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 11–20 of 205 papers

TitleStatusHype
Argoverse 2: Next Generation Datasets for Self-Driving Perception and ForecastingCode2
DeMo: Decoupling Motion Forecasting into Directional Intentions and Dynamic StatesCode2
BAD: Bidirectional Auto-regressive Diffusion for Text-to-Motion GenerationCode2
Frozen Transformers in Language Models Are Effective Visual Encoder LayersCode2
Forecast-MAE: Self-supervised Pre-training for Motion Forecasting with Masked AutoencodersCode2
HiVT: Hierarchical Vector Transformer for Multi-Agent Motion PredictionCode2
Motion Forecasting in Continuous DrivingCode2
CORE4D: A 4D Human-Object-Human Interaction Dataset for Collaborative Object REarrangementCode2
Multi-Agent Trajectory Prediction with Difficulty-Guided Feature Enhancement NetworkCode2
Best Practices for 2-Body Pose ForecastingCode1
Show:102550
← PrevPage 2 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