@inproceedings{2008-IUPR-05Jun_1853,
author = {Adrian Ulges and Christian Schulze and Daniel Keysers and Thomas Breuel},
title = {Identifying Relevant Frames in Weakly Labeled Videos for Training Concept Detectors},
booktitle = {CIVR},
year = {2008},
__utma = {43439421.687299351.1195551235.1211995572.1212400999.53},
__utmz = {43439421.1208261141.43.2.utmccn=(referral)|utmcsr=flickr.com|utmcct=/services/auth/list.gne|utmcmd=referral},
abstract = {A key problem with the automatic detection of semantic
concepts (like `interview' or `soccer') in video streams is the
manual acquisition of adequate training sets. Recently, we
have proposed to use online videos downloaded from portals
like youtube.com for this purpose, whereas tags provided by
users during video upload serve as ground truth annotations.
 The problem with such training data is that it is weakly
labeled: Annotations are only provided on video level, and
many shots of a video may be "non-relevant", i.e. not visu-
ally related to a tag. In this paper, we present a probabilistic
framework for learning from such weakly annotated training
videos in the presence of irrelevant content. Thereby, the rel-
evance of keyframes is modeled as a latent random variable
that is estimated during training.
 In quantitative experiments on real-world online videos
and TV news data, we demonstrate that the proposed model
leads to a significantly increased robustness with respect to
irrelevant content, and to a better generalization of the re-
sulting concept detectors.},
category = {multimedia databases}
}