More about VLAD: A leap from Euclidean to Riemannian manifolds

Masoud Faraki; Mehrtash T. Harandi; Fatih Porikli

doi:10.1109/CVPR.2015.7299129

More about VLAD: A leap from Euclidean to Riemannian manifolds

Masoud Faraki, Mehrtash T. Harandi, Fatih Porikli

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

41 Citations (Scopus)

Abstract

This paper takes a step forward in image and video coding by extending the well-known Vector of Locally Aggregated Descriptors (VLAD) onto an extensive space of curved Riemannian manifolds. We provide a comprehensive mathematical framework that formulates the aggregation problem of such manifold data into an elegant solution. In particular, we consider structured descriptors from visual data, namely Region Covariance Descriptors and linear subspaces that reside on the manifold of Symmetric Positive Definite matrices and the Grassmannian manifolds, respectively. Through rigorous experimental validation, we demonstrate the superior performance of this novel Riemannian VLAD descriptor on several visual classification tasks including video-based face recognition, dynamic scene recognition, and head pose classification.

Original language	English
Title of host publication	IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
Publisher	IEEE Computer Society
Pages	4951-4960
Number of pages	10
ISBN (Electronic)	9781467369640
DOIs	https://doi.org/10.1109/CVPR.2015.7299129
Publication status	Published - 14 Oct 2015
Event	IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 - Boston, United States Duration: 7 Jun 2015 → 12 Jun 2015

Publication series

Name	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume	07-12-June-2015
ISSN (Print)	1063-6919

Conference

Conference	IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
Country/Territory	United States
City	Boston
Period	7/06/15 → 12/06/15

Access to Document

10.1109/CVPR.2015.7299129

Cite this

Faraki, M., Harandi, M. T., & Porikli, F. (2015). More about VLAD: A leap from Euclidean to Riemannian manifolds. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 (pp. 4951-4960). Article 7299129 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 07-12-June-2015). IEEE Computer Society. https://doi.org/10.1109/CVPR.2015.7299129

@inproceedings{73d44e8b0c934d69995b81ef0a0bcee3,

title = "More about VLAD: A leap from Euclidean to Riemannian manifolds",

abstract = "This paper takes a step forward in image and video coding by extending the well-known Vector of Locally Aggregated Descriptors (VLAD) onto an extensive space of curved Riemannian manifolds. We provide a comprehensive mathematical framework that formulates the aggregation problem of such manifold data into an elegant solution. In particular, we consider structured descriptors from visual data, namely Region Covariance Descriptors and linear subspaces that reside on the manifold of Symmetric Positive Definite matrices and the Grassmannian manifolds, respectively. Through rigorous experimental validation, we demonstrate the superior performance of this novel Riemannian VLAD descriptor on several visual classification tasks including video-based face recognition, dynamic scene recognition, and head pose classification.",

author = "Masoud Faraki and Harandi, {Mehrtash T.} and Fatih Porikli",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 ; Conference date: 07-06-2015 Through 12-06-2015",

year = "2015",

month = oct,

day = "14",

doi = "10.1109/CVPR.2015.7299129",

language = "English",

series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

publisher = "IEEE Computer Society",

pages = "4951--4960",

booktitle = "IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015",

address = "United States",

}

Faraki, M, Harandi, MT & Porikli, F 2015, More about VLAD: A leap from Euclidean to Riemannian manifolds. in IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015., 7299129, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 07-12-June-2015, IEEE Computer Society, pp. 4951-4960, IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, United States, 7/06/15. https://doi.org/10.1109/CVPR.2015.7299129

More about VLAD: A leap from Euclidean to Riemannian manifolds. / Faraki, Masoud; Harandi, Mehrtash T.; Porikli, Fatih.
IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015. IEEE Computer Society, 2015. p. 4951-4960 7299129 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 07-12-June-2015).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - More about VLAD

T2 - IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015

AU - Faraki, Masoud

AU - Harandi, Mehrtash T.

AU - Porikli, Fatih

PY - 2015/10/14

Y1 - 2015/10/14

N2 - This paper takes a step forward in image and video coding by extending the well-known Vector of Locally Aggregated Descriptors (VLAD) onto an extensive space of curved Riemannian manifolds. We provide a comprehensive mathematical framework that formulates the aggregation problem of such manifold data into an elegant solution. In particular, we consider structured descriptors from visual data, namely Region Covariance Descriptors and linear subspaces that reside on the manifold of Symmetric Positive Definite matrices and the Grassmannian manifolds, respectively. Through rigorous experimental validation, we demonstrate the superior performance of this novel Riemannian VLAD descriptor on several visual classification tasks including video-based face recognition, dynamic scene recognition, and head pose classification.

AB - This paper takes a step forward in image and video coding by extending the well-known Vector of Locally Aggregated Descriptors (VLAD) onto an extensive space of curved Riemannian manifolds. We provide a comprehensive mathematical framework that formulates the aggregation problem of such manifold data into an elegant solution. In particular, we consider structured descriptors from visual data, namely Region Covariance Descriptors and linear subspaces that reside on the manifold of Symmetric Positive Definite matrices and the Grassmannian manifolds, respectively. Through rigorous experimental validation, we demonstrate the superior performance of this novel Riemannian VLAD descriptor on several visual classification tasks including video-based face recognition, dynamic scene recognition, and head pose classification.

UR - http://www.scopus.com/inward/record.url?scp=84959187160&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2015.7299129

DO - 10.1109/CVPR.2015.7299129

M3 - Conference contribution

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 4951

EP - 4960

BT - IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015

PB - IEEE Computer Society

Y2 - 7 June 2015 through 12 June 2015

ER -

More about VLAD: A leap from Euclidean to Riemannian manifolds

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this