Abstract Pretrained Foundation Models (PFMs) are regarded as the foundation for various
downstream tasks across different data modalities. A PFM (eg, BERT, ChatGPT, GPT-4) is …

Self-supervised learning has gained popularity because of its ability to avoid the cost of
annotating large-scale datasets. It is capable of adopting self-defined pseudolabels as …

The remarkable success of deep learning in various domains relies on the availability of
large-scale annotated datasets. However, obtaining annotations is expensive and requires …

We present a self-supervised Contrastive Video Representation Learning (CVRL) method to
learn spatiotemporal visual representations from unlabeled videos. Our representations are …

The rapid development of Artificial Intelligence (AI) technology has enabled the deployment
of various systems based on it. However, many current AI systems are found vulnerable to …

Video self-supervised learning is a challenging task, which requires significant expressive
power from the model to leverage rich spatial-temporal knowledge and generate effective …

Contrastive learning has nearly closed the gap between supervised and self-supervised
learning of image representations, and has also been explored for videos. However, prior …

Motion, as the uniqueness of a video, has been critical to the development of video
understanding models. Modern deep learning models leverage motion by either executing …

This paper studies the problem of learning self-supervised representations on videos. In
contrast to image modality that only requires appearance information on objects or scenes …

Learning a good representation for space-time correspondence is the key for various
computer vision tasks, including tracking object bounding boxes and performing video …