Fisher vector faces in the wild

Conference item

Several recent papers on automatic face verification have significantly raised the performance bar by developing novel, specialised representations that outperform standard features such as SIFT for this problem.
This paper makes two contributions: first, and somewhat surprisingly, we show that Fisher vectors on densely sampled SIFT features, i.e. an off-the-shelf object recognition representation, are capable of achieving state-of-the-art face verification performance on the challenging “Labeled Faces in the Wild” benchmark; second, since Fisher vectors are very high dimensional, we show that a compact descriptor can be learnt from them using discriminative metric learning. This compact descriptor has a better recognition accuracy and is very well suited to large scale identification tasks.

Authors: Simonyan, K; Parkhi, O; Vedaldi, A; Zisserman, A

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: British Machine Vision Association
• Host title: Proceedings of the British Machine Vision Conference 2013
• Pages: 8.1-8.11
• Publication date: 2013-09-13
• Acceptance date: 2013-07-01
• Event title: 24th British Machine Vision Conference (BMVC 2013)
• Event location: Bristol, UK
• Event website: https://bmva-archive.org.uk/bmvc/2013/index.html
• Event start date: 2013-09-09
• Event end date: 2013-09-13
• ISBN: 1901725499
• Language: English