arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.11064cs.LG
收藏

动作捕捉并非目标领域:通过合成数据扩大学习动作表示

Motion Capture is Not the Target Domain: Scaling Synthetic Data for Learning Motion Representations

Department of Statistics University of Oxford(统计系牛津大学);Big Data Institute University of Oxford(大数据研究所牛津大学);Nuffield Department of Population Health Big Data Institute University of Oxford(人口健康系大数据研究所牛津大学)

Firas Darwish, George Nicholson, Aiden Doherty, Hang Yuan

AI总结:

本文研究了通过合成数据预训练动作表示在真实场景中的迁移效果,发现混合真实数据或足够规模时能提升泛化能力,但大规模动作捕捉预训练因领域不匹配效果有限。

摘要:

合成数据为在现实数据稀缺时实现可扩展预训练提供了一个有吸引力的途径,但预先在合成数据上训练的模型往往无法可靠地转移到部署环境。我们研究了全身体态动作的这一问题,其中大规模数据收集不可行但对基于穿戴设备的人活动识别(HAR)至关重要,而合成动作可以从动作捕捉导出的表示中生成。我们使用此类合成数据预训练动作时间序列模型,并评估其在多种下游HAR任务中的迁移能力。我们的结果表明,当与真实数据混合或足够大规模时,合成预训练可以提高泛化能力。我们还证明了大规模动作捕捉预训练由于与可穿戴信号的领域不匹配,只能带来微小的收益,从而阐明了关键的仿真到现实挑战以及合成动作数据在可迁移HAR表示中的限制和机遇。

英文摘要:

Synthetic data offers a compelling path to scalable pretraining when real-world data is scarce, but models pretrained on synthetic data often fail to transfer reliably to deployment settings. We study this problem in full-body human motion, where large-scale data collection is infeasible but essential for wearable-based Human Activity Recognition (HAR), and where synthetic motion can be generated from motion-capture-derived representations. We pretrain motion time-series models using such synthetic data and evaluate their transfer across diverse downstream HAR tasks. Our results show that synthetic pretraining improves generalisation when mixed with real data or scaled sufficiently. We also demonstrate that large-scale motion-capture pretraining yields only marginal gains due to domain mismatch with wearable signals, clarifying key sim-to-real challenges and the limits and opportunities of synthetic motion data for transferable HAR representations.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