Face recognition on large-scale video in the wild with hybrid Euclidean-and-Riemannian metric learning
Face recognition on large-scale video in the wild with hybrid Euclidean-and-Riemannian metric learning
Face recognition on large-scale video in the wild is becoming increasingly important due to the ubiquity of video data captured by surveillance cameras, handheld devices, Internet uploads, and other sources. By treating each video as one image set, set-based methods recently have made great success in the field of video-based face recognition. In the wild world, videos often contain extremely complex data variations and thus pose a big challenge of set modeling for set-based methods. In this paper, we propose a novel Hybrid Euclidean-and-Riemannian Metric Learning (HERML) method to fuse multiple statistics of image set. Specifically, we represent each image set simultaneously by mean, covariance matrix and Gaussian distribution, which generally complement each other in the aspect of set modeling. However, it is not trivial to fuse them since mean, covariance matrix and Gaussian model typically lie in multiple heterogeneous spaces equipped with Euclidean or Riemannian metric. Therefore, we first implicitly map the original statistics into high dimensional Hilbert spaces by exploiting Euclidean and Riemannian kernels. With a LogDet divergence based objective function, the hybrid kernels are then fused by our hybrid metric learning framework, which can efficiently perform the fusing procedure on large-scale videos. The proposed method is evaluated on four public and challenging large-scale video face datasets. Extensive experimental results demonstrate that our method has a clear superiority over the state-of-the-art set-based methods for large-scale video-based face recognition. HighlightsRepresent image set by mean, covariance and Gaussian for discriminant information.Heterogeneous Euclidean and Riemannian kernels are exploited and fused clearly.Clear superiority over state-of-the-art set-based methods is achieved in testing.
3113 - 3124
Huang, Zhiwu
84f477cd-9097-44dd-a33e-ff71f253d36b
Wang, Ruiping
5727660b-3139-49e6-998c-f82f13fc62ec
Shan, Shiguang
78e49abb-f490-480f-b534-0b7e05c9cbe4
Chen, Xilin
48380269-4169-4310-ae77-30dade3b551b
17 June 2015
Huang, Zhiwu
84f477cd-9097-44dd-a33e-ff71f253d36b
Wang, Ruiping
5727660b-3139-49e6-998c-f82f13fc62ec
Shan, Shiguang
78e49abb-f490-480f-b534-0b7e05c9cbe4
Chen, Xilin
48380269-4169-4310-ae77-30dade3b551b
Huang, Zhiwu, Wang, Ruiping, Shan, Shiguang and Chen, Xilin
(2015)
Face recognition on large-scale video in the wild with hybrid Euclidean-and-Riemannian metric learning.
Pattern Recognition, 48 (10), .
(doi:10.1016/j.patcog.2015.03.011).
Abstract
Face recognition on large-scale video in the wild is becoming increasingly important due to the ubiquity of video data captured by surveillance cameras, handheld devices, Internet uploads, and other sources. By treating each video as one image set, set-based methods recently have made great success in the field of video-based face recognition. In the wild world, videos often contain extremely complex data variations and thus pose a big challenge of set modeling for set-based methods. In this paper, we propose a novel Hybrid Euclidean-and-Riemannian Metric Learning (HERML) method to fuse multiple statistics of image set. Specifically, we represent each image set simultaneously by mean, covariance matrix and Gaussian distribution, which generally complement each other in the aspect of set modeling. However, it is not trivial to fuse them since mean, covariance matrix and Gaussian model typically lie in multiple heterogeneous spaces equipped with Euclidean or Riemannian metric. Therefore, we first implicitly map the original statistics into high dimensional Hilbert spaces by exploiting Euclidean and Riemannian kernels. With a LogDet divergence based objective function, the hybrid kernels are then fused by our hybrid metric learning framework, which can efficiently perform the fusing procedure on large-scale videos. The proposed method is evaluated on four public and challenging large-scale video face datasets. Extensive experimental results demonstrate that our method has a clear superiority over the state-of-the-art set-based methods for large-scale video-based face recognition. HighlightsRepresent image set by mean, covariance and Gaussian for discriminant information.Heterogeneous Euclidean and Riemannian kernels are exploited and fused clearly.Clear superiority over state-of-the-art set-based methods is achieved in testing.
This record has no associated files available for download.
More information
e-pub ahead of print date: 20 March 2015
Published date: 17 June 2015
Identifiers
Local EPrints ID: 501093
URI: http://eprints.soton.ac.uk/id/eprint/501093
ISSN: 0031-3203
PURE UUID: 671e037f-aa70-473f-b0a7-6da60d036077
Catalogue record
Date deposited: 23 May 2025 16:45
Last modified: 25 May 2025 05:21
Export record
Altmetrics
Contributors
Author:
Zhiwu Huang
Author:
Ruiping Wang
Author:
Shiguang Shan
Author:
Xilin Chen
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics