Motion forecasting is the task of predicting the location of a tracked object in the future
In our baseline experiments, we illustrate how detailed map information such as lane direction, driveable area, and ground height improves the accuracy of 3D object tracking and motion forecasting.
We use 3D object tracking to mine for more than 300k interesting vehicle trajectories to create a trajectory forecasting benchmark.
To facilitate the training, the network is learned with an auxiliary task of predicting future location in which the activity will happen.
Ranked #1 on Activity Prediction on ActEV
This is implemented via a hierarchy of small-sized neural networks connected analogously to the kinematic chains in the human body as well as a joint-wise decomposition in the loss function.
First, we represent the data using a spatio-temporal tensor of 3D skeleton coordinates which allows formulating the prediction problem as an inpainting one, for which GANs work particularly well.
Nevertheless, visual monitoring of fetal motion based on displayed slices, and navigation at the level of stacks-of-slices is inefficient.