Modeling Multimodal Depression Diagnosis From the Perspective of Local Depressive Representation
- 24 October 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Affective Computing
- Vol. 17 (1) , 497-510
Abstract
Depression recognition is critical for early detection and treatment. Existing works focus on modeling coarse-grained multimodal representation to estimate the depression level. However, these approaches often overlook the inherent locality of depressive representation, resulting in weak and sparse depressive frames being overlooked. In addition, they neglect the inter modal correlations and intra-modal patterns of mood change, limiting the learning of multimodal complementary information. Therefore, we present a Locality-Aware Multimodal Depression (LAMD) recognition model. Specifically, LAMD contains three innovations: 1) Considering the sparsity of depressive features, we propose an Adaptive Temporal Attention (ATA) module to adaptively highlight keyframes with depressive features and suppress irrelevant frames. Additionally, we introduce Segment Information Sharing (SIS) strategy to overcome the limitation of inter-segment independence, enabling global awareness of depressive features within the whole segment. 2) We revisit the audio-video multimodal interaction from the perspectives of inter-modal correlation and intra-modal smoothness, introducing frame-level multimodal attention consistency constraints and smooth constraints. Furthermore, we propose a local cross attention to enhance the inter-modal interactions in adjacent time. 3) Extensive experiments on several datasets demonstrate that LAMD achieves superior performance, with up to 7.21 RMSE and 76.77% F1-score on the AVEC2014 and NJAD dataset, outperforming the prior art by a notable 0.22% and 1.88% margin, respectively. Moreover, visual analysis reveals that LAMD can adaptively perceive depressive keyframes and focus on fine-grained facial regions known for capturing subtle depressive expressions.Keywords
Funding Information
- Science and Technology Joint Project of Liaoning province (2023JH2/101700367)
- Fundamental Research Funds for the Central Universities (N25BJD005)
- National Natural Science Foundation of China (62076059)
This publication has 50 references indexed in Scilit:
- Attention-driven contextual feature fusion network for facial videos-based depression recognitionBiomedical Signal Processing and Control, 2025
- A novel multimodal depression diagnosis approach utilizing a new hybrid fusion methodBiomedical Signal Processing and Control, 2024
- Depressive semantic awareness from vlog facial and vocal streams via spatio-temporal transformerDigital Communications and Networks, 2024
- Reading Between the Frames: Multi-modal Depression Detection in Videos from Non-verbal Cues2024
- Multi-feature deep supervised voiceprint adversarial network for depression recognition from speechBiomedical Signal Processing and Control, 2023
- A novel Image-Data-Driven and Frequency-Based method for depression detectionBiomedical Signal Processing and Control, 2023
- Multi-modal Depression Estimation Based on Sub-attentional Fusion2023
- Towards Robust Deep Neural Networks for Affect and Depression Recognition from Speech2021
- Automated audiovisual depression analysisCurrent Opinion in Psychology, 2015
- OpenDLib: A Digital Library Service SystemLecture Notes in Computer Science, 2002