We introduce a context-agnostic unsupervised method to count periodicity in videos. Current methods estimate periodicity for a specific type of application (e.g. some repetitive human motion). We propose a novel method that provides a powerful generalisation ability since it is not biased towards specific visual features. It is thus applicable to a range of diverse domains that require no adaptation, by relying on a deep neural network that is trained completely unsupervised. More specifically, it is trained to transform the periodic temporal data into some lower-dimensional latent encoding in such a way that it forms a cyclic path in this latent space. We also introduce a novel algorithm that is able to reliably detect and count periods in complex time series. Despite being unsupervised and facing supervised methods with complex architectures, our experimental results demonstrate that our approach is able to reach state-of-the-art performance for periodicity counting on the challenging QUVA video benchmark.