AI Paper Atlas

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

Adaptive Text Recognition through Visual Matching

Chuhan Zhang, Ankush Gupta, Andrew Zisserman

ECCV 2020 · Vision-language and multimodal › Human and embodied modeling · approach: Language-grounded scene text and structure · 36 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 the decoder on top of the visual similarity map (ablation)visual matching model · FontSynth (train R)CER (%): 49.0 -> 9.4Improved
add position encoding to similarity disambiguation (ablation)visual matching model · FontSynth (train R)CER (%): 11.8 -> 9.4Improved
add self-attention to similarity disambiguation (ablation)visual matching model without position encoding · FontSynth (train R)CER (%): 23.9 -> 11.8Improved
add aggregator embedding (ablation)visual matching model · FontSynth (train R)CER (%): 22.9 -> 9.4Improved
add aggregator embedding (ablation)visual matching model · FontSynth (train R+B+L+I)CER (%): 8.5 -> 5.6Improved
add position encoding (ablation)visual matching model · FontSynth (train R+B+L+I)CER (%): 7.9 -> 5.6Improved
add Omniglot-Seq to training datavisual matching model · FontSynth testCER (%): 5.6 -> 3.5Improved
increase training fonts from 1 attribute (R) to 4 attributesvisual matching model · FontSynth testCER (%): 9.4 -> 5.6Improved
use test-font glyphs instead of cross-font exemplarsvisual matching model · FontSynth (train R)CER (%): 11.0 -> 9.4Improved
add 6-gram language modelvisual matching model · Google1000 EnglishCER (%): 3.1 -> 2.4Improved
add language model to Attn. Baek et al.Attn. Baek et al. · Google1000 EnglishCER (%): 5.4 -> 5.4No clear effect
add Italic split to training fonts for CTC Baek et al.CTC Baek et al. · FontSynthCER (%): 10.4 -> 10.4No 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