Analyzing and forecasting trajectories of agents like pedestrians and cars in complex scenes has become more and more significant in many intelligent systems and applications.
In this paper, we bring a new ``view'' for trajectory prediction to model and forecast trajectories hierarchically according to different frequency portions from the spectral domain to learn to forecast trajectories by considering their frequency responses.
The current methods are dedicated to studying the agents' future trajectories under the social interaction and the sceneries' physical constraints.
Different frequency bands in the trajectory spectrums could hierarchically reflect agents' motion preferences at different scales.
Ranked #3 on Trajectory Prediction on ETH/UCY
Then, we assume that the target agents may plan their future behaviors according to each of these categorized styles, thus utilizing different style channels to make predictions with significant style differences in parallel.
Visual images usually contain the informative context of the environment, thereby helping to predict agents' behaviors.