M. Saquib Sarfraz

Senior Scientist Computer Vision, Machine Learning, AI

I am an active researcher in the field of computer vision and machine learning. I recieved a PhD degree in computer vision from Technical University of Berlin, Germany in 2009. At present, I share my time both at Mercedes-Benz in the Autonomous Systems Unit as Lead Deep Learning and at Karlsruhe Institue of Technology (KIT) as a Senior Scientist and Lecturer.. At Mercedes-Benz, my responsibilities include setting/innovate the strategic computer vision related projects for ADAS and smart factory. At the CV-HCI lab KIT, I am the team lead for the work in the direction of perception of people for HCI & surveillance related applications and also member of several related funded projects. Before moving to KIT I served as an assistant professor (From 2009 till 2012) at the Electrical Engineering department of COMSATS Institute of Technology in Lahore, Pakistan. There I founded and directed the Computer Vision Research Group.

Research Interests: Deep Learning, Image and Video Understanding


Jun 17, 2023 Outstanding Reviewer Award at CVPR 2023 :1st_place_medal:
Sep 15, 2022 Paper accepted at NeurIPS 2022 on object detectors’ calibration!
Mar 5, 2022 Paper accepted at CVPR 2022 on dimensionality reduction and visualization!
Jun 19, 2021 Outstanding Reviewer Awards at CVPR 2020, CVPR 2021 and ICCV 2021 :1st_place_medal:
Jan 1, 2017 Press/Media coverage on Thermal to Visible Face Recognition for night-time surveillance

selected publications

  1. CVPR
    Hierarchical Nearest Neighbor Graph Embedding for Efficient Dimensionality Reduction
    Sarfraz, M Saquib, Koulakis, Marios, Seibold, Constantin, and Stiefelhagen, Rainer
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022
  2. CVPR
    Temporally-Weighted Hierarchical Clustering for Unsupervised Action Segmentation
    Sarfraz, M Saquib, Murray, Naila, Sharma, Vivek, Diba, Ali, Van Gool, Luc, and Stiefelhagen, Rainer
    In IEEE/CVF International Conference on Computer Vision and Pattern Recognition (CVPR) 2021
  3. CVPR
    Efficient parameter-free clustering using first neighbor relations
    Sarfraz, M Saquib, Sharma, Vivek, and Stiefelhagen, Rainer
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2019
  4. BMVC
    Content and Colour Distillation for Learning Image Translations with the Spatial Profile Loss
    Sarfraz, M Saquib, Seibold, Constantin, Khalid, Haroon, and Stiefelhagen, Rainer
    In 30th British Machine Vision Conference, (BMVC) 2019
  5. CVPR
    A pose-sensitive embedding for person re-identification with expanded cross neighborhood re-ranking
    Sarfraz, M Saquib, Schumann, Arne, Eberle, Andreas, and Stiefelhagen, Rainer
    In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2018