{"ID":2864057,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.23535","arxiv_id":"2509.23535","title":"Calibrated and Resource-Aware Super-Resolution for Reliable Driver Behavior Analysis","abstract":"Driver monitoring systems require not just high accuracy but reliable, well-calibrated confidence scores for safety-critical deployment. While direct low-resolution training yields high overall accuracy, it produces poorly calibrated predictions that can be dangerous in safety-critical scenarios. We propose a resource-aware adaptive super-resolution framework that optimizes for model calibration and high precision-recall on critical events. Our approach achieves state-of-the-art performance on safety-centric metrics: best calibration (ECE of 5.8\\% vs 6.2\\% for LR-trained baselines), highest AUPR for drowsiness detection (0.78 vs 0.74), and superior precision-recall for phone use detection (0.74 vs 0.71). A lightweight artifact detector (0.3M parameters, 5.2ms overhead) provides additional safety by filtering SR-induced hallucinations. While LR-trained video models serve as strong general-purpose baselines, our adaptive framework represents the state-of-the-art solution for safety-critical applications where reliability is paramount.","short_abstract":"Driver monitoring systems require not just high accuracy but reliable, well-calibrated confidence scores for safety-critical deployment. While direct low-resolution training yields high overall accuracy, it produces poorly calibrated predictions that can be dangerous in safety-critical scenarios. We propose a resource-...","url_abs":"https://arxiv.org/abs/2509.23535","url_pdf":"https://arxiv.org/pdf/2509.23535v1","authors":"[\"Ibne Farabi Shihab\",\"Weiheng Chai\",\"Jiyang Wang\",\"Sanjeda Akter\",\"Senem Velipasalar Gursoy\",\"Anuj Sharma\"]","published":"2025-09-28T00:08:44Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}