Saved in:
Bibliographic Details
Main Authors: Xu, Yi, Fu, Yun
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.16095
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916958209835008
author Xu, Yi
Fu, Yun
author_facet Xu, Yi
Fu, Yun
contents Trajectory prediction in multi-agent sports scenarios is inherently challenging due to the structural heterogeneity across agent roles (e.g., players vs. ball) and dynamic distribution gaps across different sports domains. Existing unified frameworks often fail to capture these structured distributional shifts, resulting in suboptimal generalization across roles and domains. We propose AdaSports-Traj, an adaptive trajectory modeling framework that explicitly addresses both intra-domain and inter-domain distribution discrepancies in sports. At its core, AdaSports-Traj incorporates a Role- and Domain-Aware Adapter to conditionally adjust latent representations based on agent identity and domain context. Additionally, we introduce a Hierarchical Contrastive Learning objective, which separately supervises role-sensitive and domain-aware representations to encourage disentangled latent structures without introducing optimization conflict. Experiments on three diverse sports datasets, Basketball-U, Football-U, and Soccer-U, demonstrate the effectiveness of our adaptive design, achieving strong performance in both unified and cross-domain trajectory prediction settings.
format Preprint
id arxiv_https___arxiv_org_abs_2509_16095
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AdaSports-Traj: Role- and Domain-Aware Adaptation for Multi-Agent Trajectory Modeling in Sports
Xu, Yi
Fu, Yun
Computer Vision and Pattern Recognition
Trajectory prediction in multi-agent sports scenarios is inherently challenging due to the structural heterogeneity across agent roles (e.g., players vs. ball) and dynamic distribution gaps across different sports domains. Existing unified frameworks often fail to capture these structured distributional shifts, resulting in suboptimal generalization across roles and domains. We propose AdaSports-Traj, an adaptive trajectory modeling framework that explicitly addresses both intra-domain and inter-domain distribution discrepancies in sports. At its core, AdaSports-Traj incorporates a Role- and Domain-Aware Adapter to conditionally adjust latent representations based on agent identity and domain context. Additionally, we introduce a Hierarchical Contrastive Learning objective, which separately supervises role-sensitive and domain-aware representations to encourage disentangled latent structures without introducing optimization conflict. Experiments on three diverse sports datasets, Basketball-U, Football-U, and Soccer-U, demonstrate the effectiveness of our adaptive design, achieving strong performance in both unified and cross-domain trajectory prediction settings.
title AdaSports-Traj: Role- and Domain-Aware Adaptation for Multi-Agent Trajectory Modeling in Sports
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.16095