# EviDep: Uncertainty-Aware Multimodal Depression Estimation via Disentangled Evidential Learning

arXiv: https://arxiv.org/abs/2604.16579 · HTML: https://mlsanity.com/paper/2604.16579/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 51 references that are in the map.
- First posted on arXiv 17 Apr 2026.

## Builds on (most cited first, 9 of 9)

- [Deep Evidential Regression](https://mlsanity.com/paper/1910.02600/) (2019)
- [WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition](https://mlsanity.com/paper/2103.04098/) (2021)
- [Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning](https://mlsanity.com/paper/1702.08811/) (2017)
- [Trustworthy Multimodal Regression with Mixture of Normal-inverse Gamma Distributions](https://mlsanity.com/paper/2111.08456/) (2021)
- [Deep Learning for Depression Recognition with Audiovisual Cues: A Review](https://mlsanity.com/paper/2106.00610/) (2021)
- [U-Fair: Uncertainty-based Multimodal Multitask Learning for Fairer Depression Detection](https://mlsanity.com/paper/2501.09687/) (2025)
- [Two-stage Temporal Modelling Framework for Video-based Depression Recognition using Graph Representation](https://mlsanity.com/paper/2111.15266/) (2021)
- [A multimodal dynamical variational autoencoder for audiovisual speech representation learning](https://mlsanity.com/paper/2305.03582/) (2023)
- [Fair Uncertainty Quantification for Depression Prediction](https://mlsanity.com/paper/2505.04931/) (2025)

## Abstract (arXiv)

Audio--visual recordings provide complementary cues for estimating depression severity, but their informativeness varies across time and modalities. Point predictions alone do not express the uncertainty associated with these estimates. We present EviDep, a multimodal evidential regression framework that integrates multi-scale temporal modeling and shared--private representation learning for uncertainty-aware depression estimation. Frequency-aware Feature Extraction decomposes behavioral feature sequences into multiple frequency bands and refines them with scale-specific experts. Disentangled Evidential Learning encourages the disentanglement of cross-modal shared and modality-specific information in the refined features. Multi-branch Evidential Regression maps the resulting shared and private representations to three Normal-Inverse-Gamma (NIG) outputs and uses evidence-weighted aggregation to estimate depression severity and quantify aleatoric and epistemic uncertainty. Experiments on AVEC 2013, AVEC 2014, DAIC-WOZ, and E-DAIC show competitive prediction accuracy, with ablation studies supporting the contributions of frequency-aware refinement and shared--private disentanglement. Further analyses show that estimated epistemic uncertainty helps identify higher-error predictions, while both uncertainty estimates generally increase under controlled feature degradation.