no code implementations • International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT) 2021 • Stepan Jezek, Martin Jonak, Radim Burget, Pavel Dvorak, Milos Skotak
In order to test the performance of state-of-the-art (SOTA) AD methods under conditions of variable spatial orientation, position and distance of multiple objects concerning the camera at different light intensities and with a non-homogeneous background, it is necessary to create a new dataset.
no code implementations • 23 Nov 2020 • Martin Kolarik, Radim Burget, Kamil Riha
Our results show the effectiveness of Instance Normalization in the limited batch size neural network training environment.
1 code implementation • 23 Nov 2020 • Martin Kolarik, Radim Burget, Carlos M. Travieso-Gonzalez, Jan Kocica
We present a novel approach of 2D to 3D transfer learning based on mapping pre-trained 2D convolutional neural network weights into planar 3D kernels.
no code implementations • 13 Jul 2019 • Pavol Harar, Zoltan Galaz, Jesus B. Alonso-Hernandez, Jiri Mekyska, Radim Burget, Zdenek Smekal
Automatic objective non-invasive detection of pathological voice based on computerized analysis of acoustic signals can play an important role in early diagnosis, progression tracking and even effective treatment of pathological voices.
no code implementations • 12 Jul 2019 • Pavol Harar, Jesus B. Alonso-Hernandez, Jiri Mekyska, Zoltan Galaz, Radim Burget, Zdenek Smekal
This paper describes a preliminary investigation of Voice Pathology Detection using Deep Neural Networks (DNN).
2 code implementations • Applied Sciences 2019 • Martin Kolařík, Radim Burget, Václav Uher, Kamil Říha, Malay Kishore Dutta
The method has been evaluated on MRI brain 3D volumetric dataset and CT thoracic scan dataset for spine segmentation.