Efficient and robust deep learning models for comprehensive scene understanding

  • Research theme/s:

    Theory and algorithms, services and quality of life (science, technology)

  • Principal investigator (PI):

    Dr. Hisham Cholakka

  • Researcher/s:

    Ankan Kumar Bhunia,  Mustansar Fiaz

  • Funding:

    MBZUAI

  • Department:

    Computer vision

  • Co-PI:

    Nil

  • Student/s

    Dhanalaxmi Gaddam, Mohammed Khaled Mohamed Ahmed Almansoori, Abhishek Singh Gehlot

  • Collaborators / partners:

    Nil

This project focuses on building a comprehensive image and video understanding model that can automatically answer challenging queries such as “what”, “where”, “how”, and “how many related to various visual contents. Here the objective is to develop robust and efficient computer vision frameworks that can be utilized for real-world problems.