A Spatio-Temporal Descriptor Based on 3D-Gradients - Archive ouverte HAL Access content directly
Conference Papers Year : 2008

A Spatio-Temporal Descriptor Based on 3D-Gradients


In this work, we present a novel local descriptor for video sequences. The proposed descriptor is based on histograms of oriented 3D spatio-temporal gradients. Our contribution is four-fold. (i) To compute 3D gradients for arbitrary scales, we develop a memory-efficient algorithm based on integral videos. (ii) We propose a generic 3D orientation quantization which is based on regular polyhedrons. (iii) We perform an in-depth evaluation of all descriptor parameters and optimize them for action recognition. (iv) We apply our descriptor to various action datasets (KTH, Weizmann, Hollywood) and show that we outperform the state-of-the-art.
Vignette du fichier
3ddesc.png (63.16 Ko) Télécharger le fichier Fichier principal
Vignette du fichier
KlaserMarszalekSchmid-BMVC08-3DGradientDescriptor.pdf (317.46 Ko) Télécharger le fichier
poster.png (1.28 Mo) Télécharger le fichier
Format : Figure, Image
Origin : Files produced by the author(s)
Format : Other

Dates and versions

inria-00514853 , version 1 (03-09-2010)


  • HAL Id : inria-00514853 , version 1


Alexander Klaser, Marcin Marszałek, Cordelia Schmid. A Spatio-Temporal Descriptor Based on 3D-Gradients. BMVC 2008 - 19th British Machine Vision Conference, Sep 2008, Leeds, United Kingdom. pp.275:1-10. ⟨inria-00514853⟩
4827 View
3928 Download


Gmail Facebook Twitter LinkedIn More