Skip to Main content Skip to Navigation

Comparison of video dynamic contents without feature matching by using rank-tests

Alain Lehmann 1 Patrick Bouthemy 2 Jian-Feng Yao 3
2 VISTA - Vision spatio-temporelle et active
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : This report presents a novel and efficient dissimilarity measure between video segments. We consider local spatio-temporal descriptors. They are considered to be realizations of an unknown, but class-specific distribution. The similarity of two video segments is calculated by evaluating an appropriate statistic issued from a rank test. It does not require any matching of the local features between the two considered video segments, and can deal with a different number of computed local features in the two segments. Furthermore, our measure is self-normalized which allows for simple cue integration, and even on-line adapted class-dependent combination of the different descriptors. Satisfactory results have been obtained on real video sequences for two motion event recognition problems.
Document type :
Complete list of metadata
Contributor : Rapport de Recherche Inria <>
Submitted on : Friday, May 19, 2006 - 8:26:39 PM
Last modification on : Thursday, January 7, 2021 - 4:19:45 PM
Long-term archiving on: : Sunday, April 4, 2010 - 9:10:33 PM


  • HAL Id : inria-00070421, version 1


Alain Lehmann, Patrick Bouthemy, Jian-Feng Yao. Comparison of video dynamic contents without feature matching by using rank-tests. [Research Report] RR-5586, INRIA. 2005, pp.15. ⟨inria-00070421⟩



Record views


Files downloads