# Vision Large Language Models Are Good Noise Handlers in Engagement Analysis

arXiv: https://arxiv.org/abs/2511.14749 · HTML: https://mlsanity.com/paper/2511.14749/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Nov 2025.

## Built on by (most cited first, 2 of 2)

- [PriorNet: Prior-Guided Engagement Estimation from Face Video](https://mlsanity.com/paper/2605.03615/) (2026)
- [Not Every Subject Should Stay: Machine Unlearning for Noisy Engagement Recognition](https://mlsanity.com/paper/2605.04713/) (2026)

## Abstract (arXiv)

Engagement recognition in video datasets, unlike traditional image classification tasks, is particularly challenged by subjective labels and noise limiting model performance. To overcome the challenges of subjective and noisy engagement labels, we propose a framework leveraging Vision Large Language Models (VLMs) to refine annotations and guide the training process. Our framework uses a questionnaire to extract behavioral cues and split data into high- and low-reliability subsets. We also introduce a training strategy combining curriculum learning with soft label refinement, gradually incorporating ambiguous samples while adjusting supervision to reflect uncertainty. We demonstrate that classical computer vision models trained on refined high-reliability subsets and enhanced with our curriculum strategy show improvements, highlighting benefits of addressing label subjectivity with VLMs. This method surpasses prior state of the art across engagement benchmarks such as EngageNet (three of six feature settings, maximum improvement of +1.21%), and DREAMS / PAFE with F1 gains of +0.22 / +0.06.