Home >

news Help

Publication Information

English:Spectral Graph Wavelets for Skeleton-based 3D Action Recognition 
Japanese: Tommi Kerola, 井上 中順, 篠田 浩一.  
English: Tommi Kerola, Nakamasa Inoue, Koichi Shinoda.  
Language English 
Journal/Book name
Japanese:電子情報通信学会技術研究報告 PRMU 
English:Technical Reports of IEICE PRMU 
Volume, Number, Page vol. 114    no. 454    pp. 131-136
Published date Feb. 19, 2015 
English:The Institute of Electronics, Information and Communication Engineers (IEICE) 
Conference name
English:Technical Reports of IEICE PRMU 
Conference site
English:Sendai-shi, Miyagi Pref. 
Official URL http://www.ieice.org/ken/paper/20150220KBw1/eng/
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.

©2007 Tokyo Institute of Technology All rights reserved.