Aniket Agarwal

I am a final year undegraduate at IIT Roorkee majoring in Applied Mathematics.

I've had the pleasure of working with Prof Christian Desrosiers and Prof Jose Dolz from ETS Montreal, on the topic of semi-supervised segmentation. I've also worked with Prof Mohamed Elhoseiny from KAUST, tackling the problem of long-tail Visual Relationship Recognition. Currently, I am working with Prof Angela Yao from NUS Singapore, where our problem focus is on egocentric 3D hand action recognition.

My main research interest lies at the intersection of Computer vision and Graphics. The recent NeRF explosion is something that excites me a lot. I am currently looking for research opportunities to work at the intersection of Graphics and Vision, especially Neural Rendering and Implicit Neural Representations.

Email / CV / Google Scholar / Twitter / Github

Research

I am interested in solving problems at the intersection of vision and graphics. Much of my research till now is on vision related problems such as Vivusl Relationship Recognition, 3D Hand Action Recognition, semi-supervised segmentation, etc.

	Exploring Long Tail Visual Relationship Recognition with Large Vocabulary Aniket Agarwal, Sherif Abdelkarim, Panos Achlioptas, Jun Chen, Jiaji Huang, Boyang Li, Kenneth Church, Mohamed Elhoseiny ICCV, 2021 project / pdf / supp / arXiv / code / cite We propose new benchmarks, GQA-LT & VG8K-LT, for solving and properly targeting the problem of long-tail VRR. Additionaly, we propose RelMix and VilHub, two techniques that can be utilized on top of any VRR model to make its prediction accuracy on tail classes better.
	RelTransformer: Balancing the Visual Relationship Detection from Local Context, Scene and Memory Jun Chen, Aniket Agarwal, Sherif Abdelkarim, Deyao Zhu, Mohamed Elhoseiny Under Review arXiv / code / cite Transformers have seen massive success for solving various Vision and Language related tasks. Here we propose a novel transformer based architecture for solving the long-tail VRR problem.
	Visual Relationship Detection using Scene Graphs: A Survey Aniket Agarwal, Ayush Mangal, Vipul* Under Review (ACM CSUR) arXiv / cite One of the first survey papers on topic of scene graphs, widely used for Visual Relationship Recognition.
	Revisiting CycleGAN for semi-supervised segmentation Arnab Mondal, Aniket Agarwal, Jose Dolz, Christian Desrosiers arXiv / code / cite Utilizing the concepts of cycle-consistency for improving the semi-supervised baseline for image segmentation.

Education

Indian Institute of Technology Roorkee
Integrated MSc in Applied Mathematics
July '17 - May '22

Student Societies:

Co-President | Vision and Language Group (Link)
Treasurer | ACM IIT Roorke Chapter (Link)
Mentor | Student Mentorship Programme
Teaching Assistant | MAN-001 course taught to freshmen year

Miscellaneous

Participated in Intern IIT 2018, held at IIT Bombay. We presented a web-based ML application, LeDoc(Link).

Some of the best experiences I've had in my undergraduate life is due to Vision and Language Group(Link). The seniors and people there are some of the best and loveliest you can find in IIT Roorkee. I am highly indebted for being a part of the group.

In my free time, I love to watch TV shows and you can most definitely find me listening to music at any time of day. I love Rock and Lo-Fi pop genre and am an ardent fan of Radiohead.

This template is stolen from here.