AI Paper Atlas

Research map / Video / Action recognition

Social Relation Recognition From Videos via Multi-Scale Spatial-Temporal Reasoning

Xinchen Liu, Wu Liu, Meng Zhang, Jingwen Chen, Lianli Gao, Chenggang Yan, Tao Mei

CVPR 2019 · Video › Action recognition · approach: Disentangled action recognition · 84 citations (OpenAlex)

Check 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
Combine PGCN with global TSN featuresPGCN · ViSRmAP: 44.73 -> 47.75Improved
Use pyramid temporal receptive fields instead of standard graph convolution (ablation)Triple Graphs reasoning · ViSRmAP: 43.46 -> 44.73Improved
Add InterG to IntraG (ablation)GCN · ViSRmAP: 41.02 -> 42.48Improved
Add POG to IntraG and InterG (ablation)GCN · ViSRmAP: 42.48 -> 43.46Improved
Add InterG to IntraG (ablation)PGCN · ViSRmAP: 43.07 -> 43.65Improved
Add POG to IntraG and InterG (ablation)PGCN · ViSRmAP: 43.65 -> 44.73Improved
Use global TSN features instead of graph reasoning aloneViSR relation recognition · ViSRmAP: 43.23; 44.73; 47.75Mixed

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