AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Unpaired Image Captioning via Scene Graph Alignments

Jiuxiang Gu, Shafiq Joty, Jianfei Cai, Handong Zhao, Xu Yang, Gang Wang

ICCV 2019 · Graph learning › Knowledge and temporal graphs · approach: Scene graph generation · 189 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
replace average pooling with attention over features (ablation)Graph-Enc-Dec · MSCOCO test (sentence scene graph input)CIDEr: 129.4 -> 151.4Improved
use independent attention for each feature set instead of one shared attention (ablation)Graph-Enc-Dec · MSCOCO test (sentence scene graph input)CIDEr: 151.4 -> 168.8Improved
use independent attention instead of average pooling on image scene graphs (no GAN) (ablation)Graph-Enc-Dec · MSCOCO test (unpaired, no GAN)CIDEr: 41.4 -> 48.5Improved
independent attention changes BLEU-4 (no GAN) (ablation)Graph-Enc-Dec · MSCOCO test (unpaired, no GAN)BLEU-4: 20.3 -> 11.9Mixed
add CycleGAN feature alignment (GP loss, 64-d discriminator) to Graph-Enc-Dec (Att) (ablation)Graph-Align · MSCOCO test (unpaired)CIDEr: 48.5 -> 69.5Improved
use gradient penalty loss instead of BCE (64-d discriminator) (ablation)Graph-Align · MSCOCO test (unpaired)CIDEr: 65.5 -> 69.5Improved
use gradient penalty loss instead of MSE (64-d discriminator) (ablation)Graph-Align · MSCOCO test (unpaired)CIDEr: 63.8 -> 69.5Improved
use 64-d discriminator output instead of 1-d with GP loss (ablation)Graph-Align · MSCOCO test (unpaired)CIDEr: 61.1 -> 69.5Improved
use 64-d discriminator output instead of 1-d with MSE loss (ablation)Graph-Align · MSCOCO test (unpaired)CIDEr: 46.7 -> 63.8Improved
use 64-d discriminator output instead of 1-d with BCE loss (ablation)Graph-Align · MSCOCO test (unpaired)CIDEr: 65.2 -> 65.5No clear effect
use separate mapping per feature type instead of one shared GAN (ablation)Graph-Align · MSCOCO test (unpaired)CIDEr: 60.1 -> 69.5Improved
use separate mapping per feature type instead of concatenated single GAN (ablation)Graph-Align · MSCOCO test (unpaired)CIDEr: 61.2 -> 69.5Improved

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