Denoising diffusion models are a powerful type of generative models used to capture
complex distributions of real-world signals. However, their applicability is limited to …

We present an approach to modeling an image-space prior on scene motion. Our prior is
learned from a collection of motion trajectories extracted from real video sequences …

From an image of a person in action, we can easily guess the 3D motion of the person in the
immediate past and future. This is because we have a mental model of 3D human dynamics …

With advances in data-driven machine learning research, a wide variety of prediction
models have been proposed to capture spatio-temporal features for the analysis of video …

Binaural audio provides a listener with 3D sound sensation, allowing a rich perceptual
experience of the scene. However, binaural recordings are scarcely available and require …

Road network extraction from satellite images often produce fragmented road segments
leading to road maps unfit for real applications. Pixel-wise classification fails to predict …

State-of-the-art methods for action recognition commonly use two networks: the spatial
stream, which takes RGB frames as input, and the temporal stream, which takes optical flow …

In this paper, we propose a convolutional layer inspired by optical flow algorithms to learn
motion representations. Our representation flow layer is a fully-differentiable layer designed …

Human actions are often captured by multiple cameras (or sensors) to overcome the
significant variations in viewpoints, background clutter, object speed, and motion patterns in …

Human-object interaction (HOI) detection aims to detect and recognise how people interact
with the objects that surround them. This is challenging as different interaction categories …