Micro-expression recognition with supervised contrastive learning

Ruicong Zhi

doi:10.1016/j.patrec.2022.09.006

Micro-expression recognition with supervised contrastive learning

2022-11-01

17

PRE

AI

DOI：10.1016/j.patrec.2022.09.006

Original

Original request for help

Save

Abstract

En 中文

A B S T R A C T Facial micro-expressions are involuntary movements of facial muscles that expose individual underlying emotions. Because of the subtle and diverse facial muscles change, extracting effective features to recog-nize micro-expressions is challenging. In this paper, a framework for micro-expression recognition with supervised contrastive learning (MER-Supcon) is proposed, and the primary purpose is to extract cru-cial features of micro-expressions and overcome the noise caused by irrelevant facial movements. First, a novel dual-terminal micro-expression acquisition strategy is proposed and applied to obtain optical flow maps, which aims to expand the datasets and reduce the adverse impact of micro-expression spotting. Then, supervised contrastive learning is introduced to learn the key representation of micro-expressions for classification. The results on CASME II and SAMM datasets show that the approach is effective and competitive compared with the state-of-the-art methods both on three-classes and five-classes evalua-tions.(c) 2022 Elsevier B.V. All rights reserved.

Keywords:

Micro-expression recognition

Supervised contrastive learning

Motion magnification

Optical flow

Micro-expression recognition with supervised contrastive learning

Abstract

Journal

Organization