weakly-supervised learning framework to jointly learn from large-scale in-the-wild 2D and indoor/synthetic 3D data. We also present a simple temporal network that exploits temporal and structural cues present in predicted pose sequences to temporally harmonize the pose estimations.

Visual Parsing and Reconstruction with Stochastic Grammars and Recursive Networks
Undergraduate Thesis, IIT Bombay
Advisor: Prof. Siddhartha Chaudhuri

Affordance based Furniture Generation
Advisor: Prof. Siddhartha Chaudhuri

Internships
prl

Object Recognition for Robot Cleaner
Samsung Research, Seoul, South Korea


Worked on efficient memory and processing time reduction for deep learning on an automated Robot Cleaner without significant losses in accuracy.

prl

Computing Delaunay Complexes using distance-only computations
DATASHAPE, Inria Sophia Antipolis
Advisor: Prof. Jean-Daniel Boissonnaut


Contributed to the GUDHI library with an implementation of computing Delaunay complexes, with a reduced computational complexity of polynomial in dimension from exponential.

Course Projects
prl

Topology aware Mesh Reconstruction: Solving for 2D Data
Uday Kusupati, Abhinav Deep Singh
Numerical Optimization for Graphics & AI, Fall 2018, UT Austin
Advisor: Prof. Qixing Huang


We propose a topology aware method for 3D reconstructions from single RGB images using graph convolutions and reinforcement learning. We test the idea on a smaller task of 1D to 2D reconstruction.

prl

Role of structured information for answering questions on data visualizations
Uday Kusupati, Ankur Garg, Venkata Ravi Teja Ailavarapu
Deep Learning Seminar, Fall 2018, UT Austin
Advisor: Prof. Philipp Krähenbühl


We exploit the structural information within bar graphs and use a multi head attention on top of them to give state of the art results on the DVQA dataset.

prl

Natural Language to Code using Transformers
Uday Kusupati, Venkata Ravi Teja Ailavarapu
Natural Language Processing, Fall 2018, UT Austin
Advisor: Prof. Greg Durrett


We analyse the effectiveness of Transformers for the natural language to code translation task and also experiment with other techniques like back translation and cycle consistency.

Teaching
ta

CS213/293 - Data Structures and Algorithms - Spring 2018 - IIT Bombay

CS101 - Computer Programming & Utilization - Fall 2017 - IIT Bombay

CS101 - Computer Programming & Utilization - Spring 2018 - IIT Bombay


Last Updated: Dec 2018
site-lift here