Sanjoy Chowdhury

I am a first year CS PhD student at University of Maryland College Park under Prof. Dinesh Manocha. Prior to this I was working as a Machine Learning Scientist with the Camera and Video AI team at ShareChat, India. I was also a visiting researcher at the Computer Vision and Pattern Recognition Unit at Indian Statistical Institute Kolkata under Prof. Ujjwal Bhattacharya.

Previously, I was 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 fortunate to be advised by Prof. C V Jawahar. During my undergrad, 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  /  Twitter

Publications

My research is at the intersection of Computer Vision, Deep Learning with a focus on Multi-modal learning, Video understanding and their various applications. I'm broadly interested in problems involving holistic scene understanding with minimal supervision, generative modeling.

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

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.

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

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

Listen to the Pixels

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.

A Survey on Fuzzy Set Theoretic Approaches for Image Segmentation

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

Not Too Deep CNN for Face Detection in Real Life Scenario

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.

Classification of Citation in Scientific Articles

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.

The devil is in the details: Video Quality Enhancement Approaches

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.