<<
| Conference/Proceedings | ACM International Conference on Multimedia Retrieval (ICMR) |
| Start date | 17.04.2011 |
| End date | 20.04.2011 |
| Pages | 8 |
| Author(s) | Pascal Kelm, Sebastian Schmiedeke, Thomas Sikora |
| Title | Multi-modal, Multi-resource Methods for Placing Flickr Videos on the Map |
| 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. |
| Key words | compression, geo-localization, gazetteers, probabilistic latent semantic analysis, MPEG-7 visual features |
| DOI | 10.1145/1991996.1992048 |
| URL | http://dl.acm.org/ft_gateway.cfm?id=1992048&ftid=980972&dwn=1&CFID=57606239&CFTOKEN=98200645 |
BibTeX