@INPROCEEDINGS{1356Schmiedeke2012,
	AUTHOR = {Schmiedeke and Sebastian and Kelm and Pascal and Sikora and Thomas},
	TITLE = {Cross-Modal Categorisation of User-Generated Video Sequences},
	BOOKTITLE = {Proceedings of the 2nd ACM International Conference on Multimedia Retrieval},
	YEAR = {2012},
	MONTH = jun,
	EDITOR = {ACM},
	PAGES = {251--258},
	ADDRESS = {New York, NY, USA},
	NOTE = {isbn: 978-1-4503-1329-2
 articleno: 25
 numpages: 8
location: Hong Kong, China},
	DOI = {10.1145/2324796.2324828},
	URL = {http://dl.acm.org/citation.cfm?id=2324828},
	ABSTRACT = {This paper describes the possibilities of cross-modal classification of multimedia documents in social media platforms.
Our framework predicts the user-chosen category of consumer-produced video sequences based on their textual and visual features.
These text resources---includes metadata and automatic speech recognition transcripts---are represented as bags of words and the video content is represented as a bag of clustered local visual features.
The contribution of the different modalities is investigated and how they should be combined if sequences lack certain resources.
Therefore, several classification methods are evaluated, varying the resources.
The paper shows an approach that achieves a mean average precision of 0.3977 using user-contributed metadata in combination with clustered SURF.}
}