Aug 2026· arXiv.org· Vol abs/2608.24580· 0 citations· 38 references
Computer Science
TL;DR
This work proposes an interpretable computational model of social engagement inspired by psychological theories of mutual visual attention that combines state-of-the-art head orientation estimation with lightweight geometric reasoning, producing explanations that remain accessible to non-technical users.
Abstract
Understanding social interactions from non-verbal visual data is important for behavior analysis and activity monitoring. We propose an interpretable computational model of social engagement inspired by psychological theories of mutual visual attention. Rather than learning interaction patterns end-to-end, our framework explicitly models dyadic visual attention and aggregates these cues into interpretable measures of individual and group engagement. The resulting modular framework combines state-of-the-art head orientation estimation with lightweight geometric reasoning, producing explanations that remain accessible to non-technical users. We evaluate the proposed approach on a variety of data through quantitative experiments and demonstrate its practical usefulness with qualitative visualizations designed to support teachers, caregivers, and social workers in understanding group interaction dynamics.
A graph-based Mixture-of-Experts (MoE) framework that explicitly separates self and social influences to enable interpretable engagement modeling, which outperforms baselines by up to 64.1% while offering interpretable insights into engagement dynamics across language and gender groups.
Monisha Singh, A. Dhall· Proceedings of the 28th Inte...· 0 citations
Understanding human intentions in complex social interactions is essential for developing socially intelligent systems, yet remains challenging due to their subjective, context-dependent, and multi-interpretable nature. Existing approaches typically reduce intention estimation to single-label outcome based prediction t...
Arthur Mercier· Proceedings of the 28th Inte...· 0 citations
Joint attention (JA) is a core mechanism of social interaction, supporting coordination, knowledge transmission and early language development; deficits in JA are also a key early indicator of autism. While prior computer vision work often operationalizes JA as frame-based co-attention to a shared target, cognitive sci...
M. Dickerman, Michael Villamizar, Sabine Stoll et al.· Proceedings of the 28th Inte...· 0 citations
A self-supervised framework that learns visual representations of interaction dynamics directly from paired videos of two people interacting, suggesting that diverse behavioral markers of engagement share a common foundation in interaction dynamics, and that this foundation can be learned without engagement-specific su...
Naga Venkata Sai Raviteja Chappa, L. Yankowitz, Gokul M. Nair et al.· Proceedings of the 28th Inte...· 0 citations
We effortlessly extract behaviorally relevant information from dynamic visual input to understand the actions of others. Here, we compare behavioral judgments of action meaning against other models capturing semantic and visual features. We measured brain activity using fMRI while participants viewed 90 video clips dep...
Jane Han, Vassiki S. Chauhan, Rebecca Philip et al.· Nature Communications· 1 citation
Visual attention is highly sensitive to spatial cues provided by others, with eye-gaze direction playing a primary role in shaping how we orient attention within different environments. While gaze-mediated attentional orienting can often be considered automatic, as it reflects our spontaneous tendency to look where oth...
Mario Dalmaso, Anna Lorenzoni· Canadian journal of experime...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.