Face recognition from caption-based supervision

Matthieu Guillaumin 1, * Thomas Mensink 1, 2 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 : In this report, 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. We survey graph-based, generative and discriminative approaches for both tasks. 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 Labeled Faces in the Wild data set. We present extensive experimental results which show that metric learning significantly improves the performance of all approaches on both tasks.
Liste complète des métadonnées

Cited literature [55 references]  Display  Hide  Download


https://hal.inria.fr/inria-00522185
Contributor : Thoth Team <>
Submitted on : Monday, February 21, 2011 - 11:21:45 AM
Last modification on : Tuesday, February 12, 2019 - 10:30:05 AM
Document(s) archivé(s) le : Sunday, May 22, 2011 - 2:51:14 AM

Files

paper.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00522185, version 2

Collections

Citation

Matthieu Guillaumin, Thomas Mensink, Jakob Verbeek, Cordelia Schmid. Face recognition from caption-based supervision. [Technical Report] RT-392, INRIA. 2010, pp.37. ⟨inria-00522185v2⟩

Share

Metrics

Record views

779

Files downloads

2500