TY - GEN
T1 - Microexpression Recognition from Action Unit-Variational Graph Autoencoder
AU - Amaanullah, Fairuuz Nurdiaz
AU - Iqbal, Mohammad
AU - Anggraini, Retno
AU - Rukmi, Alvida Mustika
AU - Hidayat, Nurul
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - Emotion recognition has helped humans express their feelings, assisting in therapy sessions or criminal investigations. However, humans are clever enough to hide their feelings, making them hard to recognize. Micro-expression can help reveal their genuine emotions from very fast-changing expressions. This study attempts to recognize micro-expression based on a deep learning model. A recent related study used action unit with graph neural networks but mostly fail to generalize the facial graph structure. To overcome the issue, we propose an integrated deep learning model from action unit-graph neural networks to build the facial graph structure and variational autoencoders to extract the latent information from it called AU-VGAE. In such way, we offer better generalization to learn the facial graph structure. In this study, the proposed model was evaluated on a public micro-expression dataset. The evaluation showed the proposed model performs better than state-of-the-art models.
AB - Emotion recognition has helped humans express their feelings, assisting in therapy sessions or criminal investigations. However, humans are clever enough to hide their feelings, making them hard to recognize. Micro-expression can help reveal their genuine emotions from very fast-changing expressions. This study attempts to recognize micro-expression based on a deep learning model. A recent related study used action unit with graph neural networks but mostly fail to generalize the facial graph structure. To overcome the issue, we propose an integrated deep learning model from action unit-graph neural networks to build the facial graph structure and variational autoencoders to extract the latent information from it called AU-VGAE. In such way, we offer better generalization to learn the facial graph structure. In this study, the proposed model was evaluated on a public micro-expression dataset. The evaluation showed the proposed model performs better than state-of-the-art models.
KW - Action unit
KW - Emotion Recognition
KW - Generative Model
KW - Graph Neural Networks
KW - Micro-expression Recognition
UR - https://www.scopus.com/pages/publications/105004410501
U2 - 10.1109/ISRITI64779.2024.10963473
DO - 10.1109/ISRITI64779.2024.10963473
M3 - Conference contribution
AN - SCOPUS:105004410501
T3 - 7th International Seminar on Research of Information Technology and Intelligent Systems: Advanced Intelligent Systems in Contemporary Society, ISRITI 2024 - Proceedings
SP - 391
EP - 396
BT - 7th International Seminar on Research of Information Technology and Intelligent Systems
A2 - Wibowo, Ferry Wahyu
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 7th International Seminar on Research of Information Technology and Intelligent Systems, ISRITI 2024
Y2 - 11 December 2024
ER -