Saved in:
Bibliographic Details
Main Authors: Yu, Yangche, Chen, Yin, Li, Jia, Jia, Peng, Zhang, Yu, Dai, Li, Hu, Zhenzhen, Wang, Meng, Hong, Richang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.14448
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915452514467840
author Yu, Yangche
Chen, Yin
Li, Jia
Jia, Peng
Zhang, Yu
Dai, Li
Hu, Zhenzhen
Wang, Meng
Hong, Richang
author_facet Yu, Yangche
Chen, Yin
Li, Jia
Jia, Peng
Zhang, Yu
Dai, Li
Hu, Zhenzhen
Wang, Meng
Hong, Richang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_14448
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generalizable Engagement Estimation in Conversation via Domain Prompting and Parallel Attention
Yu, Yangche
Chen, Yin
Li, Jia
Jia, Peng
Zhang, Yu
Dai, Li
Hu, Zhenzhen
Wang, Meng
Hong, Richang
Computer Vision and Pattern Recognition
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.
title Generalizable Engagement Estimation in Conversation via Domain Prompting and Parallel Attention
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.14448