Aakanksha

I am a PhD research scholar in the Department of Electrical Engineering at Indian Institute of Technology Madras. I am part of the Image Processing and Computer Vision (IPCV) Lab under the guidance of Prof. A. N. Rajagopalan with broad research area including deep-learning based computer vision and multimodal learning. I recieved my Bachelors Degree in Electronics and Communication Engineering from Indian Institute of Information Technology (IIIT) Guwahati in 2018. I was awarded the Chairman's Medal at IIIT Guwahati for the graduating batch of 2018. Recently, I was also awarded the prestigious Malathi Veeraraghavan Scholarship in 2021. In my spare time, I love to read, travel and play badminton.

Email  /  CV  /  Google Scholar  /  LinkedIn

News

[2023.04] I have been awarded Google Travel Grant to attend CVPR 2023.

[2023.03] Our paper has been accepted at CVPR'23.

[2022.10] I was invited to deliver a talk at the Induction Programme-2022, IIIT Guwahati.

[2022.12] I am selected as the 2021 Malathi Veeraraghavan (MV) scholar.

[2021.07] Our paper has been accepted at ICCV'21.

[2020.08] Our paper has been accepted for the Adversarial Robustness in the Real World Workshop at ECCV'20.

Publications

For the full list of my publications please visit my Google Scholar page.

PontTuset

Improving Robustness of Semantic Segmentation to Motion-Blur Using Class-Centric Augmentation
Aakanksha, A. N. Rajagopalan
CVPR'23  
PDF

PontTuset

Localize to Binauralize: Audio spatialization from Visual Sound Source Localization
Kranthi Kumar Rachavarapu, Aakanksha, Vignesh Sundaresha, A. N. Rajagopalan
ICCV'21  
PDF

PontTuset

Robust Super-Resolution of Real Faces using Smooth Features
Saurabh Goswami, Aakanksha, A. N. Rajagopalan
Adversarial Robustness in the Real World Workshop - ECCV'20  
PDF

Other Projects
PontTuset

Video-based characterization of the bounce of a spinning ball
Aakanksha, Ashish Kumar, Mahesh Panchagnula, and A.N. Rajagopalan
Project with Dept. of Applied Mechanics, IIT Madras (2022)  

Worked on an approach to develop a low-cost Decision Review System (DRS) using consumer-grade video cameras. In particular, involved in the design and development of the imaging setup, and the development of an algorithm for a video-based robust estimation of the 3D spin of a ball.