Automatic face naming with caption-based supervision

We consider two scenarios of naming people in databases of news photos with captions: (i) finding faces of a single person, and (ii) assigning names to all faces. We combine an initial text-based step, that restricts the name assigned to a face to the set of names appearing in the caption, with a second step that analyzes visual features of faces. By searching for groups of highly similar faces that can be associated with a name, the results of purely text-based search can be greatly ameliorated. We improve a recent graph-based approach, in which nodes correspond to faces and edges connect highly similar faces. We introduce constraints when optimizing the objective function, and propose improvements in the low-level methods used to construct the graphs. Furthermore, we generalize the graph-based approach to face naming in the full data set. In this multi-person naming case the optimization quickly becomes computationally demanding, and we present an important speed-up using graph-flow...

• Type: Conference
• Year: 2008
• Where: CVPR
• Authors: Matthieu Guillaumin, Thomas Mensink, Jakob J. Verbeek, Cordelia Schmid
• Keywords: Computer Vision, CVPR 2008, Graph-based Methods, Initial Text-based Step, Multi-person Naming Case, Multi-person Naming Task, Similar Faces