Uday Agarwal

I'm a Research Assistant at the Vision, Language and Learning Group, Indian Institute of Technology Jodhpur advised by Prof. Anand Mishra, where I am working on tasks related to Video Understanding namely, moment retrieval, localization of temporal segments, self-supervised representation learning for videos among other vision-language problems. I am fortunate to work with the following mentors : Dr. Manish Gupta (Microsoft Bing) on fine-grained video analysis and Prof. Chetan Arora (IIT Delhi) on AI applications for Healthcare.

I am also privileged to be mentored by Dr. Ankush Gupta (Google DeepMind). During the course of my mentorship I reviewed recent research papers, presented seminars, worked on relevant coursework, implemented projects on programming and trained neural networks from scratch.

I graduated from Vellore Institute of Technology, Bhopal with a Bachelors in Computer Science (specialization in Artificial Intelligence and Machine Learning) in September, 2023.

I am grateful to Mr. Anup Gupta (Nexus Venture Partners) and Mr. Anurag Gupta (EY) for their invaluable guidance on my career path.

Email / LinkedIn / CV / Google Scholar / Github

Recent Activities

Oct 2025: Will be attending ICCV 2025 in-person in Honolulu, Hawaii
Jun 2025: Our work on Video-to-Video Moment Retrieval got accepted at ICCV 2025 !
Dec 2024: Will be attending ICVGIP 2024 in-person at IIIT, Bangalore.
Oct 2024: Our work ChapVidMR has been accepted at ICVGIP 2024.
July 2024:Will be attending NCVPRIPG 2024 in-person at IIST, Thiruvananthapuram.
Apr 2024: In the organizing team of Summer Challenge on Automatic Assessment of Handwritten Answersheets at NCVPRIPG'24. Consider participating!
Mar 2024: Joined the Vision, Language and Learning Group (VL2G) at IIT Jodhpur as a Research Assistant.

Selected Publications

Aligning Moments in Time using Video Queries
Yogesh Kumar^*, Uday Agarwal^*, Manish Gupta, Anand Mishra
ICCV, 2025 (*equal contribution)
paper / code & dataset / slides

CHAPVIDMR:Chapter-based Video Moment Retrieval using Natural Language Queries
Uday Agarwal^*, Yogesh Kumar^*, Abu Shahid^*, Prajwal Gatti, Manish Gupta, Anand Mishra
ICVGIP, 2024 (Spotlight) (* equal contribution)
paper / code & dataset

Miscellanea

I have been learning and practicing the violin for the past 18 years and am skilled in both Indian Classical and Western Styles of Music. My musical journey has been guided by the esteemed Mr. Gulzar Hussain.

Template design taken from here.