Deepak Kumar

PhD. candidate at University of Massachussets, Dartmouth

I am doctoral candidate in Engineering and Applied science program with a concentration in Computer and Information sciences at University of Massachusetts Dartmouth. I have completed my master’s in data science from University of Massachusetts Dartmouth and my bachelor’s in computer science from SZABIST (Karachi, Pakistan).

My research focuses on computer vision, transfer learning, adversarial learning and knowledge distillation. I'm currently investigating a novel way to attack multi-modality, multi-view action recognition systems, as well as proposing a defense mechanism to protect those models from various adversarial attacks.

Currently, I am a Graduate Research Assistant at Machine Intelligence and Data Analytics (MIND) Lab at University of Massachusetts, Dartmouth. My advisor is Dr. Ming Shao .



Research and Development Intern, Ultrasound Applications- UII

Philips Research North America, Cambridge
May 2021 - August 2021

Research and Development Intern, Ultrasound Applications- UII

Philips Research North America, Cambridge
May 2020 - August 2020

Research Intern at Ultrasound Imaging and Interventions

Philips Research North America, Cambridge
May 2019 - August 2019

Graduate Research Assistant

University of Massachusetts, Dartmouth
September 2016 - Present

Data Analyst

Center for Data Science-EduEnrich
December 2013 - December 2015

Internee - Pakistan Internet Exchange

Pakistan Telecommunication Limited
June 2012 - August 2012


University of Massachusetts, Dartmouth

Doctor of Philosophy
Computer and Information Sciences
September 2018 - August-2022

University of Massachusetts, Dartmouth

Masters of Science
Data Science
Janurary 2016 - August 2018

Shaheed Zulifkar Ali Bhutto Institute of Science and Technology, Karachi

Bachelors of Science
Computer Science
August 2009 - June 2013


Programming Languages
  • Pytorch, Python, R Matlab, HTML/CSS/JS, C(Parallel Programming) , C++
Data Tools
  • Tableau, scikit-Learn, Mataplotlib, Numpy, Pandas, NLTK, D3, RapidMiner
machine Learning Packages
  • Keras, Tensor Flow, Caffe, LibSVM


Confrence Paper

  • C. Kumar, D. Kumar, and M. Shao, "Generative Adversarial Attack on Ensemble Clustering" in Winter Conference on Applications of Computer Vision, Janurary, 2022 Paper
  • D. Kumar, C. Kumar, and M. Shao, "Collaborative Knowledge Distillation for Incomplete Multi-view Action Prediction" in Image and Vision Computing Journal, Janurary, 2021 Paper
  • D. Kumar, C. Kumar, C. Seah, S. Xia and M. Shao, "Finding Achilles' Heel: Adversarial Attack on Multi-modal Action Recognition" in 2020 ACM International Conference on Multimedia, Seattle, WA, USA, 2020 Paper & PPT
  • D. Kumar, C. Kumar and M. Shao, "Cross-database mammographic image analysis through unsupervised domain adaptation," 2017 IEEE International Conference on Big Data (Big Data), Boston, MA, USA, 2017 Paper | PPT | Code


  • MS Thesis: "Cross-View Action Recognition via Joint Dictionary and Transfer Learning" PPT | Abstract | Thesis


  • 2017 NECV: Cross-Database Mammographic Image Analysis through Unsupervised Domain Adaptation PPT | Poster
  • 2018 NECV: Cross-View Action Recognition via Joint Dictionary and Transfer Learning PPT