To aggregate or not to aggregate: selective match kernels for image search - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2013

To aggregate or not to aggregate: selective match kernels for image search

Abstract

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
Vignette du fichier
iccv13_tolias.pdf (481.42 Ko) Télécharger le fichier
Vignette du fichier
iccv13_matchkernel.png (66.8 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Figure, Image
Loading...

Dates and versions

hal-00864684 , version 1 (23-09-2013)

Identifiers

  • HAL Id : hal-00864684 , version 1

Cite

Giorgos Tolias, Yannis Avrithis, Hervé Jégou. To aggregate or not to aggregate: selective match kernels for image search. ICCV - International Conference on Computer Vision, Dec 2013, Sydney, Australia. ⟨hal-00864684⟩
726 View
4147 Download

Share

Gmail Facebook X LinkedIn More