READ-Net: Clarifying Emotional Ambiguity via Adaptive Feature Recalibration for Audio-Visual Depression Detection
Authors:
- Chenglizhao ChenCCChenglizhao Chen
- Mengke SongMSMengke Song
Preprint
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.Keywords
All Related Versions
This publication has 25 references indexed in Scilit:
- LMVD: A large-scale multimodal vlog dataset for depression detection in the wildInformation Fusion, 2025
- Depressive semantic awareness from vlog facial and vocal streams via spatio-temporal transformerDigital Communications and Networks, 2024
- Additive Cross-Modal Attention Network (ACMA) for Depression Detection Based on Audio and Textual FeaturesIEEE Access, 2024
- Automatic Assessment of Depression From Speech via a Hierarchical Attention Transfer Network and Attention AutoencodersIEEE Journal of Selected Topics in Signal Processing, 2019
- Investigation of Speech Landmark Patterns for Depression DetectionIEEE Transactions on Affective Computing, 2019
- Integrating Deep and Shallow Models for Multi-Modal Depression Analysis—Hybrid ArchitecturesIEEE Transactions on Affective Computing, 2018
- Automated depression analysis using convolutional neural networks from speechJournal of Biomedical Informatics, 2018
- Automated Depression Diagnosis Based on Deep Networks to Encode Facial Appearance and DynamicsIEEE Transactions on Affective Computing, 2017
- Recognizing action units for facial expression analysisIEEE Transactions on Pattern Analysis and Machine Intelligence, 2001
- Issues and recommendations regarding use of the Beck Depression InventoryCognitive Therapy and Research, 1987