AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Chinese Text Recognition with A Pre-Trained CLIP-Like Model Through Image-IDS Aligning

Haiyang Yu, Xiaocong Wang, Bin Li, Xiangyang Xue

ICCV 2023 · Vision-language and multimodal › CLIP and zero-shot · approach: Attribute-based zero-shot learning · 61 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 matching head with canonical representations instead of fully connected prediction head (ablation)TransOCR-style CTR model · CTR benchmark HandwritingLACC: 53.00% -> 58.54%Improved
add matching head (ablation)TransOCR-style CTR model · CTR benchmark SceneLACC: 71.33% -> 70.17%Hurt
add regularization term to L_ctr (ablation)CTR model with matching head · CTR benchmark HandwritingLACC: 58.54% -> 60.30%Improved
add image-image contrastive loss L_I (lambda=1 vs 0) (ablation)CCR-CLIP · CTWCACC: 83.29% -> 85.78%Improved
use radical-level instead of stroke-level text representation (ablation)CCR-CLIP text encoder · ICDAR2013CACC: 92.74% -> 97.18%Improved
use radical-level instead of character-level representation (ablation)CCR-CLIP text encoder · CTWCACC: 82.73% -> 85.78%Improved
choose regularization weight beta=0.001 versus 0 or larger (ablation)CTR model · CTR benchmark HandwritingLACC: 59.54% -> 60.30%Improved
increase beta from 0.001 to 1 (ablation)CTR model · CTR benchmark HandwritingLACC: 60.30% -> 58.76%Hurt
image-IDS matching framework for zero-shot characters in text linesCTR model vs TransOCR · CTR benchmark zero-shot characterscharacter accuracy: 51.4% average vs TransOCR cannot recognize themImproved
image-IDS matching for few-shot charactersCTR model vs TransOCR · CTR benchmark few-shot characterscharacter accuracy: +10.6% averageImproved
image-IDS pre-training vs CUE under no printed imagesCCR-CLIP · HWDB character zero-shotCACC: +28.37% averageImproved
apply method to scene text with vertical textOurs · CTR benchmark SceneLACC: 71.33 -> 71.31No clear effect

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