AU-aware graph convolutional network for Macro- and Micro-expression spotting
This work addresses the problem of micro-expression analysis for applications like psychology and security, but it is incremental as it builds on existing graph convolutional methods with added AU information.
The paper tackled the challenge of automatic micro-expression spotting in long videos by proposing an Action-Unit-aware Graph Convolutional Network (AUW-GCN) that models relationships between facial regions and incorporates AU-related statistics, achieving new state-of-the-art performance on benchmark datasets CAS(ME)^2 and SAMM-LV.
Automatic Micro-Expression (ME) spotting in long videos is a crucial step in ME analysis but also a challenging task due to the short duration and low intensity of MEs. When solving this problem, previous works generally lack in considering the structures of human faces and the correspondence between expressions and relevant facial muscles. To address this issue for better performance of ME spotting, this paper seeks to extract finer spatial features by modeling the relationships between facial Regions of Interest (ROIs). Specifically, we propose a graph convolutional-based network, called Action-Unit-aWare Graph Convolutional Network (AUW-GCN). Furthermore, to inject prior information and to cope with the problem of small datasets, AU-related statistics are encoded into the network. Comprehensive experiments show that our results outperform baseline methods consistently and achieve new SOTA performance in two benchmark datasets,CAS(ME)^2 and SAMM-LV. Our code is available at https://github.com/xjtupanda/AUW-GCN.