More about VLAD: A leap from Euclidean to Riemannian manifolds

Masoud Faraki, Mehrtash T. Harandi, Fatih Porikli

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

29 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 languageEnglish
Title of host publicationIEEE Conference on Computer Vision and Pattern Recognition (CVPR 2015)
EditorsKristen Grauman, Erik Learned-Miller, Antonio Torralba, Andrew Zisserman
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages4951-4960
Number of pages10
ISBN (Electronic)9781467369640
ISBN (Print)9781467369657
DOIs
Publication statusPublished - 14 Oct 2015
Externally publishedYes
EventIEEE Conference on Computer Vision and Pattern Recognition 2015 - Hynes Convention Center, Boston, United States of America
Duration: 7 Jun 201512 Jun 2015
http://www.pamitc.org/cvpr15/ (Website)
https://ieeexplore.ieee.org/xpl/conhome/7293313/proceeding (Proceedings)

Conference

ConferenceIEEE Conference on Computer Vision and Pattern Recognition 2015
Abbreviated titleCVPR 2015
CountryUnited States of America
CityBoston
Period7/06/1512/06/15
Internet address

Cite this