Object detection, Person tracking, and Person property estimation (PPE) are identical
innovation areas trying to improve their accuracy in different parameters to fit various real …

While methods that regress 3D human meshes from images have progressed rapidly, the
estimated body shapes often do not capture the true human shape. This is problematic …

We introduce MotioNet, a deep neural network that directly reconstructs the motion of a 3D
human skeleton from a monocular video. While previous methods rely on either rigging or …

This paper proposes GraviCap, ie, a new approach for joint markerless 3D human motion
capture and object trajectory estimation from monocular RGB videos. We focus on scenes …

In this work, we consider the problem of estimating the 3D position of multiple humans in a
scene as well as their body shape and articulation from a single RGB video recorded with a …

Photo-based forensic identification can be critical in the prosecution of, and defense against,
criminal charges. Identification techniques range from the specific biometric-based to the …

Abstract 2D poses are insufficient to estimate human activities under the geometric
ambiguities, occlusion, diverse appearance, and viewpoints inside the image. As a result …

In this article we propose an unsupervised feature extraction method to capture temporal
information on monocular videos, where we detect and encode subject of interest in each …

Forensic DNA analysis has been critical in prosecuting crimes and overturning wrongful
convictions. At the same time, other physical and digital forensic identification techniques …

We address the difficult problem of estimating the attributes of weight and height of
individuals from pictures taken in completely unconstrained settings. We present a deep …