AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Representing Spatial Trajectories as Distributions

Didac Suris Coll-Vinent, Carl Vondrick

NeurIPS 2022 · Probabilistic and scientific modeling › Molecules and proteins · approach: Multimodal trajectory prediction · 3 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 trajectory-distribution representations with continuous-time decodingTrajRep · FineGym, Diving48, and FisV; long and short sequencesMSE: FineGym long future: 9.54 -> 8.50; Diving48 long future: 11.59 -> 9.81; FisV short interpolation: 8.28 -> 5.88Improved
Add re-encoded decoded trajectories during training (ablation)TrajRep · FineGym, Diving48, and FisV; prediction tasksMSE: FineGym long future: 8.82 -> 8.50; Diving48 long past: 11.74 -> 12.00; Diving48 short interpolation: 5.00 -> 5.04Mixed
Use re-encoding of decoded trajectories as harder training examples (ablation)TrajRep · Prediction tasks across the three datasetsMSEImproved

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