-
ETH and UCY datasets
The ETH and UCY datasets consist of various motions of 1,536 pedestrians across five unique scenes: ETH, Hotel, Univ, Zara1 and Zara2. They are recorded in crowded scenes. -
Stanford Drone Dataset
The Stanford Drone Dataset is a well-established benchmark for human trajectory prediction in bird’s eye view. The dataset consists of 20 scenes captured using a drone in... -
Spectral Temporal Graph Neural Network for Trajectory Prediction
The SpecTGNN dataset is used for trajectory prediction tasks. It contains historical observations of multiple interactive agents and their environment. -
Vi-Fi Multi-modal Dataset
The dataset used in the paper for layout sequence prediction from noisy mobile modality. -
Forking Paths
The Forking Paths dataset is a synthetic dataset created for multi-future trajectory prediction, where human annotators control agents in a 3D simulator.
