Face recognition from caption-based supervision

Matthieu Guillaumin 1 Thomas Mensink 1, 2 Jakob Verbeek 1 Cordelia Schmid 1
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : In this paper, we present methods for face recognition using a collection of images with captions. We consider two tasks: retrieving all faces of a particular person in a data set, and establishing the correct association between the names in the captions and the faces in the images. This is challenging because of the very large appearance variation in the images, as well as the potential mismatch between images and their captions. For both tasks, we compare generative and discriminative probabilistic models, as well as methods that maximize subgraph densities in similarity graphs. We extend them by considering different metric learning techniques to obtain appropriate face representations that reduce intra person variability and increase inter person separation. For the retrieval task, we also study the benefit of query expansion. To evaluate performance, we use a new fully labeled data set of 31147 faces which extends the recent LFW data set. We present extensive experimental results which show that metric learning significantly improves the performance of all approaches on both tasks.
Document type :
Journal articles
Liste complète des métadonnées

Cited literature [42 references]  Display  Hide  Download


https://hal.inria.fr/inria-00585834
Contributor : Thoth Team <>
Submitted on : Thursday, April 14, 2011 - 9:11:17 AM
Last modification on : Tuesday, February 12, 2019 - 10:30:05 AM
Document(s) archivé(s) le : Thursday, November 8, 2012 - 4:30:09 PM

Files

paper.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Matthieu Guillaumin, Thomas Mensink, Jakob Verbeek, Cordelia Schmid. Face recognition from caption-based supervision. International Journal of Computer Vision, Springer Verlag, 2012, 96 (1), pp.64-82. ⟨10.1007/s11263-011-0447-x⟩. ⟨inria-00585834⟩

Share

Metrics

Record views

1654

Files downloads

2276