Video prediction is a complex time-series forecasting task with great potential in many use cases. However, conventional methods overemphasize accuracy while ignoring the slow prediction speed caused by complicated model structures that learn too much redundant information with excessive GPU memory consumption. Furthermore, conventional methods mostly predict frames sequentially (frame-by-frame) and thus are hard to accelerate. Consequently, valuable use cases such as real-time danger prediction and warning cannot achieve fast enough inference speed to be applicable in reality. Therefore, we propose a transformer-based keypoint prediction neural network (TKN), an unsupervised learning method that boost the prediction process via constrained information extraction and parallel prediction scheme. TKN is the first real-time video prediction solution to our best knowledge, while significantly reducing computation costs and maintaining other performance. Extensive experiments on KTH and Human3.6 datasets demonstrate that TKN predicts 11 times faster than existing methods while reducing memory consumption by 17.4% and achieving state-of-the-art prediction performance on average.

翻译：视频预测是一项复杂的时间序列预测任务，在许多应用场景中具有巨大潜力。然而，传统方法过度强调准确性，却忽视了因复杂模型结构学习过多冗余信息、消耗过多GPU内存而导致的预测速度缓慢。此外，传统方法大多逐帧顺序预测帧，因此难以加速。这导致实时危险预测与预警等有价值的应用场景无法达到足够快的推理速度以在实际中适用。因此，我们提出一种基于Transformer的关键点预测神经网络（TKN），这是一种通过约束信息提取和并行预测方案来提升预测过程的无监督学习方法。据我们所知，TKN是首个实时视频预测解决方案，同时显著降低了计算成本并保持了其他性能。在KTH和Human3.6数据集上的大量实验表明，TKN在将内存消耗降低17.4%的同时，预测速度比现有方法快11倍，并平均实现了最先进的预测性能。