Aditya Kumar Singh

IIIT Hyderabad

Gachibowli, 500-032

Telangana, INDIA

Hey Voila!

I’m a second year Master’s student at CVIT Lab, International Institute of Information Technology, Hyderabad under the supervision of Prof. Makarand Tapaswi in the Video-Language Group.

My research interests broadly lie in the intersection of Computer Vision and Natural Language Processing (Multi-modal Learning). Currently, I’m focusing on the challenge of Multimodal Video Summarization on Long-form Videos. Besides, we’re also working on Emotion Recognition and Tracking from Video, Text, and Audio.

Before I joined IIITH, I was a Research Intern at Indian Statistical Institute, Kolkata (2020-21) under Prof. B. Uma Shankar in the Machine Intelligence Unit where I spent a wonderful semester working on Multi-label classification of Remote Sensing Images. I graduated with Integrated BS-MS degree in Mathematics and Statistics from Indian Institute of Science Education and Research, Kolkata in 2021.

In my spare time, I enjoy doing sports (badminton, cycling, and running mostly), sometimes painting (btw have a look at my insta page), and cooking😉.

News

Feb 28, 2023	One paper accepted to CVPR 2023 that talks about recognising emotion/mental-states in movies. Read more
Jun 23, 2022	Finalist @ Qualcomm Innovation Fellowship India 2022. Read more
Jan 15, 2022	Won the Audio-Visual Retrieval Challenge hosted by ICVGIP 2021.
Nov 10, 2021	Joined CVIT Lab, IIIT Hyderabad as a Master’s by Research student under the supervision of Prof. Makarand Tapaswi in the Video-Language Group.
Aug 17, 2021	Graduated with Integrated BS-MS degree in Mathematics and Statistics from Indian Institute of Science Education and Research, Kolkata.
Jul 28, 2021	Admitted to MS by Research program in Computer Science and Engineering at IIIT Hyderabad.
Aug 1, 2016	INSPIRE fellowship awardee (2016 - 2021). Given to communicate and attract young talent of the country inclined towards science and technology to pursue their career in R & D base.