AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Storytelling from an Image Stream Using Scene Graphs

Ruize Wang, Zhongyu Wei, Piji Li, Qi Zhang, Xuanjing Huang

AAAI 2020 · Graph learning › Knowledge and temporal graphs · approach: Scene graph generation · 60 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 GCN over scene graphs (within-image relations) (ablation)SGVST · VISTMETEOR: 35.2 -> 35.8 (w/o GCN vs full)Improved
Add GCN to model without GCN or TCN (keeping TCN off) (ablation)SGVST w/o TCN · VISTMETEOR: 35.1 -> 35.4Improved
Add TCN (cross-image relations) to model without GCN (ablation)SGVST w/o GCN · VISTMETEOR: 35.1 -> 35.2Improved
Add TCN to GCN model (ablation)SGVST · VISTMETEOR: 35.4 -> 35.8Improved
Replace single-layer GRU decoder with hierarchical two-layer attention decoder (ablation)SGVST · VISTMETEOR: 35.5 -> 35.8Improved
Add high-level biGRU encoder fused with scene graph features (ablation)SGVST · VISTMETEOR: 35.6 -> 35.8Improved
SGVST vs RL-optimized HSRL on CIDEr-DSGVST · VISTCIDEr-D: 9.8 vs 10.7 (HSRL)Hurt

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