Skip to Main content Skip to Navigation
Journal articles

Rotation and translation covariant match kernels for image retrieval

Giorgos Tolias 1 Andrei Bursuc 1 Teddy Furon 1 Hervé Jégou 1
1 LinkMedia - Creating and exploiting explicit links between multimedia fragments
Inria Rennes – Bretagne Atlantique , IRISA-D6 - MEDIA ET INTERACTIONS
Abstract : Most image encodings achieve orientation invariance by aligning the patches to their dominant orientations and translation invariance by completely ignoring patch position or by max-pooling. Albeit successful, such choices introduce too much invariance because they do not guarantee that the patches are rotated or translated consistently. In this paper, we propose a geometric-aware aggregation strategy, which jointly encodes the local descriptors together with their patch dominant angle or location. The geometric attributes are encoded in a continuous manner by leveraging explicit feature maps. Our technique is compatible with generic match kernel formulation and can be employed along with several popular encoding methods, in particular Bag-of-Words, VLAD and the Fisher vector. The method is further combined with an efficient monomial embedding to provide a codebook-free method aggregating local descriptors into a single vector representation. Invariance is achieved by efficient similarity estimation of multiple rotations or translations, offered by a simple trigonometric polynomial. This strategy is effective for image search, as shown by experiments performed on standard benchmarks for image and particular object retrieval, namely Holidays and Oxford buildings.
Complete list of metadata

Cited literature [55 references]  Display  Hide  Download
Contributor : Teddy Furon Connect in order to contact the contributor
Submitted on : Tuesday, August 25, 2015 - 4:24:55 PM
Last modification on : Tuesday, October 19, 2021 - 11:58:59 PM
Long-term archiving on: : Thursday, November 26, 2015 - 2:04:06 PM


Files produced by the author(s)



Giorgos Tolias, Andrei Bursuc, Teddy Furon, Hervé Jégou. Rotation and translation covariant match kernels for image retrieval. Computer Vision and Image Understanding, Elsevier, 2015, pp.15. ⟨10.1016/j.cviu.2015.06.007⟩. ⟨hal-01168525⟩



Record views


Files downloads