@INPROCEEDINGS{1293Kelm2011,
	AUTHOR = {Pascal Kelm and Sebastian Schmiedeke and Thomas Sikora},
	TITLE = {Multi-modal, Multi-resource Methods for Placing Flickr Videos on the Map},
	BOOKTITLE = {ACM International Conference on Multimedia Retrieval (ICMR)},
	YEAR = {2011},
	MONTH = apr,
	PAGES = {8},
	DOI = {10.1145/1991996.1992048},
	URL = {http://dl.acm.org/ft_gateway.cfm?id=1992048&ftid=980972&dwn=1&CFID=57606239&CFTOKEN=98200645},
	ABSTRACT = {We present three approaches for placing videos in Flickr on
the world map. The toponym extraction and geo lookup ap-
proach makes use of external resources to identify toponyms
in the metadata and associate them with geo-coordinates.
The metadata-based region model approach uses a k-nearest-
neighbour classifier trained over geographical regions. Videos
are represented using their metadata in a text space with re-
duced dimensionality. The visual region model approach uses
a support vector machine also trained over geographical re-
gions. Videos are represented using low-level feature vectors
from multiple key frames. Voting methods are used to form
a single decision for each video. We compare the approaches
experimentally, highlighting the importance of using appro-
priate metadata features and suitable regions as the basis of
the region model.  The best performance is achieved by the
geo-lookup approach used with fallback to the visual region
model when the video metadata contains no toponym.}
}