Dictionary of gray-level 3D patches for action recognition - Archive ouverte HAL Access content directly
Conference Papers Year : 2014

Dictionary of gray-level 3D patches for action recognition

(1) , (1) , (1)


Sparse dictionary-based methods have received a lot of focus in the recent years. In this paper, we are interested in action recognition in videos using a 3D representation based on the use of a dictionary. A 3D volume can be seen as a set of gray-level 3D patches which are 2D patches taken in successive frames in order to capture a motion pattern. The goal is to recognize human actions within these 3D volumes, whose 3D patches are described with the dictionary atoms. A motion signature is computed by building a histogram based on the use of the atoms of the dictionary. Paired with a SVM, we show that these signatures can be exploited in the context of action recognition. This method was tested on the KTH database with good results.
Fichier principal
Vignette du fichier
article_schan17_12nocpr.pdf (570.53 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01058339 , version 1 (19-12-2014)


  • HAL Id : hal-01058339 , version 1


Stefen Chan Wai Tim, Michèle Rombaut, Denis Pellerin. Dictionary of gray-level 3D patches for action recognition. MLSP 2014 - IEEE 24th International Workshop on Machine Learning for Signal Processing, Sep 2014, Reims, France. ⟨hal-01058339⟩
260 View
138 Download


Gmail Facebook Twitter LinkedIn More