Picture of Okan Köpüklü

Okan Köpüklü, M.Sc.

Technical University of Munich

Chair of Human-Machine Communication (Prof. Rigoll)

Postal address

Postal:
Arcisstr. 21
80333 München

Research Areas

• Spatiotemporal Action Localization
• Action/Activity Recognition
• Hand Gesture Recognition

Publications

  • Kayhan, Mert; Köpüklü, Okan; Sarhan, Mhd Hasan; Yigitsoy, Mehmet; Eslami, Abouzar; Rigoll, Gerhard: Deep Attention Based Semi-Supervised 2D-Pose Estimation for Surgical Instruments. Artificial Intelligence for Healthcare Applications Workshop at International Conference on Pattern Recognition, 2021 mehr…
  • Köpüklü, Okan; Herzog, Fabian; Rigoll, Gerhard: 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…
  • Köpüklü, Okan; Zheng, Jiapeng; Xu, Hang; Rigoll, Gerhard: Driver Anomaly Detection: A Dataset and Contrastive Learning Approach. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2021 mehr…
  • Köpüklü, O.; Gunduz, A.; Köse, N.; Rigoll, G.: Online Dynamic Hand Gesture Recognition Including Efficiency Analysis. IEEE Transactions on Biometrics, Behavior, and Identity Science (Vol. 2, Issue 2), 2020, pp. 85-97 mehr… Volltext ( DOI )
  • Köpüklü, Okan; Gunduz, Ahmet; Köse, Neslihan; Rigoll, Gerhard: Online dynamic hand gesture recognition including efficiency analysis. IEEE Transactions on Biometrics, Behavior, and Identity Science 2 (2), 2020, 85--97 mehr… Volltext ( DOI )
  • Köpüklü, O.; Ledwon, T.; Rong, Y.; Köse, N.; Rigoll, G.: DriverMHG: A Multi-Modal Dataset for Dynamic Recognition of Driver Micro Hand Gestures and a Real-Time Recognition Framework. 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020), 2020, pp. 275-282 mehr…
  • Köpüklü, Okan; Ledwon, Thomas; Rong, Yao; Köse, Neslihan; Rigoll, Gerhard: DriverMHG: A Multi-Modal Dataset for Dynamic Recognition of Driver Micro Hand Gestures and a Real-Time Recognition Framework. 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020), 2020 mehr…
  • Kayhan, M.; Köpüklü, O.; Sarhan, M.H.; Yigitsoy, M.; Eslami, A.; Rigol, G.l: Deep Attention Based Semi-Supervised 2D-Pose Estimation for Surgical Instruments. 2019 mehr…
  • Köpüklü, O.; Rong, Y.; Rigoll, G.: Talking with Your Hands: Scaling Hand Gestures and Recognition with CNNs. 2019 mehr…
  • Köse, Neslihan; Köpüklü, Okan; Unnervik, Alexander; Rigoll, Gerhard: Real-Time Driver State Monitoring Using a CNN Based Spatio-Temporal Approach. 2019 mehr…
  • Köpüklü, O.; Köse, N.; Gunduz, A.; Rigoll, G.: Resource Efficient 3D Convolutional Neural Networks. 2019 mehr… Volltext (mediaTUM)
  • Köpüklü, O.; Gunduz, A.; Köse, N.; Rigoll, G.: Real-time Hand Gesture Detection and Classification Using Convolutional Neural Networks. Proc. IEEE International Conference on Automatic Face and Gesture Recognition (FG 2019), 2019 mehr…
  • 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)
  • Köpüklü, O.; Wei, X.; Rigoll, G.: You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization. , 2019 mehr… Volltext (mediaTUM)
  • Köpüklü, O.; Rigoll, G.: Analysis on Temporal Dimension of Inputs for 3D Convolutional Neural Networks. Proc. Conference on Image Processing, Applications and Systems (IPAS 2018), 2018 mehr… Volltext (mediaTUM)
  • Köpüklü, O.; Köse, N.; Rigoll, G.: Motion Fused Frames: Data Level Fusion Strategy for Hand Gesture Recognition. Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2018, pp. 2216-2224 mehr… Volltext (mediaTUM)

Projects

Trilateral DFG Project "Surveillance Videos meet wearable Cameras on the Cloud"
Partners: Hebrew University Jerusalem, Al Quds University Jerusalem
Period: 15.03.2019 - 14.03.2022

Teaching

Pattern Recognition (SS 2019)

Student Projects

For inquiries regarding any student projects please apply using your most recent CV together with your grade report emphasizing your previous experience in this area and your desired starting date.

Open Topics

You can find all open topics here.

Finished Projects

2020
• Multi-view Contrastive Self-supervised Learning in Action Recognition (Research Internship)
• Multi-Currency Region-of-Interest Detection and Serial Number Recognition Based on Binarized Neural Networks: An Empirical Study (Bachelor's Thesis)
• Comparative analysis of state-of-the-art 3D object detection frameworks with focus on autonomous driving applications (Research Internship)
• A Single-Stage CNN Architecture for Real-Time Spatiotemporal Action Localisation (Master's Thesis)
• Gait Cycle Prediction for Gait Recognition (Master's Thesis)

2019
• Skeletal Hand Model Reconstruction from Depth Images Using a Convolutional Neural Network Framework (Master's Thesis)
• Temporal Association of Frame Detections for Action Tube Generation (Research Internship)
• Unsupervised Monocular Depth Prediction for Indoor Continuous Video Streams (Master's Thesis)
• An Evaluation of Semi Supervised Learning for CNN based 2D-Pose Estimation and Fine-grained Classification Tasks (Master's Thesis)
• Real-Time Driver Anomaly Detection on Multi-View In-Vehicle Video Streams (Master's Thesis)
• Scaling Hand Gestures and Recognition With CNNs (Master's Thesis)
• Inertial Sensor-Based Gesture Recognition on Hearable Devices (Bachelor's Thesis)

2018
• Dynamic Recognition of Driver Micro Hand Gestures Using Convolutional Neural Networks (Master's Thesis)
• Real-time Detection and Classification of Dynamic Hand Gestures (Master's Thesis)
• CNN-based Spatiotemporal Modeling of Video Activity Recognition (Research Internship)
• Video Activity Recognition With Classical Machine Learning Methods (Research Internship)
• Effective Video Augmentation Techniques for Training Convolutional Neural Networks (Bachelor's Thesis)