MERANet: Facial Micro-Expression Recognition using 3D Residual Attention Network

TL;DR

MERANet is a novel 3D residual attention network that improves micro-expression recognition by focusing on subtle facial regions through spatial-temporal and channel attention mechanisms, achieving state-of-the-art results.

Contribution

The paper introduces MERANet, a 3D residual attention model that effectively captures fine-grained features for micro-expression recognition, addressing challenges of small facial regions and limited data.

Findings

Outperforms existing methods on benchmark datasets

Effectively captures subtle facial micro-expressions

Utilizes combined spatial-temporal and channel attention mechanisms

Abstract

Micro-expression has emerged as a promising modality in affective computing due to its high objectivity in emotion detection. Despite the higher recognition accuracy provided by the deep learning models, there are still significant scope for improvements in micro-expression recognition techniques. The presence of micro-expressions in small-local regions of the face, as well as the limited size of available databases, continue to limit the accuracy in recognizing micro-expressions. In this work, we propose a facial micro-expression recognition model using 3D residual attention network named MERANet to tackle such challenges. The proposed model takes advantage of spatial-temporal attention and channel attention together, to learn deeper fine-grained subtle features for classification of emotions. Further, the proposed model encompasses both spatial and temporal information simultaneously using the 3D kernels and residual connections. Moreover, the channel features and spatio-temporal features are re-calibrated using the channel and spatio-temporal attentions, respectively in each residual module. Our attention mechanism enables the model to learn to focus on different facial areas of interest. The experiments are conducted on benchmark facial micro-expression datasets. A superior performance is observed as compared to the state-of-the-art for facial micro-expression recognition on benchmark data.