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

Giorgos Tolias 1, 2 Yannis Avrithis 2, 3 Hervé Jégou 1
1 TEXMEX - Multimedia content-based indexing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [30 references]  Display  Hide  Download


https://hal.inria.fr/hal-00864684
Contributor : Hervé Jégou <>
Submitted on : Monday, September 23, 2013 - 9:45:55 AM
Last modification on : Saturday, December 1, 2018 - 7:56:17 PM
Long-term archiving on : Tuesday, December 24, 2013 - 4:30:27 AM

Files

iccv13_tolias.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00864684, version 1

Citation

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⟩

Share

Metrics

Record views

926

Files downloads

4725