東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Facial Expression Analysis via Trans...

Zhang, Xiao.

Linked to FindBook

Google Book

Amazon

博客來

Facial Expression Analysis via Transfer Learning.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Facial Expression Analysis via Transfer Learning./
Author:	Zhang, Xiao.
Description:	108 p.
Notes:	Source: Dissertation Abstracts International, Volume: 76-09(E), Section: B.
Contained By:	Dissertation Abstracts International76-09B(E).
Subject:	Computer engineering. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3689585
ISBN:	9781321690798

Facial Expression Analysis via Transfer Learning.
Zhang, Xiao.

Facial Expression Analysis via Transfer Learning. - 108 p.

Source: Dissertation Abstracts International, Volume: 76-09(E), Section: B.

Thesis (Ph.D.)--University of Denver, 2015.

Automated analysis of facial expressions has remained an interesting and challenging research topic in the field of computer vision and pattern recognition due to vast applications such as human-machine interface design, social robotics, and developmental psychology. This dissertation focuses on developing and applying transfer learning algorithms---multiple kernel learning (MKL) and multi-task learning (MTL)---to resolve the problems of facial feature fusion and the exploitation of multiple facial action units (AUs) relations in designing robust facial expression recognition systems. MKL algorithms are employed to fuse multiple facial features with different kernel functions and tackle the domain adaption problem at the kernel level within support vector machines (SVM). lp-norm is adopted to enforce both sparse and non-sparse kernel combination in our methods. We further develop and apply MTL algorithms for simultaneous detection of multiple related AUs by exploiting their inter-relationships. Three variants of task structure models are designed and investigated to obtain fine depiction of AU relations. lp-norm MTMKL and TD-MTMKL (Task-Dependent MTMKL) are group-sensitive MTL methods that model the co-occurrence relations among AUs. On the other hand, our proposed hierarchical multi-task structural learning (HMTSL) includes a latent layer to learn a hierarchical structure to exploit all possible AU inter-relations for AU detection. Extensive experiments on public face databases show that our proposed transfer learning methods have produced encouraging results compared to several state-of-the-art methods for facial expression recognition and AU detection.

ISBN: 9781321690798Subjects--Topical Terms:

621879
Computer engineering.

Facial Expression Analysis via Transfer Learning.
LDR:02529nmm a2200277 4500 001 2066583
005 20151205153414.5
008 170521s2015 ||||||||||||||||| ||eng d
020 $a 9781321690798
035 $a (MiAaPQ)AAI3689585
035 $a AAI3689585
040 $a MiAaPQ $c MiAaPQ
100 1 $a Zhang, Xiao. $3 2101938
245 1 0 $a Facial Expression Analysis via Transfer Learning.
300 $a 108 p.
500 $a Source: Dissertation Abstracts International, Volume: 76-09(E), Section: B.
500 $a Adviser: Mohammad H. Mahoor.
502 $a Thesis (Ph.D.)--University of Denver, 2015.
520 $a Automated analysis of facial expressions has remained an interesting and challenging research topic in the field of computer vision and pattern recognition due to vast applications such as human-machine interface design, social robotics, and developmental psychology. This dissertation focuses on developing and applying transfer learning algorithms---multiple kernel learning (MKL) and multi-task learning (MTL)---to resolve the problems of facial feature fusion and the exploitation of multiple facial action units (AUs) relations in designing robust facial expression recognition systems. MKL algorithms are employed to fuse multiple facial features with different kernel functions and tackle the domain adaption problem at the kernel level within support vector machines (SVM). lp-norm is adopted to enforce both sparse and non-sparse kernel combination in our methods. We further develop and apply MTL algorithms for simultaneous detection of multiple related AUs by exploiting their inter-relationships. Three variants of task structure models are designed and investigated to obtain fine depiction of AU relations. lp-norm MTMKL and TD-MTMKL (Task-Dependent MTMKL) are group-sensitive MTL methods that model the co-occurrence relations among AUs. On the other hand, our proposed hierarchical multi-task structural learning (HMTSL) includes a latent layer to learn a hierarchical structure to exploit all possible AU inter-relations for AU detection. Extensive experiments on public face databases show that our proposed transfer learning methods have produced encouraging results compared to several state-of-the-art methods for facial expression recognition and AU detection.
590 $a School code: 0061.
650 4 $a Computer engineering. $3 621879
650 4 $a Artificial intelligence. $3 516317
690 $a 0464
690 $a 0800
710 2 $a University of Denver. $b Computer Engineering. $3 1035894
773 0 $t Dissertation Abstracts International $g 76-09B(E).
790 $a 0061
791 $a Ph.D.
792 $a 2015
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3689585