AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Graph Optimal Transport for Cross-Domain Alignment

Liqun Chen, Zhe Gan, Yu Cheng, Linjie Li, Lawrence Carin, Jingjing Liu

ICML 2020 · Vision-language and multimodal › Human and embodied modeling · approach: Scene graph generation · 22 citations (OpenAlex)

Read the paper

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 GOT to SCANSCAN image-text retrieval · Flickr30K and COCORsum: 452.2 -> 474.8; 384.8 -> 403.9Improved
Combine WD and GWD in GOT rather than using either distance alone (ablation)SCAN image-text retrieval · Flickr30K and COCORsum: 472.3 -> 474.8; 402.6 -> 403.9Improved
Add GOT to BANBAN · VQA 2.0 validationaccuracy: 66.00 -> 66.44Improved
Add GOT to MLECOCO image captioning · COCOCIDEr: 106.3 -> 109.2Improved
Use GWD alone instead of the Transformer baseline (ablation)Transformer machine translation · EN-VI uncasedBLEU: 29.25 ± 0.18 -> 28.65 ± 0.14Hurt
Add GOT to TransformerTransformer machine translation · EN-VI uncasedBLEU: 29.25 ± 0.18 -> 29.92 ± 0.11Improved
Add GOT to TransformerTransformer machine translation · EN-VI cased; EN-DE uncased and casedBLEU: 28.46 ± 0.17 -> 29.09 ± 0.18; 25.60 ± 0.07 -> 26.05 ± 0.17; 25.12 ± 0.12 -> 25.54 ± 0.15Improved
Add GOT to LSTMLSTM abstractive summarization · English GigawordsROUGE-1: 36.11 -> 37.10Improved
Add GOT to LSTMLSTM abstractive summarization · English GigawordsROUGE-2: 16.39 -> 17.61Improved
Add GOT to LSTMLSTM abstractive summarization · English GigawordsROUGE-L: 32.32 -> 33.70Improved
Use one shared transport plan for WD and GWD rather than separate plans (ablation)GOT machine translation · EN-VI uncased and EN-DE uncasedBLEU: 29.77 ± 0.12 -> 29.92 ± 0.11; 25.89 ± 0.17 -> 26.05 ± 0.18Improved
Set λ to 0.8 instead of 0 (ablation)GOT machine translation · EN-VIBLEU: 28.65 -> 29.92Improved

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