arXiv cs.AI· Bermet Burkanova, Yasaman Etesam, Payam Jome Yazdian, Trinity Evans, Chuxuan Zhang, Zoe Stanley, Paige Tutt\"os\'i, Angelica Lim·· 4 小时前AI 评分39
CoMPAS3D：面向交互式动作生成（双人萨尔萨舞）的数据集与基准
CoMPAS3D: A Dataset and Benchmark for Interactive Motion
AI 导读
研究者提出 CoMPAS3D 数据集与评测框架，以双人萨尔萨舞作为具身交互评测领域。数据集包含 18 名舞者 3 小时即兴双人舞动作捕捉，覆盖初学者到专业水平，含 2800 多个专家标注片段，并定义动作分类、水平估计和跟随者生成三项基准任务。将客观指标应用于 Duolando 和 InterGen，显示生成舞蹈与真实舞蹈差距巨大，微调后的视觉语言模型则与专家主观评判相关性较好。
正文 · 原文
Abstract:Socially interactive humanoids aim to interact with humans through their bodies, adapting in real time to a partner's movement, intent, and abilities. This requires models that understand both how bodies move and what their movements mean. Yet, existing evaluation frameworks for interactive motion generation do not assess whether generated reactive motions are valid or appropriate within a shared movement vocabulary. Existing frameworks rely on kinematic metrics such as FID and beat alignment that cannot capture this semantic property, while improvised interaction datasets lack fine-grained move annotations. Inspired by computational evaluations of games such as Go and Chess, we propose Salsa as an embodied interaction evaluation domain. Salsa is interactive, dyadic, and governed by a move vocabulary and community-validated judging criteria covering timing, musicality, technique, difficulty, partnering, and originality. We present CoMPAS3D, a motion capture dataset of improvised partner salsa dance and an evaluation framework covering kinematic quality, two objective metrics (move legibility and proficiency appropriateness), and six competition-based subjective dimensions. The dataset comprises 3 hours of improvisation by 18 dancers spanning beginner, intermediate, and professional skill levels, with over 2,800 expert-annotated segments covering move types, execution errors, and stylistic elements. We define three benchmark tasks: move classification, proficiency estimation, and follower generation. Fine-tuned vision-language models perform well on ground-truth sequences and correlate with subjective expert judgments, suggesting their promise as measurement tools. Applied to Duolando and InterGen, our objective metrics reveal a large gap between ground-truth and generated dances, corroborated by expert human evaluations across six judging dimensions.
| Comments: | this https URL Accepted at WACV 2027 |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2507.19684 [cs.LG] |
| (or arXiv:2507.19684v3 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2507.19684 arXiv-issued DOI via DataCite |
Submission history
From: Yasaman Etesam [view email]
[v1]
Fri, 25 Jul 2025 21:33:48 UTC (4,832 KB)
[v2]
Tue, 2 Jun 2026 17:45:14 UTC (6,768 KB)
[v3]
Thu, 5 Nov 2026 15:35:07 UTC (6,980 KB)
来源：arXiv cs.AI · arxiv.org