Continuous valence-arousal space prediction and recognition based on feature fusion

Misbah Ayoub, Haiyang Zhang, Andrew Abel

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

Abstract

In emotion recognition, the multimodal feature fusion approach for facial expression recognition is useful due to its versatility and adaptability. It leads to improved model performance by capturing information from different modalities. In this study, we employ feature-level fusion, integrating CNN and HOG features. To predict continuous valence and arousal values, we utilize a Feedforward neural network and Gradient Boosting. Performance evaluation is conducted using Mean Squared Error (MSE) and Root Mean Squared Error (RMSE). The paper presents experiments using the ADFES dataset, considering low, medium, and high intensities, as well as an augmented video dataset. The results shows that instead of relying on complex models, accuracy can be achieved by combining various types of features with appropriate hyperparameter settings and tuning. This approach is not only cost-effective in terms of computation but also robust and computationally efficient.
Original languageEnglish
Title of host publication2024 IEEE International Conference on Industrial Technology (ICIT)
Place of PublicationPiscataway, NJ
PublisherIEEE
ISBN (Electronic)9798350340266
ISBN (Print)979-8-3503-4027-3
DOIs
Publication statusPublished - 5 Jun 2024
Event2024 IEEE International Conference on Industrial Technology (ICIT) - Bristol, United Kingdom
Duration: 25 Mar 202427 Mar 2024

Publication series

NameIEEE International Conference on Industrial Technology (ICIT)
PublisherIEEE
Volume2024
ISSN (Electronic)2643-2978

Conference

Conference2024 IEEE International Conference on Industrial Technology (ICIT)
Country/TerritoryUnited Kingdom
CityBristol
Period25/03/2427/03/24

Keywords

  • CNN
  • CNN-HOG
  • Emotion recognition
  • Feature Fusion
  • Feature-Level-Fusion
  • HOG
  • Multimodal Fusion
  • Valence-Arousal Space

Fingerprint

Dive into the research topics of 'Continuous valence-arousal space prediction and recognition based on feature fusion'. Together they form a unique fingerprint.

Cite this