Spotting Macro- and Micro-expression Intervals in Long Video Sequences

TL;DR

This paper introduces baseline results for spotting macro- and micro-expressions in long videos using the MDMD method, providing a starting point for future research in facial expression analysis.

Contribution

It presents a novel application of the MDMD method for interval spotting of facial expressions in long videos, with publicly available code for benchmarking.

Findings

F1-score of 0.1196 for macro-expressions in CAS(ME)$^2$

F1-score of 0.0364 for micro-expressions in SAMM Long Videos

Baseline results establish a reference for future improvements.

Abstract

This paper presents baseline results for the Third Facial Micro-Expression Grand Challenge (MEGC 2020). Both macro- and micro-expression intervals in CAS(ME)$^2$ and SAMM Long Videos are spotted by employing the method of Main Directional Maximal Difference Analysis (MDMD). The MDMD method uses the magnitude maximal difference in the main direction of optical flow features to spot facial movements. The single-frame prediction results of the original MDMD method are post-processed into reasonable video intervals. The metric F1-scores of baseline results are evaluated: for CAS(ME)$^2$, the F1-scores are 0.1196 and 0.0082 for macro- and micro-expressions respectively, and the overall F1-score is 0.0376; for SAMM Long Videos, the F1-scores are 0.0629 and 0.0364 for macro- and micro-expressions respectively, and the overall F1-score is 0.0445. The baseline project codes are publicly available at https://github.com/HeyingGithub/Baseline-project-for-MEGC2020_spotting.