no code implementations • CVPR 2016 • Alexandre Alahi, Kratarth Goel, Vignesh Ramanathan, Alexandre Robicquet, Li Fei-Fei, Silvio Savarese
Different from the conventional LSTM, we share the information between multiple LSTMs through a new pooling layer.
Ranked #1 on Trajectory Prediction on Stanford Drone (FDE(8/12) @K=5 metric)
no code implementations • 5 Jan 2016 • Alexandre Robicquet, Alexandre Alahi, Amir Sadeghian, Bryan Anenberg, John Doherty, Eli Wu, Silvio Savarese
We present an extensive evaluation where different methods for trajectory forecasting are evaluated and compared.
no code implementations • 19 Apr 2013 • Emile Contal, David Buffoni, Alexandre Robicquet, Nicolas Vayatis
We prove theoretical upper bounds on the regret with batches of size K for this procedure which show the improvement of the order of sqrt{K} for fixed iteration cost over purely sequential versions.