Skip to Main content Skip to Navigation
New interface
Conference papers

Oriented pooling for dense and non-dense rotation-invariant features

Wan-Lei Zhao 1 Hervé Jégou 1 Guillaume Gravier 1 
1 TEXMEX - Multimedia content-based indexing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : This paper proposes a pooling strategy for local descriptors to produce a vector representation that is orientation-invariant yet implicitly incorporates the relative angles between features measured by their dominant orientation. This pooling is associated with a similarity metric that ensures that all the features have undergone a comparable rotation. This approach is especially effective when combined with dense oriented features, in contrast to existing methods that either rely on oriented features extracted on key points or on non-oriented dense features. The interest of our approach in a retrieval scenario is demonstrated on popular benchmarks comprising up to 1 million database images.
Document type :
Conference papers
Complete list of metadata

Cited literature [23 references]  Display  Hide  Download
Contributor : Hervé Jégou Connect in order to contact the contributor
Submitted on : Friday, August 23, 2013 - 12:06:38 PM
Last modification on : Wednesday, February 2, 2022 - 3:59:23 PM
Long-term archiving on: : Thursday, April 6, 2017 - 6:01:34 AM


Files produced by the author(s)


  • HAL Id : hal-00841590, version 2


Wan-Lei Zhao, Hervé Jégou, Guillaume Gravier. Oriented pooling for dense and non-dense rotation-invariant features. BMVC - 24th British Machine Vision Conference, Sep 2013, Bristol, United Kingdom. ⟨hal-00841590v2⟩



Record views


Files downloads