AI Paper Atlas

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

An End-to-End OCR Text Re-organization Sequence Learning for Rich-text Detail Image Comprehension

Liangcheng Li, Feiyu Gao, Jiajun Bu, Yongpan Wang, Zhi Yu, Qi Zheng

ECCV 2020 · Vision-language and multimodal › Human and embodied modeling · approach: Language-grounded scene text and structure · 24 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 Sinkhorn normalization to the pointer decoder (ablation)GCN-PN · DI test settotal order accuracy: 0.79 -> 0.86Improved
add Sinkhorn normalization to the pointer decoder (ablation)GCN-PN · DI test setBLEU-4: 0.71 -> 0.74Improved
add Sinkhorn normalization to the pointer decoder (ablation)GCN-PN · DI test setBLEU-2: 0.90 -> 0.92Improved
replace MLP pairwise order prediction with GCN encoder and pointer decoderPOS-MLP · DI test settotal order accuracy: 0.75 -> 0.79Improved
replace position-only heuristics with learned image-plus-geometry modelPOS-Hier · DI test settotal order accuracy: 0.70 -> 0.86Improved
replace greedy nearest-block ordering with GCN-PN-SinkhornPOS-Greedy · DI test settotal order accuracy: 0.41 -> 0.86Improved
POS-Hier versus GCN-PN on local versus longer sub-sequencesPOS-Hier · DI test setBLEU-2 vs BLEU-4: BLEU-2 0.89, BLEU-4 0.66Mixed

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