Visual attribute classification using feature selection and convolutional neural network

Rongqiang Qian; Yong Yue; Frans Coenen; Bailing Zhang

doi:10.1109/ICSP.2016.7877912

Visual attribute classification using feature selection and convolutional neural network

Rongqiang Qian, Yong Yue, Frans Coenen, Bailing Zhang

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

8 Citations (Scopus)

Abstract

Visual attribute classification has been widely discussed due to its impact on lots of applications, such as face recognition, action recognition and scene representation. Recently, Convolutional Neural Networks (CNNs) have demonstrated promising performance in image recognition, object detection and many other computer vision areas. Such networks are able to automatically learn a hierarchy of discriminate features that richly describe image content. However, dimensions of features of CNNs are usually very large. In this paper, we propose a visual attribute classification system based on feature selection and CNNs. Extensive experiments have been conducted using the Berkeley Attributes of People dataset. The best overall mean average precision (mAP) is about 89.2%.

Original language	English
Title of host publication	ICSP 2016 - 2016 IEEE 13th International Conference on Signal Processing, Proceedings
Editors	Yuan Baozong, Ruan Qiuqi, Zhao Yao, An Gaoyun
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	649-653
Number of pages	5
ISBN (Electronic)	9781509013449
DOIs	https://doi.org/10.1109/ICSP.2016.7877912
Publication status	Published - 2 Jul 2016
Event	13th IEEE International Conference on Signal Processing, ICSP 2016 - Chengdu, China Duration: 6 Nov 2016 → 10 Nov 2016

Publication series

Name	International Conference on Signal Processing Proceedings, ICSP
Volume	0

Conference

Conference	13th IEEE International Conference on Signal Processing, ICSP 2016
Country/Territory	China
City	Chengdu
Period	6/11/16 → 10/11/16

Keywords

convolutional neural networks
deep learning
feature selection
visual attribute classification

Access to Document

10.1109/ICSP.2016.7877912

Cite this

Qian, R., Yue, Y., Coenen, F., & Zhang, B. (2016). Visual attribute classification using feature selection and convolutional neural network. In Y. Baozong, R. Qiuqi, Z. Yao, & A. Gaoyun (Eds.), ICSP 2016 - 2016 IEEE 13th International Conference on Signal Processing, Proceedings (pp. 649-653). Article 7877912 (International Conference on Signal Processing Proceedings, ICSP; Vol. 0). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICSP.2016.7877912

Qian, Rongqiang ; Yue, Yong ; Coenen, Frans et al. / Visual attribute classification using feature selection and convolutional neural network. ICSP 2016 - 2016 IEEE 13th International Conference on Signal Processing, Proceedings. editor / Yuan Baozong ; Ruan Qiuqi ; Zhao Yao ; An Gaoyun. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 649-653 (International Conference on Signal Processing Proceedings, ICSP).

@inproceedings{5a063102be2a4ac784a7dc56f3ff0bfc,

title = "Visual attribute classification using feature selection and convolutional neural network",

abstract = "Visual attribute classification has been widely discussed due to its impact on lots of applications, such as face recognition, action recognition and scene representation. Recently, Convolutional Neural Networks (CNNs) have demonstrated promising performance in image recognition, object detection and many other computer vision areas. Such networks are able to automatically learn a hierarchy of discriminate features that richly describe image content. However, dimensions of features of CNNs are usually very large. In this paper, we propose a visual attribute classification system based on feature selection and CNNs. Extensive experiments have been conducted using the Berkeley Attributes of People dataset. The best overall mean average precision (mAP) is about 89.2%.",

keywords = "convolutional neural networks, deep learning, feature selection, visual attribute classification",

author = "Rongqiang Qian and Yong Yue and Frans Coenen and Bailing Zhang",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 13th IEEE International Conference on Signal Processing, ICSP 2016 ; Conference date: 06-11-2016 Through 10-11-2016",

year = "2016",

month = jul,

day = "2",

doi = "10.1109/ICSP.2016.7877912",

language = "English",

series = "International Conference on Signal Processing Proceedings, ICSP",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "649--653",

editor = "Yuan Baozong and Ruan Qiuqi and Zhao Yao and An Gaoyun",

booktitle = "ICSP 2016 - 2016 IEEE 13th International Conference on Signal Processing, Proceedings",

