A UNIFIED FORMALISM FOR VIDEO DESCRIPTORS

Olivier Kihl (1) , David Picard (2) , Philippe-Henri Gosselin (1, 3)

1 ETIS - UMR 8051 - Equipes Traitement de l'Information et Systèmes
2 MIDI - Multimedia Indexation and Data Integration
3 TEXMEX - Multimedia content-based indexing

In this paper, we propose a unified formalism for video descriptors. This formalism is based on the descriptors decomposition in three levels: primitive, scattering and projection. With this framework, we are able to rewrite easily all the usual descriptors in the literature such as HOG, HOF, SURF. Then, we propose a new projection method based on approximation with a finite expansion of orthogonal polynomials. Using our framework, we extend all usual descrip- tors by switching the projection step. The experiments are carried out on the well known KTH dataset and on the more challenging Hollywood2 action classification dataset and show state of the art results.

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Olivier Kihl, David Picard, Philippe-Henri Gosselin. A UNIFIED FORMALISM FOR VIDEO DESCRIPTORS. 2013. ⟨hal-00832190v1⟩