In this work, we explore self-supervised visual pre-training on images from diverse, in-the-
wild videos for real-world robotic tasks. Like prior work, our visual representations are pre …

The foundation models have recently shown excellent performance on a variety of
downstream tasks in computer vision. However, most existing vision foundation models …

Neural compression is the application of neural networks and other machine learning
methods to data compression. Recent advances in statistical machine learning have opened …

Abstract Video Foundation Models (VFMs) have received limited exploration due to high
computational costs and data scarcity. Previous VFMs rely on Image Foundation Models …

Modern hierarchical vision transformers have added several vision-specific components in
the pursuit of supervised classification performance. While these components lead to …

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 …

In this paper, we study masked autoencoder (MAE) pretraining on videos for matching-
based downstream tasks, including visual object tracking (VOT) and video object …

Abstract We present Recurrent Vision Transformers (RVTs), a novel backbone for object
detection with event cameras. Event cameras provide visual information with sub …

Visual model-based reinforcement learning (RL) has the potential to enable sample-efficient
robot learning from visual observations. Yet the current approaches typically train a single …

Semi-supervised action recognition is a challenging but critical task due to the high cost of
video annotations. Existing approaches mainly use convolutional neural networks, yet …