Statistical adaptive metric learning in visual action feature set recognition

Shuanglu Dai, Hong Man

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Great variances in visual features often present significant challenges in human action recognitions. To address this common problem, this paper proposes a statistical adaptive metric learning (SAML) method by exploring various selections and combinations of multiple statistics in a unified metric learning framework. Most statistics have certain advantages in specific controlled environments, and systematic selections and combinations can adapt them to more realistic “in the wild” scenarios. In the proposed method, multiple statistics, include means, covariance matrices and Gaussian distributions, are explicitly mapped or generated in the Riemannian manifolds. Typically, d-dimensional mean vectors in Rd are mapped to a Rd ×d space of symmetric positive definite (SPD) matrices Symd+. Subsequently, by embedding the heterogeneous manifolds in their tangent Hilbert space, subspace combination with minimal deviation is selected from multiple statistics. Then Mahalanobis metrics are introduced to map them back into the Euclidean space. Unified optimizations are finally performed based on the Euclidean distances. In the proposed method, subspaces with smaller deviations are selected before metric learning. Therefore, by exploring different metric combinations, the final learning is more representative and effective than exhaustively learning from all the hybrid metrics. Experimental evaluations are conducted on human action recognitions in both static and dynamic scenarios. Promising results demonstrate that the proposed method performs effectively for human action recognitions in the wild.

Original languageEnglish (US)
Pages (from-to)138-148
Number of pages11
JournalImage and Vision Computing
Volume55
DOIs
StatePublished - Nov 1 2016

Fingerprint

Statistics
Hilbert spaces
Gaussian distribution
Covariance matrix

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Computer Vision and Pattern Recognition

Cite this

@article{725d6f9b9e954977a00f32e70aba1a54,
title = "Statistical adaptive metric learning in visual action feature set recognition",
abstract = "Great variances in visual features often present significant challenges in human action recognitions. To address this common problem, this paper proposes a statistical adaptive metric learning (SAML) method by exploring various selections and combinations of multiple statistics in a unified metric learning framework. Most statistics have certain advantages in specific controlled environments, and systematic selections and combinations can adapt them to more realistic “in the wild” scenarios. In the proposed method, multiple statistics, include means, covariance matrices and Gaussian distributions, are explicitly mapped or generated in the Riemannian manifolds. Typically, d-dimensional mean vectors in Rd are mapped to a Rd ×d space of symmetric positive definite (SPD) matrices Symd+. Subsequently, by embedding the heterogeneous manifolds in their tangent Hilbert space, subspace combination with minimal deviation is selected from multiple statistics. Then Mahalanobis metrics are introduced to map them back into the Euclidean space. Unified optimizations are finally performed based on the Euclidean distances. In the proposed method, subspaces with smaller deviations are selected before metric learning. Therefore, by exploring different metric combinations, the final learning is more representative and effective than exhaustively learning from all the hybrid metrics. Experimental evaluations are conducted on human action recognitions in both static and dynamic scenarios. Promising results demonstrate that the proposed method performs effectively for human action recognitions in the wild.",
author = "Shuanglu Dai and Hong Man",
year = "2016",
month = "11",
day = "1",
doi = "https://doi.org/10.1016/j.imavis.2016.04.003",
language = "English (US)",
volume = "55",
pages = "138--148",
journal = "Image and Vision Computing",
issn = "0262-8856",
publisher = "Elsevier Limited",

}

Statistical adaptive metric learning in visual action feature set recognition. / Dai, Shuanglu; Man, Hong.

In: Image and Vision Computing, Vol. 55, 01.11.2016, p. 138-148.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Statistical adaptive metric learning in visual action feature set recognition

AU - Dai, Shuanglu

AU - Man, Hong

PY - 2016/11/1

Y1 - 2016/11/1

N2 - Great variances in visual features often present significant challenges in human action recognitions. To address this common problem, this paper proposes a statistical adaptive metric learning (SAML) method by exploring various selections and combinations of multiple statistics in a unified metric learning framework. Most statistics have certain advantages in specific controlled environments, and systematic selections and combinations can adapt them to more realistic “in the wild” scenarios. In the proposed method, multiple statistics, include means, covariance matrices and Gaussian distributions, are explicitly mapped or generated in the Riemannian manifolds. Typically, d-dimensional mean vectors in Rd are mapped to a Rd ×d space of symmetric positive definite (SPD) matrices Symd+. Subsequently, by embedding the heterogeneous manifolds in their tangent Hilbert space, subspace combination with minimal deviation is selected from multiple statistics. Then Mahalanobis metrics are introduced to map them back into the Euclidean space. Unified optimizations are finally performed based on the Euclidean distances. In the proposed method, subspaces with smaller deviations are selected before metric learning. Therefore, by exploring different metric combinations, the final learning is more representative and effective than exhaustively learning from all the hybrid metrics. Experimental evaluations are conducted on human action recognitions in both static and dynamic scenarios. Promising results demonstrate that the proposed method performs effectively for human action recognitions in the wild.

AB - Great variances in visual features often present significant challenges in human action recognitions. To address this common problem, this paper proposes a statistical adaptive metric learning (SAML) method by exploring various selections and combinations of multiple statistics in a unified metric learning framework. Most statistics have certain advantages in specific controlled environments, and systematic selections and combinations can adapt them to more realistic “in the wild” scenarios. In the proposed method, multiple statistics, include means, covariance matrices and Gaussian distributions, are explicitly mapped or generated in the Riemannian manifolds. Typically, d-dimensional mean vectors in Rd are mapped to a Rd ×d space of symmetric positive definite (SPD) matrices Symd+. Subsequently, by embedding the heterogeneous manifolds in their tangent Hilbert space, subspace combination with minimal deviation is selected from multiple statistics. Then Mahalanobis metrics are introduced to map them back into the Euclidean space. Unified optimizations are finally performed based on the Euclidean distances. In the proposed method, subspaces with smaller deviations are selected before metric learning. Therefore, by exploring different metric combinations, the final learning is more representative and effective than exhaustively learning from all the hybrid metrics. Experimental evaluations are conducted on human action recognitions in both static and dynamic scenarios. Promising results demonstrate that the proposed method performs effectively for human action recognitions in the wild.

UR - http://www.scopus.com/inward/record.url?scp=84964701703&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84964701703&partnerID=8YFLogxK

U2 - https://doi.org/10.1016/j.imavis.2016.04.003

DO - https://doi.org/10.1016/j.imavis.2016.04.003

M3 - Article

VL - 55

SP - 138

EP - 148

JO - Image and Vision Computing

JF - Image and Vision Computing

SN - 0262-8856

ER -