READ-Net: Clarifying Emotional Ambiguity via Adaptive Feature Recalibration for Audio-Visual Depression Detection

2026-01-21

AI Summary

Existing audiovisual depression detection methods often conflate transient emotional states with stable depressive symptoms, leading to affective ambiguity and reduced accuracy. To address this issue, this work proposes READ-Net, a novel framework that explicitly targets affective ambiguity through an Adaptive Feature Recalibration (AFR) mechanism. AFR dynamically adjusts the weights of multimodal affective features, preserving depression-relevant cues while suppressing irrelevant emotional interference. The proposed module is designed to be flexibly integrated into existing architectures and demonstrates consistent performance gains across three public datasets, achieving an average improvement of 4.55% in accuracy and 1.26% in F1 score over state-of-the-art methods. These results underscore the robustness and effectiveness of READ-Net in mitigating emotion-induced confounds in depression detection.

Technology Category

• Cognitive Modeling & Cognitive Systems: Affective Computing
• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning

Application Category

• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Depression is a severe global mental health issue that impairs daily functioning and overall quality of life. Although recent audio-visual approaches have improved automatic depression detection, methods that ignore emotional cues often fail to capture subtle depressive signals hidden within emotional expressions. Conversely, those incorporating emotions frequently confuse transient emotional expressions with stable depressive symptoms in feature representations, a phenomenon termed \emph{Emotional Ambiguity}, thereby leading to detection errors. To address this critical issue, we propose READ-Net, the first audio-visual depression detection framework explicitly designed to resolve Emotional Ambiguity through Adaptive Feature Recalibration (AFR). The core insight of AFR is to dynamically adjust the weights of emotional features to enhance depression-related signals. Rather than merely overlooking or naively combining emotional information, READ-Net innovatively identifies and preserves depressive-relevant cues within emotional features, while adaptively filtering out irrelevant emotional noise. This recalibration strategy significantly clarifies feature representations, and effectively mitigates the persistent challenge of emotional interference. Additionally, READ-Net can be easily integrated into existing frameworks for improved performance. Extensive evaluations on three publicly available datasets show that READ-Net outperforms state-of-the-art methods, with average gains of 4.55\% in accuracy and 1.26\% in F1-score, demonstrating its robustness to emotional disturbances and improving audio-visual depression detection.

Problem

• Emotional Ambiguity
• Depression Detection
• Audio-Visual Analysis
• Feature Representation
• Emotional Interference

Innovation

• Emotional Ambiguity
• Adaptive Feature Recalibration
• Audio-Visual Depression Detection
• Feature Recalibration
• Depression-Related Cues