About me

I am a computer vision researcher and PhD student in the Machine Learning and Perception Lab at the University of Udine, advised by Christian Micheloni. My research focuses on hardware-efficient neural network design for efficient inference — in particular, building vision backbones that achieve better speed-accuracy trade-offs on real hardware by going beyond traditional multiply-accumulate (MAC) count metrics.

I also work on egocentric vision, video frame interpolation, and object tracking. Previously, I received my M.Sc. in Informatik from TU Darmstadt (2020–2022).

News

  • Jun 2026 Paper CPUBone accepted at CVPR Findings 2026.
  • May 2026 Beyond MACs: Hardware Efficient Architecture Design for Vision Backbones published in IJCV.
  • 2025 Paper on Online Episodic Memory Visual Query Localization accepted at WACV 2026.
  • Sep 2025 T-EVO accepted at ICIAP 2025.
  • March 2025 LowFormer presented at WACV 2025.

Research Interests

Hardware-Efficient Neural Networks Vision Backbones Convolutional & Transformer Architectures Efficient Inference Video Frame Interpolation Object Detection & Tracking Egocentric Vision Person Re-Identification

Publications

CPUBone: Efficient Vision Backbone Design for Devices with Low Parallelization Capabilities
Moritz Nottebaum, Matteo Dunnhofer, Christian Micheloni
CVPR Findings, 2026
Hardware-Efficient Neural Networks Vision Backbones Efficient Inference
arXiv Code
Beyond MACs: Hardware Efficient Architecture Design for Vision Backbones
Moritz Nottebaum, Matteo Dunnhofer, Christian Micheloni
International Journal of Computer Vision (IJCV), 2026
Hardware-Efficient Neural Networks Vision Backbones Efficient Inference
arXiv IJCV
Online Episodic Memory Visual Query Localization with Egocentric Streaming Object Memory
Zaira Manigrasso, Matteo Dunnhofer, Antonino Furnari, Moritz Nottebaum, Antonio Finocchiaro, Davide Marana, Rosario Forte, Giovanni Maria Farinella, Christian Micheloni
WACV, 2026
Egocentric Vision Object Detection & Tracking
arXiv
T-EVO: Tracking in Egovision for Online Visual Episodic Memory
Zaira Manigrasso, Antonio Finocchiaro, Davide Marana, Rosario Forte, Moritz Nottebaum, Matteo Dunnhofer, Giovanni Maria Farinella, Antonino Furnari, Christian Micheloni
ICIAP, 2025 — Springer LNCS
Egocentric Vision Object Detection & Tracking
LowFormer: Hardware Efficient Design for Convolutional Transformer Backbones
Moritz Nottebaum, Matteo Dunnhofer, Christian Micheloni
WACV, 2025
Hardware-Efficient Neural Networks Vision Backbones Convolutional & Transformer Architectures
arXiv WACV Code
Efficient Feature Extraction for High-resolution Video Frame Interpolation
Moritz Nottebaum, Stefan Roth, Simone Schaub-Meyer
BMVC, 2022
Video Frame Interpolation
arXiv BMVC Code
Person Re-Identification in a Car Seat: Comparison of Cosine Similarity and Triplet Loss based approaches on Capacitive Proximity Sensing data
Silvia Rus, Moritz Nottebaum, Arjan Kuijper
PETRA, 2021
Person Re-Identification
ACM