To aggregate or not to aggregate: selective match kernels for image search
Résumé
This paper considers a family of metrics to compare images based on their local descriptors. It encompasses the VLAD descriptor and matching techniques such as Hamming Embedding. Making the bridge between these approaches leads us to propose a match kernel that takes the best of existing techniques by combining an aggregation procedure with a selective match kernel. Finally, the representation underpinning this kernel is approximated, providing a large scale image search both precise and scalable, as shown by our experiments on several benchmarks.
Fichier principal
iccv13_tolias.pdf (481.42 Ko)
Télécharger le fichier
iccv13_matchkernel.png (66.8 Ko)
Télécharger le fichier
| Origine | Fichiers produits par l'(les) auteur(s) |
|---|
| Format | Figure, Image |
|---|
Loading...