W dniach 7 - 9 września 2022, w Weronie, odbyła się 26th International Conference on Knowledge-Based and Intelligent Information & Engineering Systems (http://kes2022.kesinternational.org/). W trakcie konferencji przedstawiono pracę zrealizowaną w ramach zadania 4 projektu RID: Dawid Warchoł, Mariusz Oszust: Efficient Augmentation of Human Action Recognition Datasets with Warped Windows, https://doi.org/10.1016/j.procs.2022.09.360. Artykuł został opublikowany w czasopiśmie Procedia Computer Science. Konferencja znajduje się na liście MEiN (70 pkt).
Abstract:
In this paper, an approach to augment action recognition time series datasets, devoted to improving the accuracy of deep learning classifiers, is proposed. In the introduced method, two operators are sequentially introduced that perform linear and nonlinear modifications in the time scale of the input time series. The resulting data samples contribute to the variability within classes and allow a deep learning-based classifier to better capture their boundaries, leading to a significant improvement in the classification accuracy. The extensive experiments performed on eight publicly available action recognition datasets using the popular Bidirectional Long Short-Term Memory (BiLSTM) classifier reveal the superiority of the proposed algorithm over related approaches.
