AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Leveraging Commonsense for Object Localisation in Partial Scenes

Francesco Giuliari, Geri Skenderi, Marco Cristani, Alessio Del Bue, Yiming Wang

TPAMI 2023 · Graph learning › Knowledge and temporal graphs · approach: Scene graph generation · 5 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
add commonsense knowledge (MLP with ConceptNet via GCN)MLP · 2D localisationLSR: 0.143 -> 0.163Improved
add concept nodes with learned embeddings (ablation)D-SCG localiser · 2D localisationLSR: 0.265 -> 0.273Improved
use pretrained ConceptNet Numberbatch embeddings instead of learned (ablation)D-SCG localiser · 2D localisationLSR: 0.273 -> 0.297Improved
directed relative-position graph with end-to-end regression vs SCG-OLD-SCG localiser · 2D localisationLSR: 0.238 -> 0.297Improved
add AtLocation edges to proximity edges (ablation)D-SCG localiser · edge type ablationLSR: 0.257 -> 0.292Improved
add UsedFor edges to proximity edges (ablation)D-SCG localiser · edge type ablationLSR: 0.257 -> 0.272Improved
use both AtLocation and UsedFor edges (ablation)D-SCG localiser · edge type ablationLSR: 0.292 -> 0.297Improved
replace no-attention GraphSAGE with the proposed sparse attention (ablation)D-SCG localiser · attention ablationLSR: 0.199 -> 0.215Improved
replace GraphSAGE with GAT attention (ablation)D-SCG localiser · attention ablationLSR: 0.199 -> 0.179Hurt
replace GAT with GATv2 (ablation)D-SCG localiser · attention ablationLSR: 0.179 -> 0.202Improved
increase message passing layers from 1 to 4 (ablation)D-SCG localiser · layers ablationLSR: 0.180 -> 0.297Improved
increase message passing layers from 4 to 5 (ablation)D-SCG localiser · layers ablationLSR: 0.297 -> 0.285Hurt

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