- Do We Still Need Non-Maximum Suppression? Accurate Confidence Estimates and Implicit Duplication Modeling with IoU-Aware Calibration. , 2023 mehr… Volltext ( DOI )
- EarlyBird: Early-Fusion for Multi-View Tracking in the Bird's Eye View. , 2023 mehr… Volltext ( DOI ) Volltext (mediaTUM)
- The Box Size Confidence Bias Harms Your Object Detector. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2023 mehr… Volltext (mediaTUM)
- Synthehicle: Multi-Vehicle Multi-Camera Tracking in Virtual Cities. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops, 2023 mehr… Volltext (mediaTUM)
- Introducing A Framework for Single-Human Tracking Using Event-Based Cameras. 2023 IEEE International Conference on Image Processing (ICIP), IEEE, 2023 mehr… Volltext ( DOI ) Volltext (mediaTUM)
- Face Morphing: Fooling a Face Recognition System Is Simple! , 2022 mehr… Volltext ( DOI ) Volltext (mediaTUM)
- Towards a Deeper Understanding of Skeleton-Based Gait Recognition. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2022 mehr… Volltext (mediaTUM)
- Comparative Analysis of CNN-based Spatiotemporal Reasoning in Videos. Deep Learning for Human-Centric Activity Understanding Workshop at International Conference on Pattern Recognition, 2021 mehr…
- Gaitgraph: Graph Convolutional Network for Skeleton-Based Gait Recognition. 2021 IEEE International Conference on Image Processing (ICIP), IEEE, 2021, 2314-2318 mehr… Volltext ( DOI )
- Lightweight Multi-Branch Network For Person Re-Identification. 2021 IEEE International Conference on Image Processing (ICIP), IEEE, 2021, 1129-1133 mehr… Volltext ( DOI )
- Face Aggregation Network For Video Face Recognition. 2021 IEEE International Conference on Image Processing (ICIP), IEEE, 2021, 2973-2977 mehr… Volltext ( DOI ) Volltext (mediaTUM)
- Comparative Analysis of CNN-based Spatiotemporal Reasoning in Videos. 2019 mehr…
Fabian Herzog, M.Sc.
Technische Universität München
Lehrstuhl für Mensch - Maschine - Kommunikation (Prof. Hemmert komm.)
Postadresse
Postal:
Theresienstr. 90
80333 München
- Tel.: +49 (89) 289 - 28563
- Homepage
- fabian.herzog@tum.de
Forschungsgebiete
• Computer Vision
• Object Tracking
• (Geometric) Deep Learning
Publikationen
Projekte
Überwachungsvideos treffen tragbare Kameras in der Cloud
Projektpartner: Hebrew University Jerusalem, Al Quds University Jerusalem
Projektzeitraum: 15.03.2019 - 14.03.2022
Lehre
• Mensch-Maschine-Kommunikation II (SS 2022)
• Mensch-Maschine-Kommunikation II (SS 2022)
• Praktikum PETIT (WS 2020)
• Mensch-Maschine-Kommunikation II (SS 2020)
• Praktikum PETIT (WS 2019)
• Praktikum PSST (WS 2019)
• Mensch-Maschine-Kommunikation II (SS 2019)
Studentische Arbeiten
Bei Anfragen zu studentischen Arbeiten reichen Sie bitte folgende Unterlagen mit ein:
• Aktueller Lebenslauf
• Notenauszug
• Bisherige Erfahrungen aus dem Themengebiet
• Starttermin
Offen
Alle ausgeschriebenen Arbeiten finden Sie hier.
Abgeschlossen
2021
• Multiple Object Tracking by Graph Convolutional Message Passing (Master's Thesis)
• Fast and Lightweight Graph Convolutional Tracking (Bachelor's Thesis)
• Spatial Temporal Modeling for Multiple Object Tracking (Bachelor's Thesis)
• Robust One-Stage Tracking and Segmentation (Master's Thesis)
2020
• Gait Recognition on a Linux-based Smart Home Camera (Bachlor's Thesis)
• Multiple Person Tracking in Non-Overlapping Video Streams (Master's Thesis)
• Person Re-Identification on Synthetic Data (Bachelor's Thesis)
2019
• Cross-View Gait Recognition by Patch Alignment (Scientific Seminar)
• A Semantic 3D Reconstruction (Research Internship)
• Extension of Robust PCA for Fast Online Foreground Detection in Videos (Bachelor's Thesis)