}

Qian, R, Yue, Y, Coenen, F & Zhang, B 2016, Visual attribute classification using feature selection and convolutional neural network. in Y Baozong, R Qiuqi, Z Yao & A Gaoyun (eds), ICSP 2016 - 2016 IEEE 13th International Conference on Signal Processing, Proceedings., 7877912, International Conference on Signal Processing Proceedings, ICSP, vol. 0, Institute of Electrical and Electronics Engineers Inc., pp. 649-653, 13th IEEE International Conference on Signal Processing, ICSP 2016, Chengdu, China, 6/11/16. https://doi.org/10.1109/ICSP.2016.7877912

Visual attribute classification using feature selection and convolutional neural network. / Qian, Rongqiang; Yue, Yong; Coenen, Frans et al.
ICSP 2016 - 2016 IEEE 13th International Conference on Signal Processing, Proceedings. ed. / Yuan Baozong; Ruan Qiuqi; Zhao Yao; An Gaoyun. Institute of Electrical and Electronics Engineers Inc., 2016. p. 649-653 7877912 (International Conference on Signal Processing Proceedings, ICSP; Vol. 0).

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

TY - GEN

T1 - Visual attribute classification using feature selection and convolutional neural network

AU - Qian, Rongqiang

AU - Yue, Yong

AU - Coenen, Frans

AU - Zhang, Bailing

PY - 2016/7/2

Y1 - 2016/7/2

N2 - Visual attribute classification has been widely discussed due to its impact on lots of applications, such as face recognition, action recognition and scene representation. Recently, Convolutional Neural Networks (CNNs) have demonstrated promising performance in image recognition, object detection and many other computer vision areas. Such networks are able to automatically learn a hierarchy of discriminate features that richly describe image content. However, dimensions of features of CNNs are usually very large. In this paper, we propose a visual attribute classification system based on feature selection and CNNs. Extensive experiments have been conducted using the Berkeley Attributes of People dataset. The best overall mean average precision (mAP) is about 89.2%.

AB - Visual attribute classification has been widely discussed due to its impact on lots of applications, such as face recognition, action recognition and scene representation. Recently, Convolutional Neural Networks (CNNs) have demonstrated promising performance in image recognition, object detection and many other computer vision areas. Such networks are able to automatically learn a hierarchy of discriminate features that richly describe image content. However, dimensions of features of CNNs are usually very large. In this paper, we propose a visual attribute classification system based on feature selection and CNNs. Extensive experiments have been conducted using the Berkeley Attributes of People dataset. The best overall mean average precision (mAP) is about 89.2%.

KW - convolutional neural networks

KW - deep learning

KW - feature selection

KW - visual attribute classification

UR - http://www.scopus.com/inward/record.url?scp=85016263052&partnerID=8YFLogxK

U2 - 10.1109/ICSP.2016.7877912

DO - 10.1109/ICSP.2016.7877912

M3 - Conference Proceeding

AN - SCOPUS:85016263052

T3 - International Conference on Signal Processing Proceedings, ICSP

SP - 649

EP - 653

BT - ICSP 2016 - 2016 IEEE 13th International Conference on Signal Processing, Proceedings

A2 - Baozong, Yuan

A2 - Qiuqi, Ruan

A2 - Yao, Zhao

A2 - Gaoyun, An

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 13th IEEE International Conference on Signal Processing, ICSP 2016

Y2 - 6 November 2016 through 10 November 2016

ER -

Qian R, Yue Y, Coenen F, Zhang B. Visual attribute classification using feature selection and convolutional neural network. In Baozong Y, Qiuqi R, Yao Z, Gaoyun A, editors, ICSP 2016 - 2016 IEEE 13th International Conference on Signal Processing, Proceedings. Institute of Electrical and Electronics Engineers Inc. 2016. p. 649-653. 7877912. (International Conference on Signal Processing Proceedings, ICSP). doi: 10.1109/ICSP.2016.7877912

Visual attribute classification using feature selection and convolutional neural network

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Cite this