SOTAVerified

Motion Forecasting

Motion forecasting is the task of predicting the location of a tracked object in the future

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 21–30 of 205 papers

TitleStatusHype
MambaBEV: An efficient 3D detection model with Mamba2—0
Learning to Generate Diverse Pedestrian Movements from Web Videos with Noisy Labels—0
DeMo: Decoupling Motion Forecasting into Directional Intentions and Dynamic StatesCode2
Motion Forecasting in Continuous DrivingCode2
MDMP: Multi-modal Diffusion for supervised Motion Predictions with uncertaintyCode1
Massively Multi-Person 3D Human Motion Forecasting with Scene ContextCode1
Annealed Winner-Takes-All for Motion ForecastingCode1
BAD: Bidirectional Auto-regressive Diffusion for Text-to-Motion GenerationCode2
TrajSSL: Trajectory-Enhanced Semi-Supervised 3D Object Detection—0
Motion Forecasting via Model-Based Risk Minimization—0
Show:102550
← PrevPage 3 of 21Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1WSTbrier-minFDE (K=6)26.41—Unverified
2BaseballBrobrier-minFDE (K=6)24.35—Unverified
3Constant velocity map priorbrier-minFDE (K=6)23.39—Unverified
4DQSbrier-minFDE (K=6)12.88—Unverified
5xjtub09brier-minFDE (K=6)11.46—Unverified
6suubrier-minFDE (K=6)9.51—Unverified
7yellowtaxibrier-minFDE (K=6)8.86—Unverified
8Online_CLbrier-minFDE (K=6)8.75—Unverified
9RuShengbrier-minFDE (K=6)8.38—Unverified
10mmmdddbrier-minFDE (K=6)8.26—Unverified