Generalizable Engagement Estimation in Conversation via Domain Prompting and Parallel Attention

TL;DR

This paper introduces DAPA, a novel framework for conversational engagement estimation that improves cross-domain generalization by using domain prompting and parallel attention mechanisms, achieving state-of-the-art results.

Contribution

The paper proposes DAPA, combining domain prompting and parallel attention to enhance generalizability in engagement estimation across diverse domains.

Findings

Achieved a 0.45 increase in CCC over baseline on NoXi-J.

Set new state-of-the-art on multiple cross-cultural benchmarks.

Won first place in the Multi-Domain Engagement Estimation Challenge.

Abstract

Accurate engagement estimation is essential for adaptive human-computer interaction systems, yet robust deployment is hindered by poor generalizability across diverse domains and challenges in modeling complex interaction dynamics.To tackle these issues, we propose DAPA (Domain-Adaptive Parallel Attention), a novel framework for generalizable conversational engagement modeling. DAPA introduces a Domain Prompting mechanism by prepending learnable domain-specific vectors to the input, explicitly conditioning the model on the data's origin to facilitate domain-aware adaptation while preserving generalizable engagement representations. To capture interactional synchrony, the framework also incorporates a Parallel Cross-Attention module that explicitly aligns reactive (forward BiLSTM) and anticipatory (backward BiLSTM) states between participants.Extensive experiments demonstrate that DAPA establishes a new state-of-the-art performance on several cross-cultural and cross-linguistic benchmarks, notably achieving an absolute improvement of 0.45 in Concordance Correlation Coefficient (CCC) over a strong baseline on the NoXi-J test set. The superiority of our method was also confirmed by winning the first place in the Multi-Domain Engagement Estimation Challenge at MultiMediate'25.