AI RESEARCH
PriorNet: Prior-Guided Engagement Estimation from Face Video
arXiv CS.CV
•
ArXi:2605.03615v1 Announce Type: new Engagement estimation from face video remains challenging because facial evidence is often incomplete, labeled data are limited, and engagement annotations are subjective. We present PriorNet, a prior-guided framework that injects task-relevant priors at three stages of the pipeline: preprocessing, model adaptation, and objective design.