Mode-world weighted regression and an iterative decoder yield state-of-the-art multi-agent trajectory forecasts on Argoverse 2 by reducing mode collapse while raising ranking and top-1 confidence.
Motion transformer with global intention localization and lo- cal movement refinement.Advances in Neural Information Processing Systems, 35:6531–6543, 2022
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
IMR: Iterative Mode-World Weighted Regression for Multi-Agent Trajectory Prediction
Mode-world weighted regression and an iterative decoder yield state-of-the-art multi-agent trajectory forecasts on Argoverse 2 by reducing mode collapse while raising ranking and top-1 confidence.