AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Den-TP: A Density-Balanced Data Curation and Evaluation Framework for Trajectory Prediction

Ruining Yang, Yi Xu, Yun Fu, Lili Su

CVPR 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Multimodal trajectory prediction · 11 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use Den-TP selection instead of random selection at 50%HiVT-64 on 50% subset · Argoverse 1 valminADE: 0.750 -> 0.706Improved
Add submodular selection on top of density partitioning (ablation)Den-TP · Argoverse 1 val (HiVT-64)minADE: 0.729 -> 0.706Improved
Add density partitioning on top of submodular selection (ablation)Den-TP · Argoverse 1 val (HiVT-64)minADE: 0.724 -> 0.706Improved
Density-balanced Den-TP selection vs retaining all high-density scenarios plus random fillHiVT-64 on 50% subset · Argoverse 1 valminADE: 0.724 -> 0.706Improved
Reweight high-density samples (full data)HiVT-64 · Argoverse 1 valminADE: 0.715 vs 0.695 full dataNo clear effect
Epoch-wise resampling instead of random fixed subsetHiVT-64 at 95k · Argoverse 1 valminADE: 0.750 -> 0.752Hurt
Train on 50% Den-TP subset instead of full dataHiVT-64 · Argoverse 1 valminADE: 0.695 -> 0.706No clear effect
Train on 50% Den-TP subset instead of full dataQCNet · Argoverse 2 valminADE: 0.724 -> 0.754Hurt
Use Den-TP subset selected by HiVT-64 to train other models vs random subset (50%)DeMo · Argoverse 2 valminADE: 0.756 -> 0.704Improved
Use Den-TP subset vs Herding at 50%HiVT-64/HPNet · Argoverse 1 valminADE: 0.728 -> 0.706 (HiVT-64)Improved
Train on Den-TP subset instead of full data on high-density scenesHiVT/HPNet · Argoverse 1 high-density subsetJADE: 1.741 -> 1.677Improved
Train on Den-TP subset instead of full data on full validationHiVT/HPNet · Argoverse 1 full valJADE: 0.816 -> 0.819No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy