direkt zum Inhalt springen

direkt zum Hauptnavigationsmenü

Sie sind hier

TU Berlin

Inhalt des Dokuments

Multimodal Geo-tagging in Social Media Websites using Hierarchical Spatial Segmentation

FG NUE
Lupe

These days the sharing of photographs and videos is very popular in social networks. Many of these social media web- sites such as Flickr, Facebook and Youtube allows the user to manually label their uploaded videos with geo-information using a interface for dragging them into the map. However, the manually labelling for a large set of social media is still borring and error-prone. For this reason we present a hierarchical, multi-modal approach for estimating the GPS information. 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 national borders detection recognizes the country and its dimension to speed up the estimation and to eliminate geographical ambiguity. Next, we use a database of more than 3.2 million Flickr images to group them together into geographical regions and to build a hierarchical model. A fusion of visual and textual methods for different granularities is used to classify the videos' location into possible regions. The Flickr videos are tagged with the geo-information of the most similar training image within the regions that is previously filtered by the probabilistic model for each test video. In comparison with existing GPS estimation and image retrieval approaches at the Placing Task 2011 we will show the effectiveness and high accuracy relative to the state-of-the art solutions.

 

Paper

Pascal Kelm, Sebastian Schmiedeke, Thomas Sikora

Multimodal Geo-tagging in Social Media Websites using Hierarchical Spatial Segmentation Proceedings of the 20th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, volume 978-1-4503-1698-9/12/11, 06.11.2012 - 09.11.2012, pp. 8

Details BibTeX

Demonstrator

-->

    Related Papers

    1. Pascal Kelm, Vanessa Murdock, Sebastian Schmiedeke, Steven Schockaert, Pavel Serdyukov, Olivier Van Laere
      Georeferencing in Social Networks
      in Social Media Retrieval, Naeem Ramzan, Roelof van Zwol, Jong-Seok Lee, Kai Clüver, Xian-Sheng Hua (ed(s).), Springer, 30.11.2012
      ISBN 978-1-4471-4554-7 
      Details BibTeX
    2. Pascal Kelm, Sebastian Schmiedeke, Thomas Sikora
      Multimodal Geo-tagging in Social Media Websites using Hierarchical Spatial Segmentation
      Proceedings of the 20th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, volume 978-1-4503-1698-9/12/11, 06.11.2012 - 09.11.2012, pp. 8 
      Details BibTeX
    3. Luke Gottlieb, Jaeyoung Choi, Gerald Friedland, Pascal Kelm, Thomas Sikora
      Pushing the limits of Mechanical Turk; Qualifying the crowd for geolocation
      ACM Multimedia 2012 Workshop on Crowdsourcing for Multimedia, 29.10.2012 - 02.11.2012 
      Details BibTeX
    4. Pascal Kelm, Sebastian Schmiedeke, Kai Clüver, Thomas Sikora
    5. Automatic Geo-referencing of Flickr Videos NEM Summit 2011, 27.09.2011 - 29.09.2011 
    6. Details BibTeX
    7. Adam Rae, Vanesa Murdock, Pavel Serdyukov, Pascal Kelm:
    8. Working Notes for the Placing Task at MediaEval 2011 Multimedia Benchmark Workshop 2011, 01.09.2011 - 02.09.2011 
      Details BibTeX
    9. Pascal Kelm, Sebastian Schmiedeke, Thomas Sikora:
    10. Multi-modal, Multi-resource Methods for Placing Flickr Videos on the Map ACM International Conference on Multimedia Retrieval (ICMR), 17.04.2011 - 20.04.2011, pp. 8 
    11. Details BibTeX

    Funding

    The research leading to these results has received funding from the European Community's FP7 under grant agreement number 261743 (NoE VideoSense). We would also like to thank the MediaEval organisers for providing this data set.

    Comments and questions to Pascal Kelmhttp://www.nue.tu-berlin.de/menue/mitarbeiter/pascal_kelm/

    Zusatzinformationen / Extras