Micro-Expression Recognition Based On 3DCNN Combined With GRU and New Attention Mechanism

Micro-expressions, as a form of non-verbal emotional expressions, play a key role in interpersonal interaction. However, they are also quite challenging and not easy to analyze. In this paper, we propose a dual-branch shallow 3DCNN architecture that combines Gated Recurrent Unit (GRU) and enhances the Channel Attention Module (CAM) in Convolutional Block Attention Module (CBAM) to make it more suitable for recognizing micro facial expressions. Experiments show that the proposed method can achieve good results with a relatively simple architecture. The source code and pre-trained models are available at https://github.com/dannyFan-0201/ICIP_2024.

1. Introduction

The study of micro-expressions provides a more accurate insight into an individual’s emotional and psychological state by deeply understanding the messages conveyed through expressions. In today’s society, the importance of interpersonal communication cannot be ignored. Unlike ordinary macro-expressions [1, 2, 3], micro-expressions refer to subtle facial movements that last very briefly, usually only 1/2 or 1/4 of a second. Detecting them is challenging; however, this brevity allows them to more directly reflect the true emotion of an individual. These subtle and rapid emotional expressions have significant applications in psychology, human behavior, clinical psychotherapy, crime prevention, and lie detection [4, 5].