We introduce a novel self-supervised contrastive learning method to learn
representations from unlabelled videos. Existing approaches ignore the
specifics of input distortions, e.g., by learning invariance to temporal
transformations. Instead, we argue that video representation should preserve
video dynamics and reflect temporal manipulations of the input. Therefore, we
exploit novel constraints to build representations that are equivariant to
temporal transformations and better capture video dynamics. In our method,
relative temporal transformations between augmented clips of a video are
encoded in a vector and contrasted with other transformation vectors. To
support temporal equivariance learning, we additionally propose the
self-supervised classification of two clips of a video into 1. overlapping 2.
ordered, or 3. unordered. Our experiments show that time-equivariant
representations achieve state-of-the-art results in video retrieval and action
recognition benchmarks on UCF101, HMDB51, and Diving48.

介绍了一种新的自监督对比学习方法，旨在从未标记的视频中学习表示。该方法利用新的约束条件，以建立对时间变换等价的表示，并更好地捕捉视频动态。实验表明，时间等变表示在 UCF101，HMDB51 和 Diving48 的视频检索和动作识别基准测试中实现了最先进的结果。