Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Panorama to panorama matching for location recognition

Ahmet Iscen 1 Giorgos Tolias 2 Yannis Avrithis 1 Teddy Furon 1 Ondřej Chum 2
1 LinkMedia - Creating and exploiting explicit links between multimedia fragments
Inria Rennes – Bretagne Atlantique , IRISA-D6 - MEDIA ET INTERACTIONS
2 VRG - Visual Recognition Group [Prague]
CTU/FEE - Faculty of electrical engineering [Prague]
Abstract : Location recognition is commonly treated as visual instance retrieval on "street view" imagery. e dataset items and queries are panoramic views, i.e. groups of images taken at a single location. is work introduces a novel panorama-to-panorama matching process, either by aggregating features of individual images in a group or by explicitly constructing a larger panorama. In either case, multiple views are used as queries. We reach near perfect location recognition on a standard benchmark with only four query views.
Document type :
Preprints, Working Papers, ...
Complete list of metadatas

Cited literature [34 references]  Display  Hide  Download
Contributor : Yannis Avrithis <>
Submitted on : Tuesday, November 19, 2019 - 1:00:56 PM
Last modification on : Friday, July 10, 2020 - 4:02:00 PM
Long-term archiving on: : Thursday, February 20, 2020 - 7:16:54 PM


Files produced by the author(s)



Ahmet Iscen, Giorgos Tolias, Yannis Avrithis, Teddy Furon, Ondřej Chum. Panorama to panorama matching for location recognition. 2017. ⟨hal-02370230⟩