The purpose of this paper is to describe one-shot-learning gesture recognition systems developed on the ChaLearn Gesture Dataset (ChaLearn). We use RGB and depth im-ages and combine appearance (Histograms of Oriented Gradients) and motion descriptors (Histogram of Optical Flow) for parallel temporal segmentation and recognition. The Quadratic-Chi distance family is used to measure differences between histograms to cap-ture cross-bin relationships. We also propose a new algorithm for trimming videos-to remove all the unimportant frames from videos. We present two methods that use a com-bination of HOG-HOF descriptors together with variants of a Dynamic Time Warping technique. Both methods outperform other published methods and help narrow the gap between human performance and algorithms on this task. The code is publicly available in the MLOSS repository. © 2014 Jakub Konečný and Michal Hagara.
CITATION STYLE
Konečný, J., & Hagara, M. (2014). One-shot-learning gesture recognition using HOG-HOF features. Journal of Machine Learning Research, 15, 2513–2532. https://doi.org/10.1007/978-3-319-57021-1_12
Mendeley helps you to discover research relevant for your work.