Pramod Murthy
E-Mail: | pramod.murthy@dfki.de |
---|---|
Position: | Researcher |
Phone: | +49 631 20575-5097 |
Pramod Murthy received his Masters from TU Kaiserslautern, Germany. He completed Masters thesis titled Spatio-Temporal Convolutional Neural Network based Human Pose estimation in May 2016. Prior to pursuing masters, he professionally worked on various mobile application platforms for over 5 years.
His research interests are Computer Vision, Natural Language Processing and machine learning.
In the Augmented Vision group, he currently focuses on deep neural network architectures for human motion capture (tracking) in 2D / 3D using monocular camera images.
Please visit my website for more information.
In-Domain Inversion for Improved 3D Face Alignment on Asymmetrical Expressions
In: Proceedings of the 18th IEEE International Conference on Automatic Face and Gesture Recognition. IEEE International Conference on Automatic Face and Gesture Recognition (FG-2024), May 27-31, Istanbul, Turkey, IEEE, 5/2024.
Details
| Link 1
Magnetometer Robust Deep Human Pose Regression With Uncertainty Prediction Using Sparse Body Worn Magnetic Inertial Measurement Units
IEEE Access (IEEE) 9 Seiten 36657-36673 IEEE 2/2021 .
Details
| Link 1
| Link 2
Generation of Human Images with Clothing using Advanced Conditional Generative Adversarial Networks, International Conference on Deep Learning Theory and Applications (DeLTA 2020)
In: Ana Fred; Kurosh Madani (Hrsg.). Proceedings of the 1st International Conference on Deep Learning Theory and Applications DeLTA 2020. International Conference on Deep Learning Theory and Applications (DeLTA-2020), July 8-10, Pages 30-41, Vol. 1, ISBN 978-989-758-441-1, SciTePress, 2020.
Details
| Link 1
Fully Automatic Multi-person Human Motion Capture for VR Applications
EuroVR (EuroVR-2018), October 22-23, London, United Kingdom
Details
| Link 1
3D Human Pose Tracking inside Car using Single RGB Spherical Camera
ACM Chapters Computer Science in Cars Symposium (CSCS-17), July 6, Munich, Germany
Details
| Link 1