matteo dunnhofer

Marie Skłodowska-Curie Postdoctoral Fellow
2022_rect_opt.jpeg

Lassonde Building, York University, 4700 Keele St, Toronto ON, M3J 1P3 Canada

matteo.dunnhofer@uniud.it matteo24@yorku.ca

I am currently a Marie Skłodowska-Curie Postdoctoral Fellow (employed as RTT). I work between the Department of Mathematics, Computer Science, and Physics of the University of Udine (Udine, Italy), and the Centre for Vision Research at York University (Toronto, Canada).

I come from Tarvisio, a small town located in the Italian Alps. I received the BSc and MSc in Computer Science and the PhD in Industrial and Information Engineering from the University of Udine in 2016, 2018, and 2022 respectively. I have been a visiting student at the Australian Centre for Robotic Vision of the Queensland University of Technology (Brisbane, Australia). More recently, I spent time as a visiting researcher at the Massachusetts Institute of Technology (Cambridge, USA), and at the University of Alcalà (Madrid, Spain).

My research interests revolve around deep learning for computer vision, in particular I like to develop visual object tracking algorithms.

news

Dec 01, 2024

The SkiTB Visual Tracking Challenge is now open! Results will be presented at the CV4WS workshop at WACV 2025.

Nov 01, 2024

Moved to York University in Toronto to start my MSCA Fellowship!

Oct 05, 2024

A new edition of the workshop on computer vision in winter sports is organized in conjuction with WACV 2025!

Sep 10, 2024

One paper on efficient vision backbones accepted to WACV 2025!

Aug 01, 2024

We will present a demo on computer vision for skiing analysis at ECCV 2024!

selected publications

  1. cviu2024.png
    Visual tracking in camera-switching outdoor sport videos: Benchmark and baselines for skiing
    Matteo Dunnhofer, and Christian Micheloni
    Computer Vision and Image Understanding, 2024
  2. ijcv2023.jpg
    Visual Object Tracking in First Person Vision
    Matteo Dunnhofer, Antonino Furnari, Giovanni Maria Farinella, and Christian Micheloni
    International Journal of Computer Vision, 2023
  3. cvprw2023.jpg
    Visualizing Skiers’ Trajectories in Monocular Videos
    Matteo Dunnhofer, Luca Sordi, and Christian Micheloni
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), CVsports workshop, 2023
  4. imavis2022.png
    Combining complementary trackers for enhanced long-term visual object tracking
    Matteo Dunnhofer, Kristian Simonato, and Christian Micheloni
    Image and Vision Computing, 2022
  5. ral2021.jpg
    Weakly-Supervised Domain Adaptation of Deep Regression Trackers via Reinforced Knowledge Distillation
    Matteo Dunnhofer, Niki Martinel, and Christian Micheloni
    IEEE Robotics and Automation Letters, 2021
  6. midl2021.png
    Improving MRI-based knee disorder diagnosis with pyramidal feature details
    Matteo Dunnhofer, Niki Martinel, and Christian Micheloni
    In International Conference on Medical Imaging with Deep Learning (MIDL), 2021
  7. media2020.jpg
    Siam-U-Net: encoder-decoder siamese network for knee cartilage tracking in ultrasound images
    Matteo Dunnhofer, Maria Antico, Fumio Sasazawa, Yu Takeda, Saskia Camps, Niki Martinel, Christian Micheloni, and 2 more authors
    Medical Image Analysis, 2020
  8. accv2020.jpg
    Tracking-by-Trackers with a Distilled and Reinforced Model
    Matteo Dunnhofer, Niki Martinel, and Christian Micheloni
    In Asian Conference on Computer Vision (ACCV), 2020
  9. iccvw2019.png
    Visual Tracking by means of Deep Reinforcement Learning and an Expert Demonstrator
    Matteo Dunnhofer, Niki Martinel, Gian Luca Foresti, and Christian Micheloni
    In IEEE/CVF International Conference on Computer Vision (ICCV), Visual Object Tracking Challenge VOT2019 workshop, 2019