Sudipta Paul

I am a fifth year PhD student in the Video Computing Group (VCG), at the University of California, Riverside, advised by Dr. Amit K. Roy-Chowdhury. My research interests include Computer Vision, Deep Learning, and Multi-modal Learning.

I completed my undergraduate in Electrical and Electronic Engineering from Bangladesh University of Engineering and Technology, Dhaka, Bangladesh where I worked with Dr. SM Mahbubur Rahman on problems related to affective computing using multimodal data. During Summer 2019, I have worked as a research intern at Mayachitra in Santa Barbara, CA, USA where the work was focused on traffic activity analysis.

Email  /  CV  /  Google Scholar  /  LinkedIn

profile photo
Research Interests

I'm interested in computer vision, machine learning, deep learning, multi-modal learning. Much of my research is about working with multi-modal data to learn the correspondance between different modalities specifically video and text. I also worked on utilizing contextual information to add robustness against label noise.

Updates

  July 2022: Paper accepted in NeurIPS 2022
  July 2022: Paper accepted in ECCV 2022
  Feb. 2022: Paper accepted in Journal of Big Data
  Oct. 2021: Paper accepted in T-IP
  June 2021: Joined Mitsubishi Electric Research Laboratories as research intern
  Aug. 2020: Paper accepted in ECCV 2020
  May 2020: Paper accepted in ICASSP 2020
  June 2019: Joined Mayachitra as research intern

Publications

AVLEN: Audio-Visual-Language Embodied Navigation in 3D Environments
Sudipta Paul, Amit K Roy-Chowdhury, Anoop Cherian
Neural Information Processing Systems (NeurIPS), 2022

Text-based Temporal Localization of Novel Events
Sudipta Paul, Niluthpol Chowdhury Mithun, Amit K Roy-Chowdhury
European Conference on Computer Vision (ECCV), 2022

Text-based Localization of moments in a Video Corpus
Sudipta Paul, Niluthpol Chowdhury Mithun, Amit K Roy-Chowdhury
IEEE Transactions on Image Processing, 2021

Task-agnostic representation learning of multimodal twitter data for downstream applications
Ryan Rivas, Sudipta Paul, Vagelis Hristidis, Evangelos E Papalexakis, Amit K Roy-Chowdhury
Journal of Big Data, 2022

Connecting the Dots: Detecting Adversarial Perturbations Using Context Inconsistency
Shasha Li, Shitong Zhu, Sudipta Paul, Amit Roy-Chowdhury, Chengyu Song, Srikanth Krishnamurthy, Ananthram Swami, Kevin S Chan
European Conference on Computer Vision (ECCV), 2020

Complex Pairwise Activity Analysis Via Instance Level Evolution Reasoning
Sudipta Paul, Carlos Torres, Shivkumar Chandrasekaran, Amit K Roy-Chowdhury
International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2020

Mutual information-based selection of audiovisual affective features to predict instantaneous emotional state
Sudipta Paul, Nurani Saoda, SM Mahbubur Rahman, Dimitrios Hatzinakos
International Conference on Computer and Information Technology (ICCIT), 2016

Exploiting Context for Robustness to Label Noise in Active Learning
Sudipta Paul, Shivkumar Chandrasekaran, B.S. Manjunath, Amit K Roy-Chowdhury
ArXiv Preprint


You can find the template here.