PT Journal
AU Wenjuan Gong
   Zhang Yue
   Wei Wang
   Cheng Peng
   Jordi Gonzalez
TI Meta-MMFNet: Meta-Learning Based Multi-Model Fusion Network for Micro-Expression Recognition
SO ACM Transactions on Multimedia Computing, Communications, and Applications
JI ACMTMC
PY 2022
DI 10.1145/3539576
DE Feature Fusion; Model Fusion; Meta-Learning; Micro-Expression Recognition
AB Despite its wide applications in criminal investigations and clinical communications with patients suffering from autism, automatic micro-expression recognition remains a challenging problem because of the lack of training data and imbalanced classes problems. In this study, we proposed a meta-learning based multi-model fusion network (Meta-MMFNet) to solve the existing problems. The proposed method is based on the metric-based meta-learning pipeline, which is specifically designed for few-shot learning and is suitable for model-level fusion. The frame difference and optical flow features were fused, deep features were extracted from the fused feature, and finally in the meta-learning-based framework, weighted sum model fusion method was applied for micro-expression classification. Meta-MMFNet achieved better results than state-of-the-art methods on four datasets. The code is available at https://github.com/wenjgong/meta-fusion-based-method.
ER