English

One-Shot-Learning Gesture Recognition using HOG-HOF Features

Computer Vision and Pattern Recognition 2014-02-18 v2

Abstract

The purpose of this paper is to describe one-shot-learning gesture recognition systems developed on the \textit{ChaLearn Gesture Dataset}. We use RGB and depth images 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 capture 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 combination of HOG-HOF descriptors together with variants of Dynamic Time Warping technique. Both methods outperform other published methods and help narrow down the gap between human performance and algorithms on this task. The code has been made publicly available in the MLOSS repository.

Keywords

Cite

@article{arxiv.1312.4190,
  title  = {One-Shot-Learning Gesture Recognition using HOG-HOF Features},
  author = {Jakub Konečný and Michal Hagara},
  journal= {arXiv preprint arXiv:1312.4190},
  year   = {2014}
}

Comments

20 pages, 10 figures, 2 tables To appear in Journal of Machine Learning Research subject to minor revision

R2 v1 2026-06-22T02:27:59.579Z