Human motion generation aims to generate natural human pose sequences and shows
immense potential for real-world applications. Substantial progress has been made recently …

In this work, we investigate a simple and must-known conditional generative framework
based on Vector Quantised-Variational AutoEncoder (VQ-VAE) and Generative Pre-trained …

We study a challenging task, conditional human motion generation, which produces
plausible human motion sequences according to various conditional inputs, such as action …

We address the problem of generating diverse 3D human motions from textual descriptions.
This challenging task requires joint modeling of both modalities: understanding and …

This paper addresses a novel task of anticipating 3D human-object interactions (HOIs). Most
existing research on HOI synthesis lacks comprehensive whole-body interactions with …

We introduce HuMoR: a 3D Human Motion Model for Robust Estimation of temporal pose
and shape. Though substantial progress has been made in estimating 3D human motion …

With the recent surge in popularity of AR/VR applications, realistic and accurate control of
3D full-body avatars has become a highly demanded feature. A particular challenge is that …

We present a unified perspective on tackling various human-centric video tasks by learning
human motion representations from large-scale and heterogeneous data resources …

Large datasets are the cornerstone of recent advances in computer vision using deep
learning. In contrast, existing human motion capture (mocap) datasets are small and the …

This paper tackles the problem of human motion prediction, consisting in forecasting future
body poses from historically observed sequences. State-of-the-art approaches provide good …