Cross-database micro-expression recognition with deep convolutional networks

Zhaoqiang Xia, Huan Liang, Xiaopeng Hong, Xiaoyi Feng

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

14 Scopus citations

Abstract

Micro-expression recognition (MER) is attracting more and more interests as it has important applications for analyzing human behaviors. Since the recognition ability for individual datasets has been improved greatly, few works have been devoted to the cross database task of MER, which is more challenging for capturing the subtle changes of micro-expressions from different environments. In this paper, we employ an end-to-end deep model for learning the representation and classifier automatically. In the deep model, the recurrent convolutional layers are utilized to exploit the learning ability with the optical flow fields of micro-expression sequences, which are enhanced by a motion magnification procedure. To ease the influence of samples from different datasets (environments), we present three normalization methods (i.e., sample-wise, subject-wise and dataset-wise methods) to restrain the variations of samples. The experiments are performed on the cross database of MERC2019 challenge, and achieve comparative performance than the baseline method.

Original languageEnglish
Title of host publicationProceedings of 2019 3rd International Conference on Biometric Engineering and Applications, ICBEA 2019
PublisherAssociation for Computing Machinery
Pages56-60
Number of pages5
ISBN (Electronic)9781450363051
DOIs
StatePublished - 29 May 2019
Event3rd International Conference on Biometric Engineering and Applications, ICBEA 2019 - Stockholm, Sweden
Duration: 29 May 201931 May 2019

Publication series

NameACM International Conference Proceeding Series

Conference

Conference3rd International Conference on Biometric Engineering and Applications, ICBEA 2019
Country/TerritorySweden
CityStockholm
Period29/05/1931/05/19

Keywords

  • Data normalization
  • Micro-expression recognition
  • Recurrent convolutional networks

Fingerprint

Dive into the research topics of 'Cross-database micro-expression recognition with deep convolutional networks'. Together they form a unique fingerprint.

Cite this