AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Graph-Based Social Relation Reasoning

Wanhua Li, Yueqi Duan, Jiwen Lu, Jianjiang Feng, Jie Zhou

ECCV 2020 · Graph learning › Knowledge and temporal graphs · approach: Logical query answering and rule reasoning · 53 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 graph relational reasoning over whole image instead of pair-wise CNN (224 input)Pair CNN · PIPA social relationaccuracy (%): 58.0 -> 61.3Improved
increase input resolution from 224 to 448 (ablation)GR2N · PIPA social relationaccuracy (%): 61.3 -> 64.3Improved
increase input resolution from 224 to 448 (ablation)GR2N · PIPA social domainaccuracy (%): 69.3 -> 72.3Improved
increase input resolution from 224 to 448 (ablation)GR2N · PISC coarse relationshipsmAP (%): 72.2 -> 83.1Improved
increase input resolution from 224 to 448 (ablation)GR2N · PISC fine relationshipsmAP (%): 68.6 -> 72.7Improved
use GR2N over GCN on a fully connected graph (ablation)GCN · PIPA social relationaccuracy (%): 59.3 -> 61.3Improved
use GR2N over GGNN on a fully connected graph (ablation)GGNN · PIPA social relationaccuracy (%): 59.8 -> 61.3Improved
use any image-based GNN over Pair CNN (ablation)Pair CNN · PIPA social relationaccuracy (%): 58.0 -> 59.3Improved
jointly reason over whole image vs per-pair processingPair CNN · PISC coarse relationshipsmAP (%): 65.1 -> 83.1Improved
jointly reason over whole image vs per-pair processingPair CNN · PISC fine relationshipsmAP (%): 48.2 -> 72.7Improved
process all relations in one passPair CNN · PIPA runtime (batch size 1)forward time (s/image): 0.077 -> 0.046Improved
GR2N-448 vs GRM runtimeGRM · PIPA runtime (batch size 1)forward time (s/image): 0.294 -> 0.046Improved

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