AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Disentangled Multi-Relational Graph Convolutional Network for Pedestrian Trajectory Prediction

Inhwan Bae, Hae-Gon Jeon

AAAI 2021 · Graph learning › Knowledge and temporal graphs · approach: Graph reasoning for visual recognition · 53 citations (OpenAlex)

Read the paper

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 DMRGCN instead of Social-STGCNNpedestrian trajectory prediction · AVG (ETH and UCY)ADE: 0.44 -> 0.34Improved
use DMRGCN instead of Social-STGCNNpedestrian trajectory prediction · AVG (ETH and UCY)FDE: 0.75 -> 0.58Improved
add global temporal aggregation to the GCN-based model (ablation)DMRGCN · AVGFDE: 0.63 -> 0.58Improved
add global temporal aggregation without GCN (ablation)DMRGCN variant with no GCN · AVGFDE: 0.74 -> 0.72No clear effect
use disentangled multi-scale aggregation rather than ordinary multi-scale aggregation (ablation)DMRGCN · AVGFDE: 0.69 -> 0.68Improved
add both distance and relative-displacement relations rather than distance alone (ablation)DMRGCN with no aggregation · AVGFDE: 0.71 -> 0.70Improved
add both distance and relative-displacement relations rather than displacement alone (ablation)DMRGCN with no aggregation · AVGADE: 0.39 -> 0.38No clear effect
vary DropEdge rate across 0.9, 0.8, 0.7, 0.6, and 0.5 (ablation)DMRGCN · AVGADE: 0.37, 0.35, 0.37, 0.37, 0.37Mixed
vary the number of TPCNN blocks from 1 to 6 (ablation)DMRGCN with one GCN and DropEdge 0.8 · AVGFDE: 0.69, 0.70, 0.68, 0.63, 0.70, 0.73Mixed
increase the number of GCNs from one to two (ablation)DMRGCN with GTA · AVGFDE: 0.58 -> 0.61Hurt
vary distance-relation scale set (ablation)DMRGCN · AVGFDE: 0.72, 0.71, 0.69, 0.72, 0.70Mixed
vary relative-displacement scale set (ablation)DMRGCN · AVGFDE: 0.73, 0.71, 0.70, 0.69, 0.70Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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