2 papers
eess.IV2021
Improving Autoencoder Training Performance for Hyperspectral Unmixing with Network Reinitialisation
Kamil Książek, Przemysław Głomb, Michał Romaszewski +3
Neural networks, in particular autoencoders, are one of the most promising solutions for unmixing hyperspectral data, i.e. reconstructing the spectra of observed substances (endmem…
cs.CV2021
Hard hat wearing detection based on head keypoint localization
Bartosz Wójcik, Mateusz Żarski, Kamil Książek +2
In recent years, a lot of attention is paid to deep learning methods in the context of vision-based construction site safety systems, especially regarding personal protective equip…