Efficient image signatures and similarities using tensor products of local descriptors

David Picard 1 Philippe-Henri Gosselin 1
1 MIDI
ETIS - Equipes Traitement de l'Information et Systèmes
Abstract : In this paper, we introduce a novel image signature effective in both image retrieval and image classification. Our approach is based on the aggregation of tensor products of discriminant local features, named VLAT (vector of locally aggregated tensors). We also introduce techniques for the packing and the fast comparison of VLATs. We present connections between VLAT and methods like kernel on bags and Fisher vectors. Finally, we show the ability of our method to be effective for two different retrieval problems, thanks to experiments carried out on similarity search and classification datasets.
Document type :
Journal articles
Computer Vision and Image Understanding, Elsevier, 2013, 117 (6), pp.680-687. 〈10.1016/j.cviu.2013.02.004〉
Liste complète des métadonnées

Cited literature [38 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00799074
Contributor : Philippe-Henri Gosselin <>
Submitted on : Monday, March 11, 2013 - 2:57:42 PM
Last modification on : Thursday, May 3, 2018 - 3:18:06 PM
Document(s) archivé(s) le : Wednesday, June 12, 2013 - 6:25:07 AM

File

picard13cviu.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

David Picard, Philippe-Henri Gosselin. Efficient image signatures and similarities using tensor products of local descriptors. Computer Vision and Image Understanding, Elsevier, 2013, 117 (6), pp.680-687. 〈10.1016/j.cviu.2013.02.004〉. 〈hal-00799074〉

Share

Metrics

Record views

218

Files downloads

246