Bags of Graphs for Human Action Recognition
Résumé
Bags of visual words are a well known approach for images classification that also has been used in human action recognition. This model proposes to represent images or videos in a structure referred to as bag of visual words before classifying. The process of representing a video in a bag of visual words is known as the encoding process and is based on mapping the interest points detected in the scene into the new structure by means of a codebook. In this paper we propose to improve the representativeness of this model including the structural relations between the interest points using graph sequences. The proposed model achieves very competitive results for human action recognition and could also be applied to solve graph sequences classification problems.
Origine | Fichiers produits par l'(les) auteur(s) |
---|
Loading...