AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Learning Object Placement via Dual-Path Graph Completion

Siyuan Zhou, Liu Liu, Li Niu, Liqing Zhang

ECCV 2022 · Graph learning › Knowledge and temporal graphs · approach: Scene graph generation · 25 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 GracoNet instead of PlaceNetobject placement · OPA test (positive samples)accuracy: 0.683 -> 0.847Improved
use GracoNet instead of PlaceNetobject placement · OPA test (positive samples)FID: 36.69 -> 27.75Improved
add NEH multi-scale nodes instead of global vectors (ablation)GracoNet · OPA test (positive samples)accuracy: 0.793 -> 0.828Improved
add PSN cross-attention instead of concat+fc (ablation)GracoNet · OPA test (positive samples)accuracy: 0.828 -> 0.847Improved
add small-scale background nodes (n=[2,4,8] vs [2]) (ablation)GracoNet · OPA test (positive samples)FID/LPIPS: LPIPS 0.136 -> 0.206Improved
extend background head with 16x16 nodes (n=[2,4,8,16]) (ablation)GracoNet · OPA test (positive samples)accuracy: 0.847 -> 0.837Hurt
add placement encodings p^K and p^V (ablation)GracoNet · OPA test (positive samples)accuracy: 0.793 -> 0.847Improved
make placement encodings independent across attention heads (ablation)GracoNet · OPA test (positive samples)LPIPS: 0.170 -> 0.206Improved
add classification loss L_cls_s (ablation)GracoNet · OPA test (positive samples)accuracy: 0.734 -> 0.847Improved
add reconstruction loss L_rec_s (ablation)GracoNet · OPA test (positive samples)accuracy: 0.767 -> 0.847; FID 25.53 -> 27.75Mixed
add KL loss L_kld_s (ablation)GracoNet · OPA test (positive samples)accuracy: 0.844 -> 0.847Improved
add unsupervised adversarial loss L_adv_u (ablation)GracoNet · OPA test (positive samples)LPIPS: 0.038 -> 0.206Improved

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