Graph commute times for image representation

11 years 14 days ago
Graph commute times for image representation
We introduce a new image representation that encompasses both the general layout of groups of quantized local invariant descriptors as well as their relative frequency. A graph of interest points clusters is constructed and we use the matrix of commute times between the different nodes of the graph to obtain a description of their relative arrangement that is robust to large intra class variation. The obtained high dimensional representation is then embedded in a space of lower dimension by exploiting the spectral properties of the graph made of the different images. Classification tasks can be performed in this embedding space. We expose classification and labelling results obtained on three different datasets, including the challenging PASCAL VOC2007 dataset. The performances of our approach compare favorably with the standard bag of features, which is a particular case of our representation.
Nikos Paragios, Regis Behmo, Véronique Prin
Added 12 Oct 2009
Updated 28 Oct 2009
Type Conference
Year 2008
Where CVPR
Authors Nikos Paragios, Regis Behmo, Véronique Prinet
Comments (0)