| CARVIEW |
Select Language
HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Sat, 06 Dec 2025 16:28:01 GMT
access-control-allow-origin: *
strict-transport-security: max-age=31556952
etag: W/"69345991-60e7"
expires: Mon, 29 Dec 2025 18:29:29 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: 1001:3946E9:92121F:A3F0B2:6952C629
accept-ranges: bytes
age: 0
date: Mon, 29 Dec 2025 18:19:29 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210097-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1767032369.347680,VS0,VE223
vary: Accept-Encoding
x-fastly-request-id: 0608265a32c18d9fc08c98c47e951aedb1608ccf
content-length: 6462
Avijit Dasgupta
|
|
|
|
hello!
👋 I am Avijit, a M.S. + Ph.D. student in Computer Science at IIIT Hyderabad, India and a member of the CVIT lab, jointly advised by C. V. Jawahar, IIIT Hyderabad, and Karteek Alahari at the Thoth group, Inria. My primary research focuses on egocentric video understanding, driven by a long-term vision to make assistive technologies universally accessible. In the past, I have interned at Adobe Research India, and was a visiting scientist at Thoth, Inria. One of my works was featured on Meta’s YouTube channel.
My Ph.D. is funded by the Google India Ph.D. Fellowship, 2017 (1 out of 4 recipients). Thank you Google!
🔍 I am officially on the job market looking for industry and postdoc positions. Please reach out to me if you think I would be a good fit for your team.
recent & upcoming
Nov 2025
Ego-Exo4D extended version is accepted at IJCV, 2025
Nov 2025
Successfully completed my internship at Adobe Research, Bangalore, India 🇮🇳
Oct 2025
Two papers accepted at WACV, 2026
Oct 2025
One paper on assistive technologies is accepted at ICVGIP, 2025
Jun 2025
Started as a Research Ph.D. Intern at Adobe Research, Bangalore, India 🇮🇳
Jan 2025
Extended version of CleanAdapt is accepted at PR, 2025
October 2024
Featured in Project Aria Video by Meta!
March 2024
Ego-Exo4D is accepted at CVPR, 2024
Dec 2022
CleanAdapt won Best-Paper Runner-up at ICVGIP, 2022
Oct 2022
Our work on source-free video domain adaptation, CleanAdapt, is accepted at ICVGIP, 2022
Oct 2020
Paper accepted at ICPR, 2020.
Feb 2019
Visiting Thoth, Inria, Grenoble 🇫🇷
July 2017
Awarded Google India Ph.D. Fellowship in Machine Perception!
|
|
|
|
experience
Research Ph.D. Intern
Adobe Research
Bangalore, India
•
Jun 2025 - Nov, 2025
Working on document stylization with MLLMs
Visiting Researcher
Thoth, Inria
Grenoble, France
•
Feb 2019 - May 2019
Worked on reinforcement learning for DOOM game
Research Intern
IIIT Hyderabad
Hyderabad, India
•
Oct 2016 - Dec 2016
Worked on deep neural network visualization
Junior Research Fellow
IIT Kharagpur
Kharagpur, India
•
July 2014 - Oct 2016
Worked on various projects related to medical imaging
Research Intern
ISI Kolkata
Kolkata, India
•
July 2012 - July 2013
Developed biologically inspired image filters
publications
2026
Avijit Dasgupta*, Sainithin Artham*, Shankar Gangisetty, C. V. Jawahar
Distilling What and Why: Enhancing Driver Intention Prediction with MLLMs
WACV 2026
Ajoy Mondal, Saumya Mundra, Avijit Dasgupta, C. V. Jawahar
UniTabBank: A Large Scale Multi-Lingual, Multi-Layout, Multi-Type, Multi-Format Dataset for Table Detection
WACV 2026
2025
Kristen Grauman, Andrew Westbury, Lorenzo Torresani, Kris Kitani, Jitendra Malik, ..., Avijit Dasgupta*, ...
Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives
IJCV 2025
Shayon Dasgupta, Avijit Dasgupta, C. V. Jawahar
Are We There Yet? Exploring the Capabilities of MLLMs in Assistive AI Applications
ICVGIP 2025
Oral Presentation
Ritabrata Chakraborty, Rajatsubhra Chakraborty, Avijit Dasgupta, Sandeep Chaurasia
Do We Need Large VLMs for Spotting Soccer Actions?
IJCNLP-AACL (SRW) 2025
Oral Presentation
2024
2022
2020
Avijit Dasgupta, C. V. Jawahar, Karteek Alahari
Context Aware Group Activity Recognition
ICPR 2020
2017
Avijit Dasgupta*, Sonam Singh*
A Fully Convolutional Neural Network Based Structured Prediction Approach Towards Retinal Vessel Segmentation
ISBI 2017
2016
Avijit Dasgupta, Sudipta Mukhopadhyay, Shrikant A Mehre, Parthasarathi Bhattacharyya
Morphological Geodesic Active Contour Based Automatic Aorta Segmentation in Thoracic CT Images
CVIP 2016
Oral Presentation
Manashi Chakraborty, Sudipta Mukhopadhyay, Avijit Dasgupta, Santanu Patsa, Nishat Anjum, Jay Gopal Ray
A new approach of oral cancer detection using bilateral texture features in digital infrared thermal images
EMBC 2016
Manashi Chakraborty, Sudipta Mukhopadhyay, Avijit Dasgupta, Swapna Banerjee, Santanu Patsa, Jay G Ray, K Chaudhuri
A new paradigm of oral cancer detection using digital infrared thermal imaging
SPIE Medical Imaging 2016
2013
Avijit Dasgupta, Ashish Bakshi, Kuntal Ghosh
Lateral inhibition based holistic approach to adaptive image enhancement
IACC 2013
* indicates equal contribution
awards & honors
Best Paper Runner-up, ICVGIP 2022 (2022)
Travel Grant, IFCPAR/CEFIPRA (2019) - Visiting Thoth, Inria, Grenoble 🇫🇷
Google India Ph.D. Fellowship, Google (2017) - Awarded to 4 students in Machine Perception category
Travel Grant, ICMR (2017) - To attend and present at ISBI 2017, Australia 🇦🇺
Junior Research Fellowship, MHRD, Government of India (2014)
services
Reviewer, CVPR, ECCV, ICCV, WACV, ICDAR, ICVGIP, TMI, JBHI, CIBM (2023 - Present)