Real-Time Exact Graph Matching with Application in Human Action Recognition

Oya Celiktutan 1 Christian Wolf 1 Bülent Sankur Eric Lombardi 1
1 imagine - Extraction de Caractéristiques et Identification
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
Abstract : Graph matching is one of the principal methods to formulate the correspondence between two set of points in computer vision and pattern recognition. Most formulations are based on the minimization of a difficult energy function which is known to be NP-hard. Traditional methods solve the minimization problem approximately. In this paper, we derive an exact minimization algorithm and successfully applied to action recognition in videos. In this context, we take advantage of special properties of the time domain, in particular causality and the linear order of time, and propose a new spatio-temporal graphical structure. We show that a better solution can be obtained by exactly solving an approximated problem instead of approximately solving the original problem.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01353052
Contributor : Équipe Gestionnaire Des Publications Si Liris <>
Submitted on : Wednesday, August 10, 2016 - 4:20:34 PM
Last modification on : Tuesday, February 26, 2019 - 3:26:36 PM

Identifiers

Citation

Oya Celiktutan, Christian Wolf, Bülent Sankur, Eric Lombardi. Real-Time Exact Graph Matching with Application in Human Action Recognition. International Workshop on Human Behavior Understanding, Oct 2012, Vilamoura, Portugal. pp.17-28, ⟨10.1007/978-3-642-34014-7_2⟩. ⟨hal-01353052⟩

Share

Metrics

Record views

169