Spotting Macro- and Micro-expression Intervals in Long Video Sequences
This work provides baseline results for the MEGC 2020 challenge, addressing the need for automated facial expression analysis in video data, but it is incremental as it applies an existing method to new datasets.
This paper tackled the problem of spotting macro- and micro-expression intervals in long video sequences using the Main Directional Maximal Difference Analysis (MDMD) method, achieving F1-scores such as 0.1196 for macro-expressions and 0.0082 for micro-expressions on CAS(ME)^2, and 0.0629 and 0.0364 respectively on SAMM Long Videos.
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.