Visualization of T-MAE masking (middle) and reconstruction (right) for two ground truth multiagent trajectory instances (left). The reconstruction to the right is a combination of ground truth timesteps provided to the model (i.e. dots in the middle column with lS=5\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$l_S = 5$$\end{document} and r=0.8\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$r = 0.8$$\end{document}) and masked timesteps predicted by the model. The top/bottom row show a training/validation instance respectively