AI Paper Atlas

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

Image-based table recognition: data, model, and evaluation

Xu Zhong, Elaheh ShafieiBavani, Antonio Jimeno Yepes

ECCV 2020 · Vision-language and multimodal › Human and embodied modeling · approach: Language-grounded scene text and structure · 332 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
use dual decoders (structure + cell) instead of a single decoder (EDD vs WYGIWYS)EDD · PubTabNet test (all tables)average TEDS (%): 78.6 -> 88.3Improved
use dual decoders on complex tablesEDD · PubTabNet test (complex tables)average TEDS (%): 75.5 -> 85.4Improved
use dual decoders on simple tablesEDD · PubTabNet test (simple tables)average TEDS (%): 81.7 -> 91.2Improved
use image input instead of PDF input for Acrobat ProAcrobat Pro · PubTabNet test (all tables)average TEDS (%): 65.3 -> 53.7Hurt
increase encoder feature-map resolution (last CNN layer stride 1) (ablation)EDD · PubTabNet validationaverage TEDS (%)Improved
use independent last CNN layers for structure and cell decoders (ablation)EDD · PubTabNet validationaverage TEDS (%)Improved
EDD instead of TIES on synthetic category C3EDD · Synthetic table dataset (category C3)exact match (%): 52.9 -> 97.2Improved
EDD instead of TIES on synthetic category C4EDD · Synthetic table dataset (category C4)exact match (%): 68.5 -> 98.0Improved
EDD instead of TIES on synthetic category C1EDD · Synthetic table dataset (category C1)exact match (%): 96.9 -> 99.7Improved
shift 90% of first-row cells (TEDS vs adjacency F1 sensitivity)TEDS metric · PubTabNet validation perturbationTEDS: 60% drop on TEDS; adjacency F1 nearly 80%Hurt
increase character perturbation level from 10% to 90%TEDS metric · PubTabNet validation perturbationTEDS: 90% -> 40%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