How INRIA/IRISA identifies Geographic Location of a Video

Michele Trevisiol 1 Jonathan Delhumeau 2 Hervé Jégou 2 Guillaume Gravier 2
1 Web Research Group [Barcelona]
Universitat Pompeu Fabra [Barcelona]
2 TEXMEX - Multimedia content-based indexing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : In this paper, we describe our approaches and their results as part of the MediaEval 2012 Placing Task evaluation. We present two di erent tag-based techniques. Both rst preselect one or several geographic area of interest and then perform a deeper analysis inside the selected area(s) to return the coordinates more likely to be related with the input tags. In addition, we also implement a content-based method that uses aggregated local images descriptors (VLAD) to nd the video's visual nearest neighbors and infer its coordinates. In this work we do not use gazetteers or any other external information.
Document type :
Conference papers
Complete list of metadatas

Cited literature [5 references]  Display  Hide  Download
Contributor : Guillaume Gravier <>
Submitted on : Tuesday, November 27, 2012 - 9:05:42 AM
Last modification on : Friday, November 16, 2018 - 1:25:28 AM
Long-term archiving on : Saturday, December 17, 2016 - 3:16:45 PM


Files produced by the author(s)


  • HAL Id : hal-00757453, version 1


Michele Trevisiol, Jonathan Delhumeau, Hervé Jégou, Guillaume Gravier. How INRIA/IRISA identifies Geographic Location of a Video. Working Notes Proceedings of the MediaEval 2012 Workshop, 2012, Italy. ⟨hal-00757453⟩



Record views


Files downloads