AI Paper Atlas

Research map / Detection and segmentation / CNN features

TableSense: Spreadsheet Table Detection with Convolutional Neural Networks

Haoyu Dong, Shijie Liu, Shi Han, Zhouyu Fu, Dongmei Zhang

AAAI 2019 · Detection and segmentation › CNN features · approach: Domain-specific segmentation and detection · 50 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 Precise Bounding box Regression (PBR) module on top of BBR (ablation)TableSense · WebSheet400EoB-2 recall: 78.4 -> 91.3Improved
add PBR module on top of BBR (ablation)TableSense · WebSheet400EoB-2 precision: 68.1 -> 86.5Improved
use full 20-feature cell featurization instead of binary valued features only (ablation)TableSense · WebSheet400EoB-2 recall: 69.4 -> 91.3Improved
use full feature set instead of value string features only (ablation)TableSense · WebSheet400EoB-2 precision: 77.3 -> 86.5Improved
use full feature set instead of value string features only (ablation)TableSense · WebSheet400EoB-0 recall: 69.5 -> 80.8Improved
use TableSense (customized CNN with PBR) instead of Mask R-CNNspreadsheet table detection · WebSheet400EoB-0 precision: 40.2 -> 78.1Improved
use TableSense instead of Mask R-CNNspreadsheet table detection · WebSheet400EoB-2 recall: 75.5 -> 91.3Improved
use TableSense instead of region-growthspreadsheet table detection · WebSheet400EoB-2 precision: 52.2 -> 86.5Improved
use two-stage Mask R-CNN instead of one-stage YOLO-v3baseline detectors · WebSheet400EoB-2 recall: 63.4 -> 75.5Improved
use model from 7th active learning iteration instead of 3rd for uncertainty-based sheet selectionuncertainty metric · WebSheet400selection accuracy on sheets with errors: 81.9% -> 86.4%Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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