AI Paper Atlas

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

Scene Text Retrieval via Joint Text Detection and Similarity Learning

Hao Wang, Xiang Bai, Mingkun Yang, Shenggao Zhu, Jing Wang, Wenyu Liu

CVPR 2021 · Vision-language and multimodal › Human and embodied modeling · approach: Composed and text-based image retrieval · 47 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
Jointly optimize text detection and cross-modal similarity learning instead of separating the stages (ablation)Scene text retrieval · SVT, STR, CTRmAP: 82.88 -> 89.38; 70.83 -> 77.09; 61.16 -> 66.45Improved
Add word augmentation strategy (ablation)Baseline similarity-learning method · SVT, STR, CTRmAP: 88.05 -> 88.68; 73.70 -> 75.76; 62.97 -> 64.59Improved
Add CTC loss to align visual and textual features (ablation)Baseline similarity-learning method · SVT, STR, CTRmAP: 88.05 -> 88.62; 73.70 -> 75.54; 62.97 -> 64.08Improved
Add both word augmentation strategy and CTC loss (ablation)Baseline similarity-learning method · SVT, STR, CTRmAP: 88.05 -> 89.38; 73.70 -> 77.09; 62.97 -> 66.45Improved
Add auxiliary similarity training on proposal-proposal and query-query pairs (ablation)Scene text retrieval model · SVT, STR, CTRmAP: 85.28 -> 87.78; 66.50 -> 70.18; 51.79 -> 53.90Improved
Learn cross-modal similarity instead of predicting PHOC vectors (ablation)Same text detection network · SVT, STR, CTRmAP: 80.87 -> 87.78; 60.00 -> 70.18; 42.89 -> 53.90Improved
Use multi-scale testingOurs · SVT, STR, CTRmAP: +2.31%; +3.07%; +3.42%Improved
Use the proposed retrieval method rather than the strongest prior method in the comparisonScene text retrieval · SVT, STR, CTRmAP: 85.74 -> 89.38; 74.48 -> 77.09; 55.54 -> 66.45Improved
Apply the method to Chinese retrieval with 3755 character categories rather than 1019Ours on CSVTR · CSVTRmAP: 60.23 -> 50.12Hurt

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