I am a Ph.D. candidate advised by Prof. Saket Anand and Prof. Chetan Arora .
My research interest lies in Computer Vision and Deep Learning; research topics include Active Learning, Data Fairness, and Domain Adaptation.
For comprehensive and effective training of deep models, our focus should be on proposing methods to utilize the available data efficiently. Thus, my research investigates visual data's contextual aspect using model's uncertainty to train deep networks effectively. I am interested in solving problems using less supervision.
I am on the job market. Please reach out if you think I could be a good fit for your team
sharata [at] iiitd.ac.in
sharat29ag [at] gmail.com
LAB B413, R&D Block, IIIT-Delhi, Delhi, 110020
B.Tech in CSE, 2016
GEU, Dehradun, India
Does Data Repair Leads to Fair Models? Curating Contextually Fair Data to Reduce Model Bias
WACV 2022
[ Paper ] [ Code ] [ Project Page ]
Improved Dynamic Time Warping Based Approach for Activity Recognition
FICTA 2017
Modified Dense Trajectory for Real Time Action Recognition
IJCTA 2017