AI Paper Atlas

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

Image-to-Character-to-Word Transformers for Accurate Scene Text Recognition

Chuhui Xue, Jiaxing Huang, Wenqing Zhang, Shijian Lu, Changhu Wang, Song Bai

TPAMI 2023 · Vision-language and multimodal › Human and embodied modeling · approach: Language-grounded scene text and structure · 37 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 C2W module on top of I2C (ablation)I2C · CUTE (synthetic)word accuracy: 81.2 -> 93.1Improved
add C2W module on top of I2C (ablation)I2C · Total-Text (synthetic)word accuracy: 71.0 -> 79.8Improved
add C2W module on top of I2C (ablation)I2C · IC15 (synthetic)word accuracy: 75.2 -> 82.8Improved
add C2W module on top of I2C (ablation)I2C · IIIT5K (synthetic)word accuracy: 89.2 -> 94.3Improved
predict relative character positions (I2C) instead of DETR 2D coordinates (ablation)DETR · IC15word accuracy: 60.1 -> 75.2Improved
add C2W on top of I2C to beat DETR (ablation)DETR · IC13word accuracy: 76.7 -> 95.0Improved
two-stage I2C2W instead of one-stage I2W (ablation)I2W · CUTEword accuracy: 87.8 -> 93.1Improved
two-stage I2C2W instead of one-stage I2W (ablation)I2W · IC15word accuracy: 79.8 -> 82.8Improved
fine-tune with real imagesI2C2W · IC15word accuracy: 82.8 -> 85.3Improved
fine-tune with real imagesI2C2W · IIIT5Kword accuracy: 94.3 -> 94.5No clear effect
reduce N from 25 to 10 character candidates (ablation)I2C2W · Total-Textword accuracy: 79.8 -> 76.7Hurt
increase N from 25 to 100 character candidates (ablation)I2C2W · IC13word accuracy: 95.0 -> 92.8Hurt

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