Long term temporal representation methods demand high computational cost, restricting their practical use in real world applications. We propose a two-step deep residual method for efficiently learning long-term discriminative temporal representation, whilst significantly reducing computational cost. In the first step, a novel self-supervision deep temporal embedding method is presented to embed repetitive short-term motions at a cluster-friendly feature space. In the second step, an efficient temporal representation is made by leveraging the differences between the original data and its associated repetitive motion clusters as a novel deep residual method. Experimental results demonstrate that, the proposed method achieves competitive results on some challenging human action recognition datasets like UCF101, HMDB51, THUMOS14, and Kinetics-400.

中文翻译：

---

动作识别中基于上下文的深度时间嵌入网络

长期时间表示方法需要很高的计算成本，从而限制了它们在实际应用中的实际使用。我们提出了两步深度残差方法，可以有效地学习长期判别性时间表示，同时显着降低计算成本。第一步，提出了一种新颖的自我监督深度时态嵌入方法，将重复的短期运动嵌入到聚类友好的特征空间中。在第二步中，通过利用原始数据及其关联的重复运动簇之间的差异作为一种新颖的深度残差方法，可以进行有效的时间表示。实验结果表明，该方法在一些具有挑战性的人类动作识别数据集（如UCF101，HMDB51，THUMOS14和Kinetics-400）上取得了竞争性结果。