AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Exploring Visual Relationship for Image Captioning

Ting Yao, Yingwei Pan, Yehao Li, Tao Mei

ECCV 2018 · Graph learning › Knowledge and temporal graphs · approach: Graph reasoning for visual recognition · 971 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 semantic and spatial relation graphs with GCN (full GCN-LSTM) over Up-DownUp-Down region captioner · COCO Karpathy test (cross-entropy)CIDEr-D: 113.5 -> 117.1Improved
add semantic and spatial relation graphs with GCN (full GCN-LSTM) over Up-DownUp-Down region captioner · COCO Karpathy test (CIDEr-D optimization)CIDEr-D: 120.1 -> 128.7Improved
add semantic-graph GCN only over Up-DownUp-Down region captioner · COCO Karpathy test (cross-entropy)CIDEr-D: 113.5 -> 116.3Improved
add spatial-graph GCN only over Up-DownUp-Down region captioner · COCO Karpathy test (cross-entropy)CIDEr-D: 113.5 -> 115.6Improved
add spatial graph to semantic-graph model (fuse both) (ablation)GCN-LSTM_sem · COCO Karpathy test (cross-entropy)CIDEr-D: 116.3 -> 117.1Improved
add semantic graph to spatial-graph model (fuse both) (ablation)GCN-LSTM_spa · COCO Karpathy test (cross-entropy)CIDEr-D: 115.6 -> 117.1Improved
use late fusion of decoders instead of early fusion before attention (ablation)GCN-LSTM · COCO Karpathy test (cross-entropy)CIDEr-D: 116.4 -> 117.1Improved
use late fusion of decoders instead of early fusion after attention (ablation)GCN-LSTM · COCO Karpathy test (cross-entropy)CIDEr-D: 116.6 -> 117.1Improved
tune tradeoff alpha between semantic and spatial decoders (0 to 1) (ablation)GCN-LSTM · COCO Karpathy test (cross-entropy)BLEU-4, METEOR, CIDEr-D: best at alpha about 0.7Improved
replace Up-Down with GCN-LSTM on online server c5Up-Down region captioner · COCO online test server (c5)CIDEr-D: 117.9 -> 125.3Improved
replace Up-Down with GCN-LSTM in human Turing testUp-Down region captioner · COCO human studyM2 Turing test pass rate: 78.5 -> 82.1Improved

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