Image and video data analysis has become an increasingly important research area with
applications in different domains such as security surveillance, healthcare, augmented and …

Recovering high-quality 3D human motion in complex scenes from monocular videos is
important for many applications, ranging from AR/VR to robotics. However, capturing …

Understanding social interactions from egocentric views is crucial for many applications,
ranging from assistive robotics to AR/VR. Key to reasoning about interactions is to …

We propose the first real-time system for the egocentric estimation of 3D human body pose
in a wide range of unconstrained everyday activities. This setting has a unique set of …

Existing motion capture datasets are largely short-range and cannot yet fit the need of long-
range applications. We propose LiDARHuman26M, a new human motion capture dataset …

The high frame rate is a critical requirement for capturing fast human motions. In this setting,
existing markerless image-based methods are constrained by the lighting requirement, the …

We present a cascaded convolutional neural network for 2D hand pose estimation from
single in-the-wild RGB images. Inspired by the commonly used silhouette information in the …

Due to the visual ambiguity, purely kinematic formulations on monocular human motion
capture are often physically incorrect, biomechanically implausible, and can not reconstruct …

Recent advances in image-based human pose estimation make it possible to capture 3D
human motion from a single RGB video. However, the inherent depth ambiguity and self …

Occlusions between human and objects, especially for the activities of human-object
interactions, are very common in practical applications. However, most of the existing …