Contact Huseyin Coskun Email: huseyin=coskun|[at]|tum.de (replace '=' with '.') Position: PhD Candidate Address: Chair for Computer Aided Medical Procedures & Augmented Reality Fakultät für Informatik Technische Universität München Boltzmannstr. 3 85748 Garching b. München Office: MI 03.13.039

Active research projects

Patient Pose Estimation In this project, we investigate machine learning algorithms for the purpose of real-time 3D human pose estimation in a hospital monitoring scenario. Patients are typically covered with a blanket and the bed is cluttered with books, laptops and other everyday objects. This makes the task more challenging than background-free human pose estimation. With the constraint of day and night monitoring capacity, we have recently published a method based on depth data which will be presented at MICCAI 2016, see link to the paper below. On this project page, you can also find the used dataset and training code. For further information, please contact Felix Achilles.

Student Projects

Feel free to contact me to any of the following projects or if you have your own project/thesis ideas. Sometimes I have proposals not yet added to the list below.

Available

Running
DA/MA/BA	Weakly-Supervised Action Segmentation (Huseyin Coskun, Prof. Nassir Navab, Federico Tombari)

Finished
DA/MA/BA	Action Recognition and Generation With RNNs (Huseyin Coskun, Christian Rupprecht, Federico Tombari, Prof. Nassir Navab)

Research Topics

I am currently involved in conducting research in the following research areas.

• Temporal alignment
• Activity recognition and segmentation
• Human pose estimation.
• Recurrent neural networks.

Education

• 2016 - Master in Artificial Intelligence / Universitat Politècnica de Catalunya (UPC), Barcelona, Spain
• 2011 - Mathematics Engineering / Istanbul Technical University (ITU), Istanbul, Turkey

Teaching Assistance

• Praktikum: Machine Learning in Medical Imaging (2017WiSe)
• Seminar: Foundations of Computer Vision (2017WiSe)
• Seminar: Recent Trends in 3D Computer Vision and Deep Learning (2017WiSe)
• Praktikum: Perception and Learning in Robotics and Augmented Reality (2017SoSe)
• Seminar: Recent Trends in 3D Computer Vision (2016WiSe)

List of Publications

2019
	J. Postel, F. Ferroni, H. Coskun, N. Navab, F. Tombari Sampling-free Epistemic Uncertainty Estimation Using Approximated Variance Propagation International Conference on Computer Vision (ICCV), Seoul, Korea, October 2019 [oral]. (bib)
2017
	H. Coskun, F. Achilles, R. DiPietro, N. Navab, F. Tombari Long Short-Term Memory Kalman Filters:Recurrent Neural Estimators for Pose Regularization International Conference on Computer Vision (ICCV), Venice, Italy, October 2017 (bib)
2016
	F. Achilles, A.E. Ichim, H. Coskun, F. Tombari, S. Noachtar, N. Navab PatientMocap: Human Pose Estimation under Blanket Occlusion for Hospital Monitoring Applications Proceedings of the 19th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), Athens, Greece, October 2016 (bib)