Learning the spatial-temporal structure of body movements is a fundamental problem for
character motion synthesis. In this work, we propose a novel neural network architecture …

Training a bipedal character to play basketball and interact with objects, or a quadruped
character to move in various locomotion modes, are difficult tasks due to the fast and …

We present a framework to synthesize character movements based on high level
parameters, such that the produced movements respect the manifold of human motion …

Quadruped motion includes a wide variation of gaits such as walk, pace, trot and canter, and
actions such as jum**, sitting, turning and idling. Applying existing data-driven character …

We present GANimator, a generative model that learns to synthesize novel motions from a
single, short motion sequence. GANimator generates motions that resemble the core …

Data-driven modelling and synthesis of motion is an active research area with applications
that include animation, games, and social robotics. This paper introduces a new class of …

We propose a recurrent neural network architecture with a Forward Kinematics layer and
cycle consistency based adversarial training objective for unsupervised motion retargetting …

Human activity recognition has potential to impact a wide range of applications from
surveillance to human computer interfaces to content based video retrieval. Recently, the …

Planning algorithms are impacting technical disciplines and industries around the world,
including robotics, computer-aided design, manufacturing, computer graphics, aerospace …

Abstract Dynamic Time War** (DTW) has a quadratic time and space complexity that limits
its use to small time series. In this paper we introduce FastDTW, an approximation of DTW …