PGformer：用于多人高交互性极端运动预测的代理桥接博弈Transformer
PGformer: Proxy-Bridged Game Transformer for Multi-Person Highly Interactive Extreme Motion Prediction
AI总结：
本文提出PGformer模型，通过交叉查询注意力模块和代理单元学习多人高度交互姿态轨迹间的双向依赖关系，有效解决了极端运动协同预测问题，并在多个数据集上取得优异性能。
摘要：
多人运动预测是一项具有挑战性的任务，特别是在高度交互的真实世界场景中。以往的大多数工作致力于研究弱交互的情况（例如一起行走），在这种情况下，通常孤立地预测每个人的姿态仍然能取得良好的性能。本文专注于具有极端运动的多人协同运动预测，并尝试探索高度交互人物姿态轨迹之间的关系。具体而言，提出了一种新颖的交叉查询注意力（XQA）模块，以双向学习针对这种情况量身定制的两个姿态序列之间的交叉依赖关系。此外，引入了一个代理单元来桥接相关人物，该单元与我们提出的XQA模块协同工作，并精细地控制双向空间信息流。这些设计随后被整合到一个基于Transformer的架构中，由此产生的模型被称为代理桥接博弈Transformer（PGformer），用于多人交互运动预测。其有效性已在具有挑战性的ExPI数据集上进行了评估，该数据集包含高度交互的动作。我们的PGformer在短期和长期预测中均大幅优于最先进的方法。此外，我们的方法还可以兼容弱交互的CMU-Mocap和MuPoTS-3D数据集，并扩展到2人以上的情况，取得了令人鼓舞的结果。
英文摘要：
Multi-person motion prediction is a challenging task, especially for real-world scenarios of highly interacted persons. Most previous works have been devoted to studying the case of weak interactions (e.g., walking together), in which typically forecasting each human pose in isolation can still achieve good performances. This paper focuses on collaborative motion prediction for multiple persons with extreme motions and attempts to explore the relationships between the highly interactive persons' pose trajectories. Specifically, a novel cross-query attention (XQA) module is proposed to bilaterally learn the cross-dependencies between the two pose sequences tailored for this situation. A proxy unit is additionally introduced to bridge the involved persons, which cooperates with our proposed XQA module and subtly controls the bidirectional spatial information flows. These designs are then integrated into a Transformer-based architecture and the resulting model is called Proxy-bridged Game Transformer (PGformer) for multi-person interactive motion prediction. Its effectiveness has been evaluated on the challenging ExPI dataset, which involves highly interactive actions. Our PGformer consistently outperforms the state-of-the-art methods in both short- and long-term predictions by a large margin. Besides, our approach can also be compatible with the weakly interacted CMU-Mocap and MuPoTS-3D datasets and extended to the case of more than 2 individuals with encouraging results.
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。
