Anticipating the future motions of 3D articulate objects is challenging due to its non-linear
and highly stochastic nature. Current approaches typically represent the skeleton of an …

Predicting future trajectories of surrounding agents is essential for safety-critical autonomous
driving. Most existing work focuses on predicting marginal trajectories for each agent …

Motion forecasting is a key module in an autonomous driving system. Due to the
heterogeneous nature of multi-sourced input, multimodality in agent behavior, and low …

Despite the great progress in human motion prediction, it remains a challenging task due to
the complicated structural dynamics of human behaviors. In this paper, we address this …

Forecasting long-term human motion is a challenging task due to the non-linearity, multi-
modality and inherent uncertainty in future trajectories. The underlying scene and past …

We propose to predict the future trajectories of observed agents (eg, pedestrians or vehicles)
by estimating and using their goals at multiple time scales. We argue that the goal of a …

Despite significant progress in image-based 3D scene flow estimation, the performance of
such approaches has not yet reached the fidelity required by many applications …

An effective understanding of the contextual environment and accurate motion forecasting of
surrounding agents is crucial for the development of autonomous vehicles and social mobile …

The real-world deployment of an autonomous driving system requires its components to run
on-board and in real-time, including the motion prediction module that predicts the future …

Predicting future motions of road participants is an important task for driving autonomously in
urban scenes. Existing models excel at predicting marginal trajectories for single agents, yet …