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. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1109/ICCV.2011.6126415 | ICCV |
Keywords | Field | DocType |
unsupervised metric learning,tv series,uncontrolled tv video data,particular video,identification performance,face-track identification,face track,face identification,identification problem,video frame,cast-specific metrics,robustness,learning artificial intelligence,face,semi supervised learning,feature extraction,face recognition,machine vision,measurement,tv,face tracking | Pattern clustering,Computer science,Robustness (computer science),Artificial intelligence,Face detection,Cluster analysis,Parameter identification problem,Computer vision,Facial recognition system,Pattern recognition,Feature extraction,Machine learning,Scripting language | Conference |
Volume | Issue | ISSN |
2011 | 1 | 1550-5499 |
Citations | PageRank | References |
75 | 2.72 | 14 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
R. Gokberk Cinbis | 1 | 510 | 25.60 |
J. J. Verbeek | 2 | 3944 | 181.44 |
Cordelia Schmid | 3 | 28581 | 1983.22 |