Abstract
Recognizing faces in unconstrained videos is a task of mounting importance. While obviously related to face recognition in still images, it has its own unique characteristics and algorithmic requirements. Over the years several methods have been suggested for this problem, and a few benchmark data sets have been assembled to facilitate its study. However, there is a sizable gap between the actual application needs and the current state of the art. In this paper we make the following contributions. (a) We present a comprehensive database of labeled videos of faces in challenging, uncontrolled conditions (i.e., `in the wild'), the `YouTube Faces' database, along with benchmark, pair-matching tests <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> . (b) We employ our benchmark to survey and compare the performance of a large variety of existing video face recognition techniques. Finally, (c) we describe a novel set-to-set similarity measure, the Matched Background Similarity (MBGS). This similarity is shown to considerably improve performance on the benchmark tests.
Keywords
Computer scienceFacial recognition systemArtificial intelligenceSimilarity (geometry)Pattern recognition (psychology)Face (sociological concept)Computer visionSpeech recognitionImage (mathematics)
Affiliated Institutions
Related Publications
Region competition: unifying snakes, region growing, energy/Bayes/MDL for multi-band image segmentation
We present a novel statistical and variational approach to image segmentation based on a new algorithm named region competition. This algorithm is derived by minimizing a genera...
A general framework for object detection
This paper presents a general trainable framework for object detection in static images of cluttered scenes. The detection technique we develop is based on a wavelet representat...
Compressed sensing
Suppose x is an unknown vector in Ropf <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">m</sup> (a digital image or signal); we pla...
Lower Bounds for the Partitioning of Graphs
Let a k-partition of a graph be a division of the vertices into k disjoint subsets containing m <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.or...
On the Capacity of Radio Communication Systems with Diversity in a Rayleigh Fading Environment
In this paper, we study the fundamental limits on the data rate of multiple antenna systems in a Rayleigh fading environment. With <tex xmlns:mml="http://www.w3.org/1998/Math/Ma...
Publication Info
- Year
- 2011
- Type
- article
- Pages
- 529-534
- Citations
- 1430
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
1430
OpenAlex
Cite This
Lior Wolf,
Tal Hassner,
Itay Maoz
(2011).
Face recognition in unconstrained videos with matched background similarity.
, 529-534.
https://doi.org/10.1109/cvpr.2011.5995566
Identifiers
- DOI
- 10.1109/cvpr.2011.5995566