Weakly-supervised temporal action localization (WS-TAL) aims to localize actions in untrimmed videos with only video-level labels. Most existing models follow the "localization by classification" procedure: locate temporal regions contributing most to the video-level classification. Generally, they process each snippet (or frame) individually and thus overlook the fruitful temporal context relation. Here arises the single snippet cheating issue: "hard" snippets are too vague to be classified. In this paper, we argue that learning by comparing helps identify these hard snippets and we propose to utilize snippet Contrastive learning to Localize Actions, CoLA for short. Specifically, we propose a Snippet Contrast (SniCo) Loss to refine the hard snippet representation in feature space, which guides the network to perceive precise temporal boundaries and avoid the temporal interval interruption. Besides, since it is infeasible to access frame-level annotations, we introduce a Hard Snippet Mining algorithm to locate the potential hard snippets. Substantial analyses verify that this mining strategy efficaciously captures the hard snippets and SniCo Loss leads to more informative feature representation. Extensive experiments show that CoLA achieves state-of-the-art results on THUMOS'14 and ActivityNet v1.2 datasets.

翻译：(WS-TAL), 目的是将未剪辑的视频中的动作本地化, 仅使用视频标签。 大多数现有模型都遵循“ 分类本地化” 程序 : 定位对视频分类贡献最大的时间区域 。 一般来说, 它们单独处理每个片段( 或框架), 从而忽略有成果的时间背景关系 。 这里出现了单片欺骗问题 : “ 硬” 片段太模糊, 无法分类 。 在本文中, 我们争辩说, 比较学习有助于识别这些硬片段, 我们提议使用断片反差学习来定位动作, 科拉短调。 具体地说, 我们建议使用一个“ 断片反差( Snico) 失败 来完善地段空间的硬片代表, 引导网络了解准确的时间界限并避免时间间隔中断 。 此外, 由于无法访问框架级说明, 我们引入了硬片采矿算法来定位潜在的硬片片片段。 大量分析证实, 这一采矿战略是否精确地捕捉到硬片段和Snico- loadalalal laves adal laves laves 。