Deep supervised learning algorithms typically require a large volume of labeled data to
achieve satisfactory performance. However, the process of collecting and labeling such data …

The research advances concerning the typical architectures of convolutional neural
networks (CNNs) as well as their optimizations are analyzed and elaborated in detail in this …

Finding correspondences between images is a fundamental problem in computer vision. In
this paper, we show that correspondence emerges in image diffusion models without any …

Video object segmentation (VOS) aims at segmenting a particular object throughout the
entire video clip sequence. The state-of-the-art VOS methods have achieved excellent …

In this paper, we question if self-supervised learning provides new properties to Vision
Transformer (ViT) that stand out compared to convolutional networks (convnets). Beyond the …

Generic motion understanding from video involves not only tracking objects, but also
perceiving how their surfaces deform and move. This information is useful to make …

In video transformers, the time dimension is often treated in the same way as the two spatial
dimensions. However, in a scene where objects or the camera may move, a physical point …

Panoptic segmentation assigns semantic and instance ID labels to every pixel of an image.
As permutations of instance IDs are also valid solutions, the task requires learning of high …

Tracking pixels in videos is typically studied as an optical flow estimation problem, where
every pixel is described with a displacement vector that locates it in the next frame. Even …

The objective of this paper is visual-only self-supervised video representation learning. We
make the following contributions:(i) we investigate the benefit of adding semantic-class …