Authentic Emotion Mapping: Benchmarking Facial Expressions in Real News

TL;DR

This paper introduces a new benchmark for emotion recognition from facial landmarks in realistic news videos, utilizing Graph Neural Networks to improve accuracy and efficiency over traditional RGB-based methods.

Contribution

It presents a novel dataset and benchmark for facial landmark-based emotion recognition using GNNs, offering a resource for future research in realistic settings.

Findings

GNN-based approach improves emotion recognition accuracy

Facial landmark analysis reduces resource requirements

Benchmark dataset demonstrates viability for real-world applications

Abstract

In this paper, we present a novel benchmark for Emotion Recognition using facial landmarks extracted from realistic news videos. Traditional methods relying on RGB images are resource-intensive, whereas our approach with Facial Landmark Emotion Recognition (FLER) offers a simplified yet effective alternative. By leveraging Graph Neural Networks (GNNs) to analyze the geometric and spatial relationships of facial landmarks, our method enhances the understanding and accuracy of emotion recognition. We discuss the advancements and challenges in deep learning techniques for emotion recognition, particularly focusing on Graph Neural Networks (GNNs) and Transformers. Our experimental results demonstrate the viability and potential of our dataset as a benchmark, setting a new direction for future research in emotion recognition technologies. The codes and models are at: https://github.com/wangzhifengharrison/benchmark_real_news