Sanjoy Chowdhury

I am working as a Machine Learning Scientist with the Camera and Video AI team at ShareChat, India. I am also a visiting researcher at the Computer Vision and Pattern Recognition Unit at Indian Statistical Institute Kolkata under Prof. Ujjwal Bhattacharya.

From June 2019 to June 2021, I had worked as a Senior Research Engineer with the Vision Intelligence Group at Samsung R&D Institute Bangalore. I primarily worked on developing novel AI powered solutions for different smart devices of Samsung.

I received my MTech in Computer Science & Engineering from IIIT Hyderabad, where I was Teaching Assistant (TA) for Prof. Ravi Kiran Sarvadevabhatla and Prof. Ashok Kumar Das for the courses Statistical Methods in AI and Discrete Mathematics and Algorithms respectively. During my days at IIIT-H, I was fortunate to be advised by Prof. C V Jawahar.

During my undergrad days, I had worked as research interns under Prof. Pabitra Mitra at IIT Kharagpur and at the CVPR Unit at ISI Kolkata under Prof. Ujjwal Bhattacharya.

Email  /  GitHub  /  Google Scholar  /  LinkedIn

profile photo

Publications

I'm broadly interested in Computer vision, Multi-modal deep learning, Reinforcement learning areas and their various applications to solve real world problems involving but not limited to holistic scene understanding with minimal supervision, adversarial learning, domain adaptation etc.

project image

AudViSum: Self-Supervised Deep Reinforcement Learning for Diverse Audio-Visual Summary Generation


Sanjoy Chowdhury*, Aditya P. Patra*, Subhrajyoti Dasgupta, Ujjwal Bhattacharya
British Machine Vision Conference (BMVC), 2021
Paper / Code / Slides

Introduced a novel deep reinforcement learning based self-supervised audio-visual summarization model that leverages both audio and visual information to generate diverse yet semantically meaningful summaries.

project image

V-DESIRR: Very Fast Deep Embedded Single Image Reflection Removal


B H Pawan Prasad, Green Rosh K S, Lokesh R B, Kaushik Mitra, Sanjoy Chowdhury
International Conference on Computer Vision (ICCV), 2021
Paper / Code

We have proposed a multi-scale end to end architecture for detecting and removing weak, medium and strong reflections from naturally occurring images.

project image

Listen to the Pixels


Sanjoy Chowdhury, Subhrajyoti Dasgupta, Sudip Das, Ujjwal Bhattacharya
International Conference on Image Processing (ICIP), 2021
Paper / Code / Slides

In this study, we exploited the concurrency between audio and visual modalities in an attempt to solve the joint audio-visual segmentation problem in a self-supervised manner.

project image

A Survey on Fuzzy Set Theoretic Approaches for Image Segmentation


Ajoy Mondal*, Sanjoy Chowdhury*
ACM Computing Surveys, 2021 (Under review)

The survey paper performs an in depth comparison and analysis on fuzzy set theory based image segmentation techniques.

project image

Not Too Deep CNN for Face Detection in Real Life Scenario


Sanjoy Chowdhury, Parthasarathi Mukherjee, Ujjwal Bhattacharya
International Conference on Next Generation Computing Technologies, Springer, 2017 (Best paper award, Oral)
Paper / Code

Proposed a multi-scale face detection framework that is capable of detecting faces of multiple size and different orientations in low resolution images while achieving sufficiently low latency and modest detection rates in the wild.

project image

Classification of Citation in Scientific Articles


Sanjoy Chowdhury, Harsh Vardhan, Pabitra Mitra, Dinabandhu Bhandari
National Conference on Recent Advances in Science and Technology, 2016 (Oral)
Abstract / Code

Designed a multi-class classification system to find out the type of citation i.e. a citation belongs to which facet. We aimed to achieve this by extracting and analysing citation information from the text.







Blog(s)

Have tried my hand at writing technical blogs.

project image

The devil is in the details: Video Quality Enhancement Approaches


Link

The blog contextualizes the problem of video enhancement in present day scenario and talks about a couple of interesting approaches to handle this challenging task.







Selected projects

These include coursework, side projects and unpublished research work.

project image

Document Image Unwarping


Code

Worked towards proposing a novel end-to-end Deep Learning based method to unwarp arbitrarily curved and folded paper documents captured in the wild and extract text from it.

project image

Semi-Supervised Multi-View Correlation Feature Learning with Application to Webpage Classification


Code

Implemented a semi-supervised multi-view correlation feature learning (SMCFL) approach, for webpage classification. SMCFL seeks for a discriminant common space by learning a multi-view shared transformation in a semi-supervised manner. This was done as a part of course project and contains implementation of paper

project image

Bias-Free-Hatespeech-Detection


Code / Original paper

Implemented a bias free hatespeech detection system leveraging adversarial learning.







Affiliations




IIT Kharagpur
Apr-Sep 2016

ISI Kolkata
Feb-July 2017

IIIT Hyderabad
Aug 2017 - May 2019

Mentor Graphics Hyderabad
May - July 2018

Samsung Research Bangalore
June 2019 - June 2021

ShareChat Bangalore
June 2021 - Present






News

Oct 2021 Paper on audio-visual summarization accepted in BMVC 2021.
Sep 2021 My first blog on Video Quality Enhancement released at Tech @ ShareChat.
July 2021 Paper on reflection removal got accepted in ICCV 2021.
June 2021 Joined ShareChat Data Science team.
May 2021 Paper on audio-visual joint segmentation accepted in ICIP 2021.
Dec 2018 Accepted Samsung Research offer. Joined in June 2019.
Sep 2018 Received Dean's merit list award for academic excellence at IIIT Hyderabad.
Oct 2017 Our work on multi-scale, low-latency face detection framework received Best Paper Award at NGCT-2017.

Design and source code from Leonid Keselman