{"slug": "uncovering-latent-depression-severity-for-binary-depression-detection-via", "title": "Uncovering Latent Depression Severity for Binary Depression Detection via Advantage-weighting Ranking", "summary": "Researchers proposed a fine-grained multimodal framework for automatic depression detection using audio-visual data, featuring a Binary Advantage-weighting Ranking Loss that optimizes latent space distribution through hard pair mining and intra-class variance minimization. The model achieved state-of-the-art performance on the D-vlog and LMVD datasets.", "body_md": "arXiv:2607.05901v1 Announce Type: new\nAbstract: Automatic depression detection using audio-visual data faces significant challenges, particularly in disentangling overlapping feature distributions and establishing robust decision boundaries. To address this, we propose a fine-grained multimodal framework featuring a temporal encoder and a mutual transformer to facilitate deep cross-modal fusion. Our core contribution is the Binary Advantage-weighting Ranking Loss, which optimizes the latent space distribution through two complementary mechanisms: Advantage-weighted Separation, which mines hard pairs by computing a pairwise prediction difference matrix and dynamically weighting them based on their difficulty; and Advantage-weighted Compactness, which minimizes intra-class variance to force features to cluster around their respective class centers. Extensive experiments on D-vlog and LMVD demonstrate that our model reconstructs the latent ordinal structure by prioritizing hard pairs, thereby achieving state-of-the-art performance.", "url": "https://wpnews.pro/news/uncovering-latent-depression-severity-for-binary-depression-detection-via", "canonical_source": "https://arxiv.org/abs/2607.05901", "published_at": "2026-07-08 04:00:00+00:00", "updated_at": "2026-07-08 04:05:42.938097+00:00", "lang": "en", "topics": ["machine-learning", "computer-vision", "natural-language-processing"], "entities": ["D-vlog", "LMVD"], "alternates": {"html": "https://wpnews.pro/news/uncovering-latent-depression-severity-for-binary-depression-detection-via", "markdown": "https://wpnews.pro/news/uncovering-latent-depression-severity-for-binary-depression-detection-via.md", "text": "https://wpnews.pro/news/uncovering-latent-depression-severity-for-binary-depression-detection-via.txt", "jsonld": "https://wpnews.pro/news/uncovering-latent-depression-severity-for-binary-depression-detection-via.jsonld"}}