Learning Graphs to Match - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2013

Learning Graphs to Match


Many tasks in computer vision are formulated as graph matching problems. Despite the NP-hard nature of the problem, fast and accurate approximations have led to significant progress in a wide range of applications. Learning graph models from observed data, however, still remains a challenging issue. This paper presents an effective scheme to parameterize a graph model, and learn its structural attributes for visual object matching. For this, we propose a graph representation with histogram-based attributes, and optimize them to increase the matching accuracy. Experimental evaluations on synthetic and real image datasets demonstrate the effectiveness of our approach, and show significant improvement in matching accuracy over graphs with pre-defined structures.
Fichier principal
Vignette du fichier
cho13.pdf (2.4 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-00875105 , version 1 (21-10-2013)



Minsu Cho, Karteek Alahari, Jean Ponce. Learning Graphs to Match. ICCV - IEEE International Conference on Computer Vision, Dec 2013, Sydney, Australia. pp.25-32, ⟨10.1109/ICCV.2013.11⟩. ⟨hal-00875105⟩
620 View
455 Download



Gmail Mastodon Facebook X LinkedIn More