Framework learns latent scene embeddings from 24 trajectory datasets to produce transferability scores that correlate with cross-dataset model performance.
arXiv preprint arXiv:2403.11643 (2024)
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
CiT achieves SOTA conditional trajectory prediction by cross-time-domain intention interaction that corrects representations using complementary social information from different time domains.
Introduces RHP module using continuous learnable potential field for dynamic risk profiling in trajectory prediction, reporting 25% RMSE and 29.1% minFDE reductions on highD and SHRP2 datasets.
citing papers explorer
-
Unveiling Transferability in Trajectory Prediction via Latent Scene Embeddings
Framework learns latent scene embeddings from 24 trajectory datasets to produce transferability scores that correlate with cross-dataset model performance.
-
Chatting about Conditional Trajectory Prediction
CiT achieves SOTA conditional trajectory prediction by cross-time-domain intention interaction that corrects representations using complementary social information from different time domains.
-
From Cues to Horizons: Dynamic Risk Horizon Profiling for Trajectory Prediction
Introduces RHP module using continuous learnable potential field for dynamic risk profiling in trajectory prediction, reporting 25% RMSE and 29.1% minFDE reductions on highD and SHRP2 datasets.