Unsupervised Metric Learning for Face Identification in TV Video

Ramazan Gokberk Cinbis 1, * Jakob Verbeek 1 Cordelia Schmid 1
* Corresponding author
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : The goal of face identification is to decide whether two faces depict the same person or not. This paper addresses the identification problem for face-tracks that are automatically collected from uncontrolled TV video data. Face-track identification is an important component in systems that automatically label characters in TV series or movies based on subtitles and/or scripts: it enables effective transfer of the sparse text-based supervision to other faces. We show that, without manually labeling any examples, metric learning can be effectively used to address this problem. This is possible by using pairs of faces within a track as positive examples, while negative training examples can be generated from pairs of face tracks of different people that appear together in a video frame. In this manner we can learn a cast-specific metric, adapted to the people appearing in a particular video, without using any supervision. Identification performance can be further improved using semi-supervised learning where we also include labels for some of the face tracks. We show that our cast-specific metrics not only improve identification, but also recognition and clustering.
Document type :
Conference papers
ICCV 2011 - International Conference on Computer Vision, Nov 2011, Barcelona, Spain. IEEE, pp.1559-1566, 2011, <10.1109/ICCV.2011.6126415>
Liste complète des métadonnées


https://hal.inria.fr/inria-00611682
Contributor : Jakob Verbeek <>
Submitted on : Wednesday, July 27, 2011 - 9:32:33 AM
Last modification on : Monday, July 21, 2014 - 12:09:18 AM
Document(s) archivé(s) le : Monday, November 7, 2011 - 11:32:48 AM

Files

paper_express.pdf
Explicit agreement for this submission

Identifiers

Collections

Citation

Ramazan Gokberk Cinbis, Jakob Verbeek, Cordelia Schmid. Unsupervised Metric Learning for Face Identification in TV Video. ICCV 2011 - International Conference on Computer Vision, Nov 2011, Barcelona, Spain. IEEE, pp.1559-1566, 2011, <10.1109/ICCV.2011.6126415>. <inria-00611682>

Share

Metrics

Record views

2382

Document downloads

5224