PriorNet: Prior-Guided Engagement Estimation from Face Video

TL;DR

PriorNet introduces a prior-guided framework for face video engagement estimation, effectively handling incomplete facial data and limited labels through explicit prior injection at multiple pipeline stages.

Contribution

It proposes a novel multi-stage prior-guided approach, including explicit handling of missing faces, efficient model adaptation, and uncertainty-aware training, improving performance across multiple datasets.

Findings

PriorNet outperforms previous methods on EngageNet, DAiSEE, DREAMS, and PAFE datasets.

Component ablations show that preprocessing, adaptation, and priors contribute complementarily.

Explicit prior injection is validated as a beneficial design principle for engagement estimation.

Abstract

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. PriorNet converts face-detection failures into explicit zero-frame placeholders so that missing-face events remain represented in the input sequence, adapts a frozen Self-supervised Video Facial Affect Perceiver (SVFAP) backbone through a Prior-guided Low-Rank Adaptation module (Prior-LoRA) for parameter-efficient specialization, and trains with a Dirichlet-evidential, uncertainty-weighted objective under hard-label supervision. We evaluate PriorNet on EngageNet, DAiSEE, DREAMS, and PAFE using each dataset's native evaluation protocol. Across these benchmarks, PriorNet improves over the strongest listed prior reference within each dataset's evaluation framing, while component ablations on EngageNet and DAiSEE indicate that the gains arise from complementary contributions of preprocessing, adaptation, and objective-level priors. These results support explicit prior injection as a useful design principle for face-video engagement estimation under the benchmark conditions studied in this work.