Modeling Multimodal Social Interactions: New Challenges and Baselines with Densely Aligned Representations

arXiv:2403.02090v1 Announce Type: cross
Abstract: Understanding social interactions involving both verbal and non-verbal cues is essential to effectively interpret social situations. However, most prior works on multimodal social cues focus predominantly on single-person behaviors or rely on holistic visual representations that are not densely aligned to utterances in multi-party environments. They are limited in modeling the intricate dynamics of multi-party interactions. In this paper, we introduce three new challenging tasks to model the fine-grained dynamics between multiple people: speaking target …

abstract arxiv challenges cs.cl cs.cv cs.lg focus interactions modeling multimodal person prior social type understanding verbal visual