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 …

Device-free activity recognition plays a crucial role in smart building, security, and human–
computer interaction, which shows its strength in its convenience and cost-efficiency …

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 …

We present a new test-time optimization method for estimating dense and long-range motion
from a video sequence. Prior optical flow or particle video tracking algorithms typically …

Establishing correspondence between images or scenes is a significant challenge in
computer vision, especially given occlusions, viewpoint changes, and varying object …

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 …

Existing approaches for unsupervised point cloud pre-training are constrained to either
scene-level or point/voxel-level instance discrimination. Scene-level methods tend to lose …

Object-centric representations are a promising path toward more systematic generalization
by providing flexible abstractions upon which compositional world models can be built …

Abstract Coronavirus disease 2019 (COVID-19) has infected more than 1.3 million
individuals all over the world and caused more than 106,000 deaths. One major hurdle in …

The training of a feature extraction network typically requires abundant manually annotated
training samples, making this a time-consuming and costly process. Accordingly, we …