解决人体动作预测中长期依赖导致短期预测变差的问题
Temporal Continual Learning with Prior Compensation for Human Motion Prediction
- 分阶段训练，用先验补偿因子保留历史信息
- 在四个数据集上显著提升短期与长期预测精度
- 可适配多种模型和任务，适合动作预测研究者
人体动作预测（HMP）旨在根据历史运动序列预测未来不同时刻的姿态。现有方法通常同等对待各时刻的预测，导致短期预测受长期预测目标制约，且难以有效利用先前预测的先验信息。本文提出一种新型多阶段训练框架——时间持续学习（TCL），通过引入先验补偿因子（PCF）来恢复训练中丢失的先验信息，并基于理论推导获得更合理的优化目标。该框架可轻松集成到不同HMP主干模型中，适用于多种数据集与应用场景。在四个标准HMP基准数据集上的大量实验验证了TCL的有效性与灵活性。代码已开源：https://github.com/hyqlat/TCL。
原文摘要 · Abstract (English)
Human Motion Prediction (HMP) aims to predict future poses at different moments according to past motion sequences. Previous approaches have treated the prediction of various moments equally, resulting in two main limitations: the learning of short-term predictions is hindered by the focus on long-term predictions, and the incorporation of prior information from past predictions into subsequent predictions is limited. In this paper, we introduce a novel multi-stage training framework called Temporal Continual Learning (TCL) to address the above challenges. To better preserve prior information, we introduce the Prior Compensation Factor (PCF). We incorporate it into the model training to compensate for the lost prior information. Furthermore, we derive a more reasonable optimization objective through theoretical derivation. It is important to note that our TCL framework can be easily integrated with different HMP backbone models and adapted to various datasets and applications. Extensive experiments on four HMP benchmark datasets demonstrate the effectiveness and flexibility of TCL. The code is available at https://github.com/hyqlat/TCL.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。