Enregistré dans:
Détails bibliographiques
Auteurs principaux: Soga, Masato, Takebayashi, Ryuki
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2604.22164
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915953257742336
author Soga, Masato
Takebayashi, Ryuki
author_facet Soga, Masato
Takebayashi, Ryuki
contents Recent advances in deep learning have enabled the generation of videos from textual descriptions as well as the prediction of future sequences from input videos. Similarly, in human motion modeling, motions can be generated from text or predicted from a single person's motion sequence. However, these approaches primarily focus on single-agent motion generation. In contrast, this study addresses the problem of generating the motion of one person based on the motion of another in interaction scenarios, where the two motions are mutually dependent. We construct a dataset of paired action-reaction motion sequences extracted from boxing match videos and investigate the effectiveness of Transformer-based models for this task. Specifically, we implement and compare three models: a simple Transformer, iTransformer, and Crossformer. In addition, we introduce a person ID embedding to explicitly distinguish between individuals, enabling the model to maintain structural consistency and better capture interaction dynamics. Experimental results show that the simple Transformer can generate plausible interaction-aware motions without suffering from posture collapse, while iTransformer and Crossformer accumulate errors over time, leading to unstable motion generation. Furthermore, the proposed person ID embedding contributes to preventing structural collapse and improving motion consistency. These results highlight the importance of explicitly modeling individual identity in interaction-aware motion generation.
format Preprint
id arxiv_https___arxiv_org_abs_2604_22164
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Learning Reactive Human Motion Generation from Paired Interaction Data Using Transformer-Based Models
Soga, Masato
Takebayashi, Ryuki
Computer Vision and Pattern Recognition
Recent advances in deep learning have enabled the generation of videos from textual descriptions as well as the prediction of future sequences from input videos. Similarly, in human motion modeling, motions can be generated from text or predicted from a single person's motion sequence. However, these approaches primarily focus on single-agent motion generation. In contrast, this study addresses the problem of generating the motion of one person based on the motion of another in interaction scenarios, where the two motions are mutually dependent. We construct a dataset of paired action-reaction motion sequences extracted from boxing match videos and investigate the effectiveness of Transformer-based models for this task. Specifically, we implement and compare three models: a simple Transformer, iTransformer, and Crossformer. In addition, we introduce a person ID embedding to explicitly distinguish between individuals, enabling the model to maintain structural consistency and better capture interaction dynamics. Experimental results show that the simple Transformer can generate plausible interaction-aware motions without suffering from posture collapse, while iTransformer and Crossformer accumulate errors over time, leading to unstable motion generation. Furthermore, the proposed person ID embedding contributes to preventing structural collapse and improving motion consistency. These results highlight the importance of explicitly modeling individual identity in interaction-aware motion generation.
title Learning Reactive Human Motion Generation from Paired Interaction Data Using Transformer-Based Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.22164