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

  • Köse, N.; Köpüklü, O.; Unnervik, A.; Rigoll, G.: Real-Time Driver State Monitoring Using a CNN Based Spatio-Temporal Approach. 2019 more…
  • 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 more…
  • Köpüklü, O.; Rong, Y.; Rigoll, G.: Talking with Your Hands: Scaling Hand Gestures and Recognition with CNNs. 2019 more…
  • Köpüklü. O.; Herzog, F.; Rigoll, G.: Comparative Analysis of CNN-based Spatiotemporal Reasoning in Videos. 2019 more…
  • Köpüklü, O.; Köse, N.; Gunduz, A.; Rigoll, G.: Resource Efficient 3D Convolutional Neural Networks. 2019 more… Full text (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 more…
  • 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 more… Full text ( 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 more… Full text ( 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 more… Full text ( DOI ) Full text (mediaTUM)
  • Köpüklü, O.; Wei, X.; Rigoll, G.: You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization. , 2019 more… Full text (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 more… Full text (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 more… Full text (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

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)