Muhammad Jehanzeb Mirza

TU Graz, Austria.

CV | Linkedin | Google Scholar | Github | Email

Hi, I am Jehanzeb Mirza. I recently received my PhD. in Computer Vision from TU Graz, Austria, where I was advised by Professor Horst Bischof, and Professor Serge Belongie served as an external referee. I did my Masters from KIT, Germany in Electrical Engineering and Information Technology (ETIT) and received my Bachelors in Electrical Engineering (EE) from NUST, Pakistan.

My PhD. research mainly focused on learning from unlabeled data. During my Phd., I have worked with various data modalities including images, point clouds, videos, radar signals and most recently natural language. I am particularly interested in Self-Supervised learning for uni-modal models and also Multi-Modal Learning for vision-language models.


  • muhammad.mirza [at] icg.tugraz.at

  • Graz, Austria


  • Ph.D. in Computer Vision (2021 - 2024)

    TU Graz, Austria.

    MS in ETIT (2017 - 2020)

    KIT, Germany.

    BS in EE (2013 - 2017)

    NUST, Pakistan

Recent News


Selected Publications

Supervised Student Works (Selected)

  • Bachelor Thesis: Test-Time Adaptation for Multi-Modal Vision-Language Models (Ongoing).
  • Master Thesis: Online Test-Time Training for 3D point clouds with Masked Autoencoders (Completed) [ paper @ ICCV ]
  • Bachelor Thesis: Online Domain Incremental Learning for Driving in Adverse Weather Conditions (Completed) [ paper @ IEEE IV (oral) ]
  • Master Thesis: How Much are Data Augmentations Worth for Representation Learning in 3D Point Clouds (Completed).