Foto von Stefan Hörmann

Stefan Hörmann, M.Sc.

Technische Universität München

Lehrstuhl für Mensch - Maschine - Kommunikation (Prof. Rigoll)

Postadresse

Postal:
Arcisstr. 21
80333 München

Forschungsgebiete

• Deep Learning
• Computer Vision
• Face Recognition

Publikationen

  • Hörmann, S.; Knoche, M.; Babaee, Ma.; Köpüklü, O.; Rigoll, G.: Outlier-Robust Neural Aggregation Network for Video Face Identification. Proc. International Conference on Image Processing (ICIP 2019), 2019, pp. 1675-1679 mehr… Volltext ( DOI )
  • Babaee, Ma.; Zhu, Y.; Köpüklü, O.; Hörmann, S.; Rigoll, G.: Gait Energy Image Restoration Using Generative Adversarial Networks. Proc. International Conference on Image Processing (ICIP 2019), 2019, pp. 2596-2600 mehr… Volltext ( DOI )
  • Köpüklü, O.; Babaee, Ma.; Hörmann, S.; Rigoll, G.: Convolutional Neural Networks with Layer Reuse. Proc. 26th IEEE International Conference on Image Processing (ICIP 2019), 2019, pp. 345-349 mehr… Volltext ( DOI ) Volltext (mediaTUM)
  • Hörmann, S.; Comulada Simpson, E.; Bahram, M.: A generic Steering Wheel Torque Model using Neural Networks. Proc. Driving Simulation Conference, 2017, 2017, pp. 43-50 mehr…

Gutachtertätigkeiten

EURASIP JIVP (2018)

Projekte

Datengetriebene Wertschöpfung von Multimedia Content
Projektpartner: ProSiebenSat.1 Media SE, munich media intelligence
Projektzeitraum: 01.04.2017 - 30.09.2018

Lehre

• Signaltheorie (WS 2019)
• Signal Represenation TUMAsia (WS 2019)
• Signaldarstellung Übung für Wiederholer (SS 2019, SS 2018)
• Signaldarstellung für MSE (WS 2018)
• Signaldarstellung (WS 2018, WS 2017)

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

2019
• Dynamic Feature Learning for Partial Face Recognition (Scientific Seminar)
• A Survey on Set-Based Face Recognition (Research Internship)
• Attention Based Fusion Using Feature Aggregation for Audio-Visual Person Verification (Master's Thesis)
• Enhanced Driver Gaze Classification using Video Data together with Car Bus Signals (Master's Thesis)
• Burst Image Deblurring Using Permutation Invariant Convolutional Neural Networks (Scientific Seminar)
• Multicolumn Networks for Face Recognition (Scientific Seminar)
• Semi-automatic dataset labeling using pretrained neural networks (Research Internship)
• Facial Emotion Recognition for Automotive Applications using RGB-D Information (Master's Thesis)
• Gesichtsbasierte Schauspielererkennung in Filmen (Bachelor's Thesis)
• Comparison of different GANs for Face Recognition (Research Internship)
• Performance Evaluation of GANs for Face Recognition Tasks against Image Degradations (Master's Thesis)

2018
• Exploring Disentangled Feature Representation Beyond Face Identification (Scientific Seminar)
• Seeing Voices and Hearing Faces: Cross-modal biometric matching (Scientific Seminar)
• Facelet-Bank for Fast Portrait Manipulation (Scientific Seminar)
• Joint Identification and Outlier Detection of Face Clusters Using an Aggregation Network (Master's Thesis)
• Region-based face detection with a fully-convolutional neural network (Master's Thesis)
• Disentangled Representation Learning GAN for Pose-Invariant Face Recognition (Scientific Seminar)
• Class Rectification Hard Mining for Imbalanced Deep Learning (Scientific Seminar)

2017
• Detecting Masked Faces in the Wild with LLE-CNNs (Scientific Seminar)
• Finding Tiny Faces (Scientific Seminar)