使用基于 Transformer 的模型进行鲁棒人体运动预测
Robust Human Motion Forecasting using Transformer-based Model
AI总结：
提出双通道 Transformer 模型 2CH-TR，利用 400ms 观测序列实时预测短期与长期三维人体运动，在遮挡噪声下更轻量快速，并降低 Human3.6M 上的预测误差。
摘要：
理解人体运动是开发人机协作应用的一项基本挑战。计算机视觉研究人员在处理这一领域时，仅关注降低预测误差，却没有考虑促进其在机器人中实施的要求。在本文中，我们提出了一种基于 Transformer 的新模型，可同时处理短期和长期的实时三维人体运动预测。我们的双通道 Transformer（2CH-TR）能够高效利用短观测序列（400ms）的时空信息，并在当前最先进方法面前取得具有竞争力的准确率。2CH-TR 的突出之处在于 Transformer 的高效性能，比竞争模型更轻量、更快速。此外，我们的模型在人体运动被严重遮挡的条件下进行了测试，证明了其在高噪声环境中重建和预测三维人体运动的鲁棒性。实验结果表明，在相同输入前缀条件下，所提出的 2CH-TR 在重建和预测方面优于另一种基于 Transformer 的最先进模型 ST-Transformer。在 Human3.6M 数据集上、采用 400ms 输入前缀时，我们的模型将 ST-Transformer 的均方误差在短期预测中降低了 8.89%，在长期预测中降低了 2.57%。网页：https://evm7.github.io/2CHTR-page/
英文摘要：
Comprehending human motion is a fundamental challenge for developing Human-Robot Collaborative applications. Computer vision researchers have addressed this field by only focusing on reducing error in predictions, but not taking into account the requirements to facilitate its implementation in robots. In this paper, we propose a new model based on Transformer that simultaneously deals with the real time 3D human motion forecasting in the short and long term. Our 2-Channel Transformer (2CH-TR) is able to efficiently exploit the spatio-temporal information of a shortly observed sequence (400ms) and generates a competitive accuracy against the current state-of-the-art. 2CH-TR stands out for the efficient performance of the Transformer, being lighter and faster than its competitors. In addition, our model is tested in conditions where the human motion is severely occluded, demonstrating its robustness in reconstructing and predicting 3D human motion in a highly noisy environment. Our experiment results show that the proposed 2CH-TR outperforms the ST-Transformer, which is another state-of-the-art model based on the Transformer, in terms of reconstruction and prediction under the same conditions of input prefix. Our model reduces in 8.89% the mean squared error of ST-Transformer in short-term prediction, and 2.57% in long-term prediction in Human3.6M dataset with 400ms input prefix. Webpage: https://evm7.github.io/2CHTR-page/
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。
