Fabian Herzog

I am a research assistant and PhD student at the Institute of Human-Machine Communication of the Technical University of Munich, Germany. My main research is in computer vision and pattern recognition.

Prior to joining TU Munich, I did my Master's in Scientific Computing in Göttingen with a focus on mathematical image processing.

Email / Google Scholar / Github / Twitter / LinkedIn

Research

My research is on machine learning and computer vision for video processing. Here are my recent projects and papers:

	The Box Size Confidence Bias Harms Your Object Detector J. Gilg, T. Teepe, F. Herzog, and G. Rigoll arXiv, 2022 arXiv / code We demonstrate how to modify the histogram binning calibration to improve performance through conditional confidence calibration.
	Face Aggregation Network For Video Face Recognition S. Hörmann, Z. Chao, M. Knoche, F. Herzog, and G. Rigoll IEEE International Conference on Image Processing (ICIP), 2021 IEEE Article *Accepted for ICIP 2021* We suggest a permutation invariant U-Net architecture capable of processing an arbitrary number of frames in video face recognition.
	GaitGraph: Graph Convolutional Network for Skeleton-Based Gait Recognition T. Teepe, A. Khan, J. Gilg, F. Herzog, S. Hörmann, and G. Rigoll IEEE International Conference on Image Processing (ICIP), 2021 arXiv / code *Accepted for ICIP 2021* A novel Graph Convolutional Network (GCN) to obtain a modern model-based approach for gait recognition.
	Lightweight Multi-Branch Network for Person Re-Identification F. Herzog, X. Ji, T. Teepe, S. Hörmann, J. Gilg, and G. Rigoll IEEE International Conference on Image Processing (ICIP), 2021 arXiv / code *Accepted for ICIP 2021* Lightweight network that combines global, part-based, and channel features in a unified multi-branch architecture.
	Dissected 3D CNNs: Temporal Skip Connections for Efficient Online Video Processing O. Köpüklü, S. Hörmann, F. Herzog, H. Cevikalp, and G. Rigoll arXiv, 2020 arXiv / code *Accepted for Computer Vision and Image Understanding Journal* We propose dissected 3D CNNs to address several serious handicaps of 3D ResNet models during online operation.
	Comparative Analysis of CNN-Based Spatiotemporal Reasoning in Videos O. Köpüklü, F. Herzog, and G. Rigoll ICPR International Workshops and Challenges. ICPR 2021. arXiv / code / video / publication *Accepted for ICPR International Workshops 2021* A comparative analysis of different spatiotemporal modeling techniques for action and gesture recognition.

Teaching

Summer 2021

Human-Machine Communication II (Exercises)

Winter 2020 / 2021

Practical Course on Audio and Image Processing

Summer 2020

Human-Machine Communication II (Exercises)
~~Musical Acoustics (Assistance)~~ (canceled due to COVID-19)

Winter 2019 / 2020

Practical Course on Audio and Image Processing
Practical Course on Systems Engineering

Summer 2019

Human-Machine Communication II (Exercises)

Supervision

I'm supervising theses in the areas of computer vision and pattern recognition. Due to the high number of applications, I can only respond to complete applications with current CV, transcript of records and motivation letter. I do not supervise external theses.

Professional Service

Reviewer for the NVIDIA AI City Challenge 2021 CVPR Workshop

This website template was stolen with permission from Jon Barron. Imprint.