Home > Research > Publications & Outputs > Enhanced Gradient-Based Local Feature Descripto...

Research

Links

Text available via DOI:

Keywords

View graph of relations

Enhanced Gradient-Based Local Feature Descriptors by Saliency Map for Egocentric Action Recognition

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

Enhanced Gradient-Based Local Feature Descriptors by Saliency Map for Egocentric Action Recognition. / Zuo, Zheming; Wei, Bo; Chao, Fei et al.
In: Applied System Innovation, Vol. 2, No. 1, 7, 31.03.2019.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Zuo, Z, Wei, B, Chao, F, Qu, Y, Peng, Y & Yang, L 2019, 'Enhanced Gradient-Based Local Feature Descriptors by Saliency Map for Egocentric Action Recognition', Applied System Innovation, vol. 2, no. 1, 7. https://doi.org/10.3390/asi2010007

APA

Zuo, Z., Wei, B., Chao, F., Qu, Y., Peng, Y., & Yang, L. (2019). Enhanced Gradient-Based Local Feature Descriptors by Saliency Map for Egocentric Action Recognition. Applied System Innovation, 2(1), Article 7. https://doi.org/10.3390/asi2010007

Vancouver

Zuo Z, Wei B, Chao F, Qu Y, Peng Y, Yang L. Enhanced Gradient-Based Local Feature Descriptors by Saliency Map for Egocentric Action Recognition. Applied System Innovation. 2019 Mar 31;2(1):7. Epub 2019 Feb 19. doi: 10.3390/asi2010007

Author

Zuo, Zheming ; Wei, Bo ; Chao, Fei et al. / Enhanced Gradient-Based Local Feature Descriptors by Saliency Map for Egocentric Action Recognition. In: Applied System Innovation. 2019 ; Vol. 2, No. 1.

Bibtex

@article{f4ae0c1f01c64401b95c39a5d5c8a8a8,
title = "Enhanced Gradient-Based Local Feature Descriptors by Saliency Map for Egocentric Action Recognition",
abstract = "Egocentric video analysis is an important tool in healthcare that serves a variety of purposes, such as memory aid systems and physical rehabilitation, and feature extraction is an indispensable process for such analysis. Local feature descriptors have been widely applied due to their simple implementation and reasonable efficiency and performance in applications. This paper proposes an enhanced spatial and temporal local feature descriptor extraction method to boost the performance of action classification. The approach allows local feature descriptors to take advantage of saliency maps, which provide insights into visual attention. The effectiveness of the proposed method was validated and evaluated by a comparative study, whose results demonstrated an improved accuracy of around 2%",
keywords = "saliency map, local feature descriptors, egocentril action recognition, HOG, HMG, HOF, MBH",
author = "Zheming Zuo and Bo Wei and Fei Chao and Yanpeng Qu and Yonghong Peng and Longzhi Yang",
year = "2019",
month = mar,
day = "31",
doi = "10.3390/asi2010007",
language = "Undefined/Unknown",
volume = "2",
journal = "Applied System Innovation",
publisher = "Multidisciplinary Digital Publishing Institute",
number = "1",

}

RIS

TY - JOUR

T1 - Enhanced Gradient-Based Local Feature Descriptors by Saliency Map for Egocentric Action Recognition

AU - Zuo, Zheming

AU - Wei, Bo

AU - Chao, Fei

AU - Qu, Yanpeng

AU - Peng, Yonghong

AU - Yang, Longzhi

PY - 2019/3/31

Y1 - 2019/3/31

N2 - Egocentric video analysis is an important tool in healthcare that serves a variety of purposes, such as memory aid systems and physical rehabilitation, and feature extraction is an indispensable process for such analysis. Local feature descriptors have been widely applied due to their simple implementation and reasonable efficiency and performance in applications. This paper proposes an enhanced spatial and temporal local feature descriptor extraction method to boost the performance of action classification. The approach allows local feature descriptors to take advantage of saliency maps, which provide insights into visual attention. The effectiveness of the proposed method was validated and evaluated by a comparative study, whose results demonstrated an improved accuracy of around 2%

AB - Egocentric video analysis is an important tool in healthcare that serves a variety of purposes, such as memory aid systems and physical rehabilitation, and feature extraction is an indispensable process for such analysis. Local feature descriptors have been widely applied due to their simple implementation and reasonable efficiency and performance in applications. This paper proposes an enhanced spatial and temporal local feature descriptor extraction method to boost the performance of action classification. The approach allows local feature descriptors to take advantage of saliency maps, which provide insights into visual attention. The effectiveness of the proposed method was validated and evaluated by a comparative study, whose results demonstrated an improved accuracy of around 2%

KW - saliency map

KW - local feature descriptors

KW - egocentril action recognition

KW - HOG

KW - HMG

KW - HOF

KW - MBH

U2 - 10.3390/asi2010007

DO - 10.3390/asi2010007

M3 - Journal article

VL - 2

JO - Applied System Innovation

JF - Applied System Innovation

IS - 1

M1 - 7

ER -