TubeTagger -­ YouTube-based Concept Detection

Adrian Ulges, Markus Koch, Damian Borth, Thomas Breuel
Proceddings of the International Workshop on Internet Multimedia Mining, Miami, FL, USA, IEEE Computer Society, 12/2009

Abstract:

We present TubeTagger, a concept-based video retrieval system that exploits web video as an information source. The system performs a visual learning on YouTube clips (i.e., it trains detectors for semantic concepts like "soccer" or "windmill"), and a semantic learning on the associated tags (i.e., relations between concepts like "swimming" and "water" are discovered). This way, a text-based video search free of manual indexing is realized. We present a quantitative study on web-based concept detection comparing several features and statistical models on a large-scale dataset of YouTube content. Beyond this, we report several key findings related to concept learning from YouTube and its generalization to different domains, and illustrate certain characteristics of YouTube-learned concepts, like focus of interest and redundancy. To get a hands-on impression of web-based concept detection, we invite researchers and practitioners to test our web demo.

Files:

  http://madm.dfki.de/demo/tubetagger
  tubetagger.pdf

BibTex:

@inproceedings{ ULGE2009,
	Title = {TubeTagger -­ YouTube-based Concept Detection},
	Author = {Adrian Ulges and Markus Koch and Damian Borth and Thomas Breuel},
	BookTitle = {Proceddings of the International Workshop on Internet Multimedia Mining},
	Month = {12},
	Year = {2009},
	Publisher = {IEEE Computer Society}
}

     
Last modified:: 30.08.2016