AI Paper Atlas

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

TAP: Text-Aware Pre-Training for Text-VQA and Text-Caption

Zhengyuan Yang, Yijuan Lu, Jianfeng Wang, Xi Yin, Dinei Florencio, Lijuan Wang, Cha Zhang, Lei Zhang, Jiebo Luo

CVPR 2021 · Vision-language and multimodal › Human and embodied modeling · approach: Concept-guided image captioning · 107 citations (OpenAlex)

Check 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
Apply scene-text-aware pre-training with MLM, ITM, and RPPM4C† · TextVQA valaccuracy: 44.50% to 49.91%Improved
Add large-scale OCR-CC pre-training and other extra dataTAP · TextVQA valaccuracy: 49.91% to 54.71%Improved
Apply TAP pre-trainingM4C† · TextCaps valCIDEr: 99.89 to 105.05Improved
Add scene-text words to MLM and ITM input (ablation)MLM+ITM pre-training · TextVQA valaccuracy: 44.63 to 49.01Improved
Add MLM and ITM pre-training without scene-text words (ablation)M4C · TextVQA valaccuracy: 44.50 to 44.63No clear effect
Add detected scene-text words without pre-training (ablation)M4C · TextVQA valaccuracy: 44.48 to 44.50No clear effect
Add RPP with a single spatial relation class (ablation)M4C · TextVQA valaccuracy: 44.50% to 46.42%Improved
Add RPP to MLM and ITM (ablation)MLM+ITM · TextVQA valaccuracy: 49.01% to 49.91%Improved
Extend RPP from one spatial relation to 12 classes (ablation)TAP · TextVQA valaccuracy: 49.91% to 50.17%Improved
Add ST-VQA pre-training data (ablation)TAP · TextVQAaccuracy: 49.91% to 50.57%Improved
Add TextCaps pre-training data (ablation)TAP with ST-VQA data · TextVQAaccuracy: 50.57% to 51.86%Improved
Add OCR-CC as the pre-training data source (ablation)TAP · TextVQAaccuracy: 52.10%Improved

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