Time Efficient Micro-Expression Recognition using Weighted Spatio-Temporal Landmark Graphs

Nikin Matharaarachchi, Muhammad Fermi Pasha, Sonya Coleman, Dermot Kerr

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

28 Downloads (Pure)

Abstract

Micro-expressions have been shown to be effective in understanding the genuine emotions of a person. While many advances have been made in detecting micro-expressions using deep learning, previous studies in recognizing micro-expressions require pre-processing steps and the use of large feature sets resulting in large runtimes and thus have limited applicability in real-world scenarios. In this paper, we propose time-efficient end-to-end framework which uses landmark-based positional features to generate spatio-temporal graphs that can be applied to micro-expression recognition using Graph Convolutional Neural
Networks (GCNs). We explore the importance of landmark features and propose a selective feature reduction approach to further improve efficiency. We perform experiments using the SMIC, CASMEII and SAMM datasets and demonstrate that our approach significantly speeds up predictions and delivers results
comparable to the state-of-the-art.
Original languageEnglish
Title of host publication2023 International Conference on Machine Learning and Applications (ICMLA)
EditorsM. Arif Wani, Mihai Boicu, Moamar Sayed-Mouchaweh, Pedro Henriques Abreu, Joao Gama
PublisherIEEE
Pages1-8
Number of pages8
ISBN (Electronic)979-8-3503-4534-6
ISBN (Print)979-8-3503-1891-3
DOIs
Publication statusPublished online - 19 Mar 2024
Event22nd International Conference on Machine Learning and Applications - Hyatt Regency Jacksonville Riverfront, Florida, United States
Duration: 15 Dec 202317 Dec 2023
https://www.icmla-conference.org/icmla23/

Publication series

NameProceedings - 22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023

Conference

Conference22nd International Conference on Machine Learning and Applications
Abbreviated titleICMLA'23
Country/TerritoryUnited States
CityFlorida
Period15/12/2317/12/23
Internet address

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Keywords

  • micro-expressions
  • emotion
  • GCN
  • Deep learning
  • graph networks
  • deep learning

Fingerprint

Dive into the research topics of 'Time Efficient Micro-Expression Recognition using Weighted Spatio-Temporal Landmark Graphs'. Together they form a unique fingerprint.

Cite this