标题:Coupled source domain targetized with updating tag vectors for micro-expression recognition
作者:Zhu, Xuena; Ben, Xianye; Liu, Shigang; Yan, Rui; Meng, Weixiao
作者机构:[Zhu, Xuena; Ben, Xianye] Shandong Univ, Sch Informat Sci & Engn, 27 Shanda South Rd, Jinan 250100, Peoples R China.; [Liu, Shigang] Shaanxi Normal 更多
通讯作者:Ben, Xianye
通讯作者地址:[Ben, XY]Shandong Univ, Sch Informat Sci & Engn, 27 Shanda South Rd, Jinan 250100, Peoples R China.
来源:MULTIMEDIA TOOLS AND APPLICATIONS
出版年:2018
卷:77
期:3
页码:3105-3124
DOI:10.1007/s11042-017-4943-z
关键词:Micro-expression recognition; Coupled source domain targetized; Tag; vectors; Transfer learning
摘要:Micro-expression has raised increasing attention for analyzing human inner emotions. However, most micro-expression recognition methods are developed with specific feature representations and extraction methods, such as local binary pattern on three orthogonal planes (LBP-TOP) and optical flow. The performance in such micro-expression recognition models is not high due to the limited training samples and the unequal size of the sample category. To improve the performance, we present a novel algorithm, named coupled source domain targetized with updating tag vectors, and we apply it to the micro-expression recognition. This method leverages rich speech data to enhance micro-expression recognition by transferring learning from the speech to the micro-expression recognition. The method highlights are: it simultaneously projects micro-expression samples and speech samples into a common space, then minimizes the reconstruction error between the speech and micro-expression samples, with an updating tag vectors added in the reconstruction process. It performs recognition by using dictionary learning together with support vector machine (SVM). Experimental results on the CASIA Chinese emotional corpus and CASME II micro-expression database demonstrate the effectiveness of our method.
收录类别:EI;SCOPUS;SCIE
WOS核心被引频次:2
Scopus被引频次:2
资源类型:期刊论文
原文链接:https://www.scopus.com/inward/record.uri?eid=2-s2.0-85025445774&doi=10.1007%2fs11042-017-4943-z&partnerID=40&md5=0f0d1ff1147e40624ffc6bae4f3a98fd
TOP