Pre-training video transformers on extra large-scale datasets is generally required to
achieve premier performance on relatively small datasets. In this paper, we show that video …

Benefiting from masked visual modeling, self-supervised video representation learning has
achieved remarkable progress. However, existing methods focus on learning …

Transformer models have shown great success handling long-range interactions, making
them a promising tool for modeling video. However, they lack inductive biases and scale …

Understanding the visual world from the perspective of humans (egocentric) has been a
long-standing challenge in computer vision. Egocentric videos exhibit high scene complexity …

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 …

Motion, as a feature of video that changes in temporal sequences, is crucial to visual
understanding. The powerful video representation and extraction models are typically able …

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

Self-supervised learning (SSL) techniques have recently produced outstanding results in
learning visual representations from unlabeled videos. Despite the importance of motion in …

As the most essential property in a video, motion information is critical to a robust and
generalized video representation. To inject motion dynamics, recent works have adopted …

Powerful self-supervised representation models are able to step out of the traditional
supervised paradigm and rely merely on unlabeled data to achieve a deep understanding of …