A heterogeneous dictionary model for representation and recognition of human actions

Rushil Anirudh, Karthikeyan Ramamurthy, Jayaraman J. Thiagarajan, Pavan Turaga, Andreas Spanias

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

In this paper, we consider low-dimensional and sparse representation models for human actions, that are consistent with how actions evolve in high-dimensional feature spaces. We first show that human actions can be well approximated by piecewise linear structures in the feature space. Based on this, we propose a new dictionary model that considers each atom in the dictionary to be an affine subspace defined by a point and a corresponding line. When compared to centered clustering approaches such as K-means, we show that the proposed dictionary is a better generative model for human actions. Furthermore, we demonstrate the utility of this model in efficient representation and recognition of human activities that are not available in the training set.

Original languageEnglish (US)
Title of host publicationICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Pages3472-3476
Number of pages5
DOIs
StatePublished - Oct 18 2013
Event2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Vancouver, BC, Canada
Duration: May 26 2013May 31 2013

Other

Other2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013
CountryCanada
CityVancouver, BC
Period5/26/135/31/13

Fingerprint

Glossaries
Atoms

Keywords

  • Activity analysis
  • Dictionary learning
  • Sparse representations

ASJC Scopus subject areas

  • Signal Processing
  • Software
  • Electrical and Electronic Engineering

Cite this

Anirudh, R., Ramamurthy, K., Thiagarajan, J. J., Turaga, P., & Spanias, A. (2013). A heterogeneous dictionary model for representation and recognition of human actions. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (pp. 3472-3476). [6638303] https://doi.org/10.1109/ICASSP.2013.6638303

A heterogeneous dictionary model for representation and recognition of human actions. / Anirudh, Rushil; Ramamurthy, Karthikeyan; Thiagarajan, Jayaraman J.; Turaga, Pavan; Spanias, Andreas.

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2013. p. 3472-3476 6638303.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Anirudh, R, Ramamurthy, K, Thiagarajan, JJ, Turaga, P & Spanias, A 2013, A heterogeneous dictionary model for representation and recognition of human actions. in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings., 6638303, pp. 3472-3476, 2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013, Vancouver, BC, Canada, 5/26/13. https://doi.org/10.1109/ICASSP.2013.6638303
Anirudh R, Ramamurthy K, Thiagarajan JJ, Turaga P, Spanias A. A heterogeneous dictionary model for representation and recognition of human actions. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2013. p. 3472-3476. 6638303 https://doi.org/10.1109/ICASSP.2013.6638303
Anirudh, Rushil ; Ramamurthy, Karthikeyan ; Thiagarajan, Jayaraman J. ; Turaga, Pavan ; Spanias, Andreas. / A heterogeneous dictionary model for representation and recognition of human actions. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2013. pp. 3472-3476
@inproceedings{a2f2e2fd2e6a45cea4d9a4103c2d7168,
title = "A heterogeneous dictionary model for representation and recognition of human actions",
abstract = "In this paper, we consider low-dimensional and sparse representation models for human actions, that are consistent with how actions evolve in high-dimensional feature spaces. We first show that human actions can be well approximated by piecewise linear structures in the feature space. Based on this, we propose a new dictionary model that considers each atom in the dictionary to be an affine subspace defined by a point and a corresponding line. When compared to centered clustering approaches such as K-means, we show that the proposed dictionary is a better generative model for human actions. Furthermore, we demonstrate the utility of this model in efficient representation and recognition of human activities that are not available in the training set.",
keywords = "Activity analysis, Dictionary learning, Sparse representations",
author = "Rushil Anirudh and Karthikeyan Ramamurthy and Thiagarajan, {Jayaraman J.} and Pavan Turaga and Andreas Spanias",
year = "2013",
month = "10",
day = "18",
doi = "10.1109/ICASSP.2013.6638303",
language = "English (US)",
isbn = "9781479903566",
pages = "3472--3476",
booktitle = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

}

TY - GEN

T1 - A heterogeneous dictionary model for representation and recognition of human actions

AU - Anirudh, Rushil

AU - Ramamurthy, Karthikeyan

AU - Thiagarajan, Jayaraman J.

AU - Turaga, Pavan

AU - Spanias, Andreas

PY - 2013/10/18

Y1 - 2013/10/18

N2 - In this paper, we consider low-dimensional and sparse representation models for human actions, that are consistent with how actions evolve in high-dimensional feature spaces. We first show that human actions can be well approximated by piecewise linear structures in the feature space. Based on this, we propose a new dictionary model that considers each atom in the dictionary to be an affine subspace defined by a point and a corresponding line. When compared to centered clustering approaches such as K-means, we show that the proposed dictionary is a better generative model for human actions. Furthermore, we demonstrate the utility of this model in efficient representation and recognition of human activities that are not available in the training set.

AB - In this paper, we consider low-dimensional and sparse representation models for human actions, that are consistent with how actions evolve in high-dimensional feature spaces. We first show that human actions can be well approximated by piecewise linear structures in the feature space. Based on this, we propose a new dictionary model that considers each atom in the dictionary to be an affine subspace defined by a point and a corresponding line. When compared to centered clustering approaches such as K-means, we show that the proposed dictionary is a better generative model for human actions. Furthermore, we demonstrate the utility of this model in efficient representation and recognition of human activities that are not available in the training set.

KW - Activity analysis

KW - Dictionary learning

KW - Sparse representations

UR - http://www.scopus.com/inward/record.url?scp=84890492168&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84890492168&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2013.6638303

DO - 10.1109/ICASSP.2013.6638303

M3 - Conference contribution

AN - SCOPUS:84890492168

SN - 9781479903566

SP - 3472

EP - 3476

BT - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

ER -