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:视频预测是一个具有潜在应用的复杂时间序列预测任务。然而,传统方法过分强调准确性,忽视了由于学习过多冗余信息和GPU内存消耗过多而导致的缓慢预测速度。此外,传统方法大多按顺序预测帧,因此难以加速。因此,我们提出了基于transformer的关键点预测神经网络(TKN),一种无监督学习方法,通过受限信息提取和并行预测方案提高预测过程。在我们的最佳知识范围内,TKN是第一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证明,TKN的预测速度比现有方法快11倍,内存消耗减少17.4%,并在平均水平上实现了最新的预测性能。