Multimodal machine learning is a vibrant multi-disciplinary research field that aims to design
computer agents with intelligent capabilities such as understanding, reasoning, and learning …

Intangible cultural heritage (ICH) as a field of research and site for digital efforts has grown
significantly since the UNESCO 2003 Convention for the Safeguarding of Intangible …

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

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 …

Stochastic human motion prediction (HMP) has generally been tackled with generative
adversarial networks and variational autoencoders. Most prior works aim at predicting highly …

Synthesizing 3D human avatars interacting realistically with a scene is an important problem
with applications in AR/VR, video games, and robotics. Towards this goal, we address the …

We present UnrealEgo, ie, a new large-scale naturalistic dataset for egocentric 3D human
pose estimation. UnrealEgo is based on an advanced concept of eyeglasses equipped with …

We present a lightweight and affordable motion capture method based on two smartwatches
and a head-mounted camera. In contrast to the existing approaches that use six or more …

Motion in-betweening (MIB) is a process of generating intermediate skeletal movement
between the given start and target poses while preserving the naturalness of the motion …

Movement dataset reviews exist but are limited in coverage, both in terms of size and
research discipline. While topic-specific reviews clearly have their merit, it is critical to have a …