{"slug": "affectflow-dino-uncertainty-aware-multi-task-affect-estimation-via-conditional", "title": "AffectFlow-DINO: Uncertainty-Aware Multi-Task Affect Estimation via Conditional Rectified Flow", "summary": "Researchers introduced AffectFlow-DINO, a multi-task learning system for the 11th ABAW challenge that uses conditional rectified flow to model uncertainty in facial affect estimation. The system jointly estimates valence-arousal, classifies facial expressions, and detects action units, achieving a multi-task learning score of 1.177, significantly outperforming the official baseline of 0.45.", "body_md": "arXiv:2607.13250v1 Announce Type: new\nAbstract: We present \\textbf{AffectFlow-DINO}, a multi-task learning system for the 11th ABAW challenge that extends a standard deterministic architecture with a conditional rectified-flow head to model the inherent ambiguity of in-the-wild facial behavior. Instead of predicting a single affect estimate, the model learns a conditional generative distribution, enabling uncertainty-aware one-to-many predictions through Monte Carlo sampling. The system jointly estimates continuous valence-arousal, classifies eight facial expressions, and detects twelve Action Units from static face images. Built on a frozen DINOv3 ViT-S/16 backbone, extensive ablation studies show that rectified-flow decoding consistently improves deterministic prediction, particularly for valence-arousal estimation (CCC-V $+0.058$). We further show that post-hoc threshold calibration effectively recovers performance on severely imbalanced rare classes (e.g., Fear: $3.8\\% \\rightarrow 33.1\\%$) without retraining. Combined with backbone fine-tuning and flow retuning, the final model achieves $\\mathbf{P_{MTL}=1.177}$, substantially outperforming the official challenge baseline of $P_{MTL}=0.45$.", "url": "https://wpnews.pro/news/affectflow-dino-uncertainty-aware-multi-task-affect-estimation-via-conditional", "canonical_source": "https://arxiv.org/abs/2607.13250", "published_at": "2026-07-16 04:00:00+00:00", "updated_at": "2026-07-16 04:10:05.080407+00:00", "lang": "en", "topics": ["artificial-intelligence", "computer-vision", "machine-learning", "ai-research"], "entities": ["AffectFlow-DINO", "ABAW", "DINOv3", "ViT-S/16"], "alternates": {"html": "https://wpnews.pro/news/affectflow-dino-uncertainty-aware-multi-task-affect-estimation-via-conditional", "markdown": "https://wpnews.pro/news/affectflow-dino-uncertainty-aware-multi-task-affect-estimation-via-conditional.md", "text": "https://wpnews.pro/news/affectflow-dino-uncertainty-aware-multi-task-affect-estimation-via-conditional.txt", "jsonld": "https://wpnews.pro/news/affectflow-dino-uncertainty-aware-multi-task-affect-estimation-via-conditional.jsonld"}}