|Working Notes Proceedings of the MediaEval 2012 Workshop
|Santa Croce in Fossabanda Piazza Santa Croce, 5 - 56125 - Pisa - Toscana - Italia
|Martha A. Larson, Sebastian Schmiedeke, Pascal Kelm, Adam Rae, Vasileios Mezaris, Tomas Piatrik, Mohammad Soleymani, Florian Metze, Gareth J.F. Jones
|Pascal Kelm, Sebastian Schmiedeke, Thomas Sikora
|How Spatial Segmentation improves the Multimodal Geo-Tagging
|In this paper we present a hierarchical, multi-modal ap- proach in combination with diﬀerent granularity levels for the Placing Task at the MediaEval benchmark 2012. Our approach makes use of external resources like gazetteers to extract toponyms in the metadata and of visual and textual features to identify similar content. First, the bounderies detection recognizes the country and its dimension to speed up the estimation and to eliminate geographical ambiguity. Next, we prepared a training database to group them to- gether into geographical regions and to build a hierarchical model. The fusion of visual and textual methods for diﬀer- ent granularities is used to classify the videos’ location into possible regions. At the end the Flickr videos are tagged with the geo-information of the most similar training image within the regions that is previously ﬁltered by the proba- bilistic model for each test video.
|multimedia analysis, placing task 2012, automatic geotagging, hierarchical segmentation