Home >

news Help

Publication Information

English:Spectral Graph Skeletons for 3D Action Recognition 
Japanese: Kerola Tommi, 井上中順, 篠田浩一.  
English: Tommi Kerola, Nakamasa Inoue, Koichi Shinoda.  
Language English 
Journal/Book name
English:Proc. Asian Conference on Computer Vision (ACCV) 
Volume, Number, Page         pp. 1-16
Published date Nov. 1, 2014 
English:Springer International Publishing AG, Cham 
Conference name
English:The 12th Asian Conference on Computer Vision (ACCV 2014) 
Conference site
English:University Cultural Centre 
Official URL http://www.accv2014.org/
DOI https://doi.org/10.1007/978-3-319-16817-3_27
Abstract We present spectral graph skeletons (SGS), a novel graph-based method for action recognition from depth cameras. The contribution of this paper is to leverage a spectral graph wavelet transform (SGWT) for creating an overcomplete representation of an action signal lying on a 3D skeleton graph. The resulting SGS descriptor is efficiently computable in time linear in the action sequence length. We investigate the suitability of our method by experiments on three publicly available datasets, resulting in performance comparable to state-of-the-art action recognition approaches. Namely, our method achieves 91.4% accuracy on the challenging MSRAction3D dataset in the cross-subject setting. SGS also achieves 96.0% and 98.8% accuracy on the MSRActionPairs3D and UCF-Kinect datasets, respectively. While this study focuses on action recognition, the proposed framework can in general be applied to any time series of graphs.

©2007 Tokyo Institute of Technology All rights reserved.