Time-series data exists in every corner of real-world systems and services, ranging from
satellites in the sky to wearable devices on human bodies. Learning representations by …

Video self-supervised learning (VSSL) has made significant progress in recent years.
However, the exact behavior and dynamics of these models under different forms of …

Abstract This paper proposes Group Activity Feature (GAF) learning in which features of
multi-person activity are learned as a compact latent vector. Unlike prior work in which the …

Self-supervised learning methods have shown significant promise in acquiring robust
spatiotemporal representations from unlabeled videos. In this work, we address three critical …

Self-supervised video representation learning leaves out heavy manual annotation by
automatically excavating supervisory signals. Although contrastive learning based …

Contrastive representation learning has proven to be an effective self-supervised learning
method for images and videos. Most successful approaches are based on Noise Contrastive …

Self-supervised learning is an effective way for label-free model pre-training, especially in
the video domain where labeling is expensive. Existing self-supervised works in the video …

Self-supervised approaches for video have shown impressive results in video
understanding tasks. However, unlike early works that leverage temporal self-supervision …

Self-supervised contrastive learning draws on power representational models to acquire
generic semantic features from unlabeled data, and the key to training such models lies in …

In this paper, we propose a self-supervised video representation learning (video SSL)
method by taking inspiration from cognitive science and neuroscience on human visual …