From facial parts responses to face detection: A deep learning approach

Shuo Yang; Ping Luo; Chen Change Loy; Xiaoou Tang

doi:10.1109/ICCV.2015.419

From facial parts responses to face detection: A deep learning approach

Shuo Yang, Ping Luo, Chen Change Loy, Xiaoou Tang

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

483 Citations (Scopus)

Abstract

In this paper, we propose a novel deep convolutional network (DCN) that achieves outstanding performance on FDDB, PASCAL Face, and AFW. Specifically, our method achieves a high recall rate of 90.99% on the challenging FDDB benchmark, outperforming the state-of-the-art method [23] by a large margin of 2.91%. Importantly, we consider finding faces from a new perspective through scoring facial parts responses by their spatial structure and arrangement. The scoring mechanism is carefully formulated considering challenging cases where faces are only partially visible. This consideration allows our network to detect faces under severe occlusion and unconstrained pose variation, which are the main difficulty and bottleneck of most existing face detection approaches. We show that despite the use of DCN, our network can achieve practical runtime speed.

Original language	English
Title of host publication	2015 International Conference on Computer Vision, ICCV 2015
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	3676-3684
Number of pages	9
ISBN (Electronic)	9781467383912
DOIs	https://doi.org/10.1109/ICCV.2015.419
Publication status	Published - Feb 17 2015
Externally published	Yes
Event	15th IEEE International Conference on Computer Vision, ICCV 2015 - Santiago, Chile Duration: Dec 11 2015 → Dec 18 2015

Publication series

Name	Proceedings of the IEEE International Conference on Computer Vision
Volume	2015 International Conference on Computer Vision, ICCV 2015
ISSN (Print)	1550-5499

Conference

Conference	15th IEEE International Conference on Computer Vision, ICCV 2015
Country/Territory	Chile
City	Santiago
Period	12/11/15 → 12/18/15

Bibliographical note

Publisher Copyright:
© 2015 IEEE.

ASJC Scopus Subject Areas

Software
Computer Vision and Pattern Recognition

Access to Document

10.1109/ICCV.2015.419

Cite this

Yang, S., Luo, P., Loy, C. C., & Tang, X. (2015). From facial parts responses to face detection: A deep learning approach. In 2015 International Conference on Computer Vision, ICCV 2015 (pp. 3676-3684). Article 7410776 (Proceedings of the IEEE International Conference on Computer Vision; Vol. 2015 International Conference on Computer Vision, ICCV 2015). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCV.2015.419

@inproceedings{f1e5a1cc582f4dd7b7245c0fdef7f51d,

title = "From facial parts responses to face detection: A deep learning approach",

abstract = "In this paper, we propose a novel deep convolutional network (DCN) that achieves outstanding performance on FDDB, PASCAL Face, and AFW. Specifically, our method achieves a high recall rate of 90.99\% on the challenging FDDB benchmark, outperforming the state-of-the-art method [23] by a large margin of 2.91\%. Importantly, we consider finding faces from a new perspective through scoring facial parts responses by their spatial structure and arrangement. The scoring mechanism is carefully formulated considering challenging cases where faces are only partially visible. This consideration allows our network to detect faces under severe occlusion and unconstrained pose variation, which are the main difficulty and bottleneck of most existing face detection approaches. We show that despite the use of DCN, our network can achieve practical runtime speed.",

author = "Shuo Yang and Ping Luo and Loy, \{Chen Change\} and Xiaoou Tang",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; 15th IEEE International Conference on Computer Vision, ICCV 2015 ; Conference date: 11-12-2015 Through 18-12-2015",

year = "2015",

month = feb,

day = "17",

doi = "10.1109/ICCV.2015.419",

language = "English",

series = "Proceedings of the IEEE International Conference on Computer Vision",

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

pages = "3676--3684",

booktitle = "2015 International Conference on Computer Vision, ICCV 2015",

address = "United States",

}

Yang, S, Luo, P, Loy, CC & Tang, X 2015, From facial parts responses to face detection: A deep learning approach. in 2015 International Conference on Computer Vision, ICCV 2015., 7410776, Proceedings of the IEEE International Conference on Computer Vision, vol. 2015 International Conference on Computer Vision, ICCV 2015, Institute of Electrical and Electronics Engineers Inc., pp. 3676-3684, 15th IEEE International Conference on Computer Vision, ICCV 2015, Santiago, Chile, 12/11/15. https://doi.org/10.1109/ICCV.2015.419

From facial parts responses to face detection: A deep learning approach. / Yang, Shuo; Luo, Ping; Loy, Chen Change et al.
2015 International Conference on Computer Vision, ICCV 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 3676-3684 7410776 (Proceedings of the IEEE International Conference on Computer Vision; Vol. 2015 International Conference on Computer Vision, ICCV 2015).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - From facial parts responses to face detection

T2 - 15th IEEE International Conference on Computer Vision, ICCV 2015

AU - Yang, Shuo

AU - Luo, Ping

AU - Loy, Chen Change

AU - Tang, Xiaoou

PY - 2015/2/17

Y1 - 2015/2/17

N2 - In this paper, we propose a novel deep convolutional network (DCN) that achieves outstanding performance on FDDB, PASCAL Face, and AFW. Specifically, our method achieves a high recall rate of 90.99% on the challenging FDDB benchmark, outperforming the state-of-the-art method [23] by a large margin of 2.91%. Importantly, we consider finding faces from a new perspective through scoring facial parts responses by their spatial structure and arrangement. The scoring mechanism is carefully formulated considering challenging cases where faces are only partially visible. This consideration allows our network to detect faces under severe occlusion and unconstrained pose variation, which are the main difficulty and bottleneck of most existing face detection approaches. We show that despite the use of DCN, our network can achieve practical runtime speed.

AB - In this paper, we propose a novel deep convolutional network (DCN) that achieves outstanding performance on FDDB, PASCAL Face, and AFW. Specifically, our method achieves a high recall rate of 90.99% on the challenging FDDB benchmark, outperforming the state-of-the-art method [23] by a large margin of 2.91%. Importantly, we consider finding faces from a new perspective through scoring facial parts responses by their spatial structure and arrangement. The scoring mechanism is carefully formulated considering challenging cases where faces are only partially visible. This consideration allows our network to detect faces under severe occlusion and unconstrained pose variation, which are the main difficulty and bottleneck of most existing face detection approaches. We show that despite the use of DCN, our network can achieve practical runtime speed.

UR - http://www.scopus.com/inward/record.url?scp=84973904792&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84973904792&partnerID=8YFLogxK

U2 - 10.1109/ICCV.2015.419

DO - 10.1109/ICCV.2015.419

M3 - Conference contribution

AN - SCOPUS:84973904792

T3 - Proceedings of the IEEE International Conference on Computer Vision

SP - 3676

EP - 3684

BT - 2015 International Conference on Computer Vision, ICCV 2015

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 11 December 2015 through 18 December 2015

ER -

From facial parts responses to face detection: A deep learning approach

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus Subject Areas

Access to Document

Other files and links

Cite this