OUS: Scene-Guided Dynamic Facial Expression Recognition

TL;DR

This paper introduces OUS, a novel method for dynamic facial expression recognition that incorporates scene context to better align with human emotional understanding, significantly improving performance on major datasets.

Contribution

The paper proposes OUS, a scene-guided approach that effectively integrates scene and facial features for more accurate emotion recognition, addressing a key gap in existing methods.

Findings

OUS outperforms existing methods on DFEW and FERV39k datasets.

Incorporating scene context improves emotion recognition accuracy.

Analysis of the Rigid Cognitive Problem enhances understanding of scene-emotion relationships.

Abstract

Dynamic Facial Expression Recognition (DFER) is crucial for affective computing but often overlooks the impact of scene context. We have identified a significant issue in current DFER tasks: human annotators typically integrate emotions from various angles, including environmental cues and body language, whereas existing DFER methods tend to consider the scene as noise that needs to be filtered out, focusing solely on facial information. We refer to this as the Rigid Cognitive Problem. The Rigid Cognitive Problem can lead to discrepancies between the cognition of annotators and models in some samples. To align more closely with the human cognitive paradigm of emotions, we propose an Overall Understanding of the Scene DFER method (OUS). OUS effectively integrates scene and facial features, combining scene-specific emotional knowledge for DFER. Extensive experiments on the two largest datasets in the DFER field, DFEW and FERV39k, demonstrate that OUS significantly outperforms existing methods. By analyzing the Rigid Cognitive Problem, OUS successfully understands the complex relationship between scene context and emotional expression, closely aligning with human emotional understanding in real-world scenarios.