Dynamic Time Warping (DTW) is widely used for temporal data processing.
However, existing methods can neither learn the discriminative prototypes of
different classes nor exploit such prototypes for further analysis. We propose
Discriminative Prototype DTW (DP-DTW), a novel method to learn class-specific
discriminative prototypes for temporal recognition tasks. DP-DTW shows superior
performance compared to conventional DTWs on time series classification
benchmarks. Combined with end-to-end deep learning, DP-DTW can handle
challenging weakly supervised action segmentation problems and achieves state
of the art results on standard benchmarks. Moreover, detailed reasoning on the
input video is enabled by the learned action prototypes. Specifically, an
action-based video summarization can be obtained by aligning the input sequence
with action prototypes.

本文提出了 DP-DTW 方法，用于学习类别特定的判别式原型，以便在时间识别任务中实现更好的性能，并且结合端到端深度学习，可在标准基准测试中实现最先进的弱监督行动分割问题，并通过对所学行动原型的详细推理来启用输入视频的详细摘要，即可以通过将输入序列与行动原型对齐来获得基于行动的视频摘要。