Motion Forecasting On Argoverse Cvpr 2020

评估指标

DAC (K=6)
MR (K=1)
MR (K=6)
brier-minFDE (K=6)
minADE (K=1)
minADE (K=6)
minFDE (K=1)
minFDE (K=6)

评测结果

各个模型在此基准测试上的表现结果

Paper TitleRepository
lt_cont_k60.99310.53480.53483.29231.54071.54073.29233.2923--
Holmes0.99270.820.41813.35842.90761.38366.54162.6639--
SEPT0.99220.51540.10321.68201.44120.72823.17771.0566--
HTTP0.99220.61330.1422.11141.83860.91164.03091.4503--
R-Pred0.9920.53440.11651.77651.58430.76293.47181.1236R-Pred: Two-Stage Motion Prediction Via Tube-Query Attention-Based Trajectory Refinement-
ATTTHOM0.99130.55730.12071.79921.6320.83443.55051.1568--
argo_test_18_5m_add_rotation_change_data_change_model_3_010.99120.59180.2052.35441.85941.14633.82161.7597--
TO0.99120.55280.10751.7941.61240.78193.51161.1127--
Anonymous12340.9910.78280.29043.21962.95761.45376.36732.5476--
HIKVISION-ADLab-hz0.99090.5530.12091.81881.62870.8183.52631.1888--
LaneRCNN (IROS 2021)0.99030.56850.12322.1471.68520.90383.69161.4526LaneRCNN: Distributed Representations for Graph-Centric Motion Forecasting-
chl(yiqi)0.99030.55790.1211.88171.61170.8133.50871.1873--
DCMS0.99020.53220.10941.75641.47680.76593.25151.135Bootstrap Motion Forecasting With Self-Consistent Constraints-
Jack-M0.990.5750.12661.85671.7150.82853.75821.2403--
GANet0.98990.54990.11791.78991.59210.8063.45481.1605GANet: Goal Area Network for Motion Forecasting
SceneTransformer0.98990.59210.12551.88681.81080.80264.05511.2321--
PRIME0.98980.58670.1152.09781.91051.21873.82171.5582--
FGNet_sub0.98980.58140.13411.9181.65610.80123.64961.2235--
Ameame0.98980.55140.12071.80061.59590.80573.46481.1693--
VI LaneIter0.98970.52750.10651.73131.51810.77093.28491.1057--
0 of 299 row(s) selected.
Motion Forecasting On Argoverse Cvpr 2020 | SOTA | HyperAI超神经