It ’ s in the bag : Stronger supervision for automated face labelling

@inproceedings{Parkhi2015ItS,
  title={It ’ s in the bag : Stronger supervision for automated face labelling},
  author={Omkar M. Parkhi},
  year={2015}
}
The objective of this work is automatic labelling of characters in TV video and movies, given weak supervisory information provided by an aligned transcript. We make four contributions: (i) a new strategy for obtaining stronger supervisory information from aligned transcripts; (ii) an explicit model for classifying background characters, based on their face-tracks; and (iii) employing new ConvNet based face features. Each of these contributions delivers a significant boost in performance, and… CONTINUE READING

References

Publications referenced by this paper.
Showing 1-10 of 26 references

“Knock! Knock! Who is it?” probabilistic person identification in TV-series

2012 IEEE Conference on Computer Vision and Pattern Recognition • 2012
View 14 Excerpts
Highly Influenced

Finding Actors and Actions in Movies

2013 IEEE International Conference on Computer Vision • 2013
View 13 Excerpts
Highly Influenced

Learning from Partial Labels

Journal of Machine Learning Research • 2011
View 9 Excerpts
Highly Influenced

“Who are you?” - Learning person specific classifiers from video

2009 IEEE Conference on Computer Vision and Pattern Recognition • 2009
View 19 Excerpts
Highly Influenced

Hello! My name is.

M. Everingham, J. Sivic, A. Zisserman
Buffy” – automatic naming of characters in TV video. In Proc. BMVC., • 2006
View 10 Excerpts
Highly Influenced

Learning to recognize faces from videos and weakly related information cues

2011 8th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) • 2011
View 4 Excerpts
Highly Influenced

Similar Papers

Loading similar papers…