Video anomaly detection is an ill-posed problem because it relies on many parameters such
as appearance, pose, camera angle, background, and more. We distill the problem to …

With the increasing demand for human-computer interaction and health monitoring, human
behavior recognition with device-free patterns has attracted extensive attention. The …

The world's elderly population continues to grow at an unprecedented rate, creating a need
to monitor the safety of an aging population. One of the current problems is accurately …

Various audio and video applications rely on multiple deep neural network (DNN) models
deployed on edge servers to conduct inference with ms-level latency service-level …

Root-relative loss has formed the basis of 3D human pose estimation for many years.
However, this point-to-point loss treats every keypoint separately and ignores internal …

Skeleton-based action recognition is a prominent research area that provides a concise
representation of human motion. However, real-world scenarios pose challenges to the …

Abstract Video Anomaly Detection (VAD) represents a challenging and prominent research
task within computer vision. In recent years, Pose-based Video Anomaly Detection (PAD) …

Abstract We introduce Neural Puppeteer, an efficient neural rendering pipeline for
articulated shapes. By inverse rendering, we can predict 3D keypoints from multi-view 2D …

Human modelling and pose estimation stands at the crossroads of Computer Vision,
Computer Graphics, and Machine Learning. This paper presents a thorough investigation of …

Objects' rigid motions in 3D space are described by rotations and translations of a highly-
correlated set of points, each with associated x, y, z coordinates that real-valued networks …