@inproceedings{2008-IUPR-31Jan_1134,
author = {Adrian Ulges and Christian Schulze and Daniel Keysers and Thomas Breuel},
title = {A System that Learns to Tag Videos by Watching Youtube},
booktitle = {International Conference on Computer Vision Systems},
year = {2008},
pdf = {2008-IUPR-31Jan_1134.pdf},
__utma = {43439421.687299351.1195551235.1201045065.1201539098.17},
__utmz = {43439421.1195551235.1.1.utmccn=(direct)|utmcsr=(direct)|utmcmd=(none)},
abstract = {We present a system that automatically tags videos, i.e. de- tects high-level semantic concepts like objects or actions
in them. To do so, our system does not rely on datasets manually annotated for re- search purposes. Instead, we propose
to use videos from online portals like youtube.com as a novel source of training data, whereas tags pro- vided by users
during upload serve as ground truth annotations. This allows our system to learn autonomously by automatically
downloading its training set. The key contribution of this work is a number of large-scale quantita- tive experiments on
real-world online videos, in which we investigate the influence of the individual system components, and how well our
tagger generalizes to novel content. Our key results are: (1) Fair tagging results can be obtained by a late fusion of
several kinds of visual features. (2) Using more than one keyframe per shot is helpful. (3) To generalize to different
video content (e.g., another video portal), the system can be adapted by expanding its training set.},
category = {visual object recognition;multimedia databases}
}