MANTRA

Reported on 6 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Time Series6 results

Trajectory PredictiononETH/UCY
ADE-8/12· 2020-06-05
0.32
best: 0.54 (Sophie)
MANTRA: Memory Augmented Networks for Multiple Trajectory Prediction arXiv:2006.03340
Trajectory PredictiononETH/UCY
FDE-8/12· 2020-06-05
0.33
best: 0.84 (Social BiGAT)
MANTRA: Memory Augmented Networks for Multiple Trajectory Prediction arXiv:2006.03340
Trajectory PredictiononStanford Drone
ADE (8/12) @K=5· 2020-06-05
13.51
best: 31.19 (Social LSTM)
MANTRA: Memory Augmented Networks for Multiple Trajectory Prediction arXiv:2006.03340
Trajectory PredictiononStanford Drone
ADE-8/12 @K = 20· 2020-06-05
8.96
best: 27.23 (Social GAN)
MANTRA: Memory Augmented Networks for Multiple Trajectory Prediction arXiv:2006.03340
Trajectory PredictiononStanford Drone
FDE(8/12) @K=5· 2020-06-05
27.34
best: 56.97 (Social LSTM)
MANTRA: Memory Augmented Networks for Multiple Trajectory Prediction arXiv:2006.03340
Trajectory PredictiononStanford Drone
FDE-8/12 @K= 20· 2020-06-05
17.76
best: 41.44 (Social GAN)
MANTRA: Memory Augmented Networks for Multiple Trajectory Prediction arXiv:2006.03340