SocialGen: Modeling Multi-Human Social Interaction with Language Models

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Yu, Heng, Zhang, Juze, Chen, Changan, Xiang, Tiange, Fang, Yusu, Niebles, Juan Carlos, Adeli, Ehsan
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909557399224320
author Yu, Heng
Zhang, Juze
Chen, Changan
Xiang, Tiange
Fang, Yusu
Niebles, Juan Carlos
Adeli, Ehsan
author_facet Yu, Heng
Zhang, Juze
Chen, Changan
Xiang, Tiange
Fang, Yusu
Niebles, Juan Carlos
Adeli, Ehsan
contents Human interactions in everyday life are inherently social, involving engagements with diverse individuals across various contexts. Modeling these social interactions is fundamental to a wide range of real-world applications. In this paper, we introduce SocialGen, the first unified motion-language model capable of modeling interaction behaviors among varying numbers of individuals, to address this crucial yet challenging problem. Unlike prior methods that are limited to two-person interactions, we propose a novel social motion representation that supports tokenizing the motions of an arbitrary number of individuals and aligning them with the language space. This alignment enables the model to leverage rich, pretrained linguistic knowledge to better understand and reason about human social behaviors. To tackle the challenges of data scarcity, we curate a comprehensive multi-human interaction dataset, SocialX, enriched with textual annotations. Leveraging this dataset, we establish the first comprehensive benchmark for multi-human interaction tasks. Our method achieves state-of-the-art performance across motion-language tasks, setting a new standard for multi-human interaction modeling.
format Preprint
id arxiv_https___arxiv_org_abs_2503_22906
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SocialGen: Modeling Multi-Human Social Interaction with Language Models
Yu, Heng
Zhang, Juze
Chen, Changan
Xiang, Tiange
Fang, Yusu
Niebles, Juan Carlos
Adeli, Ehsan
Computer Vision and Pattern Recognition
Human interactions in everyday life are inherently social, involving engagements with diverse individuals across various contexts. Modeling these social interactions is fundamental to a wide range of real-world applications. In this paper, we introduce SocialGen, the first unified motion-language model capable of modeling interaction behaviors among varying numbers of individuals, to address this crucial yet challenging problem. Unlike prior methods that are limited to two-person interactions, we propose a novel social motion representation that supports tokenizing the motions of an arbitrary number of individuals and aligning them with the language space. This alignment enables the model to leverage rich, pretrained linguistic knowledge to better understand and reason about human social behaviors. To tackle the challenges of data scarcity, we curate a comprehensive multi-human interaction dataset, SocialX, enriched with textual annotations. Leveraging this dataset, we establish the first comprehensive benchmark for multi-human interaction tasks. Our method achieves state-of-the-art performance across motion-language tasks, setting a new standard for multi-human interaction modeling.
title SocialGen: Modeling Multi-Human Social Interaction with Language Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.22906