SOTAVerified

Trajectory Forecasting

Trajectory forecasting is a sequential prediction task, where a forecasting model predicts future trajectories of all moving agents (humans, vehicles, etc.) in a scene, based on their past trajectories and/or the scene context.

(Illustrative figure from Social NCE: Contrastive Learning of Socially-aware Motion Representations)

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 141–150 of 187 papers

TitleStatusHype
Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networks—0
Social-DualCVAE: Multimodal Trajectory Forecasting Based on Social Interactions Pattern Aware and Dual Conditional Variational Auto-Encoder—0
SocialMOIF: Multi-Order Intention Fusion for Pedestrian Trajectory Prediction—0
Spatially-Aware Graph Neural Networks for Relational Behavior Forecasting from Sensor Data—0
Spatial-Temporal Consistency Network for Low-Latency Trajectory Forecasting—0
Targeted Adversarial Attacks against Neural Network Trajectory Predictors—0
The Invisible EgoHand: 3D Hand Forecasting through EgoBody Pose Estimation—0
Towards Robust Human Trajectory Prediction in Raw Videos—0
TrackGPT -- A generative pre-trained transformer for cross-domain entity trajectory forecasting—0
Tractable Joint Prediction and Planning over Discrete Behavior Modes for Urban Driving—0
Show:102550
← PrevPage 15 of 19Next →

No leaderboard results yet.