AI Paper Atlas

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

Focusing Attention: Towards Accurate Text Recognition in Natural Images

Zhanzhan Cheng, Fan Bai, Yunlu Xu, Gang Zheng, Shiliang Pu, Shuigeng Zhou

ICCV 2017 · Vision-language and multimodal › Human and embodied modeling · approach: Language-grounded scene text and structure · 542 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 focusing network (FN) to the attention network (ablation)AN with ResNet encoder · IIIT5k (lexicon-free)accuracy (%): 83.7 -> 87.4Improved
add the focusing network (FN) to the attention network (ablation)AN with ResNet encoder · IC15 (lexicon-free)accuracy (%): 63.3 -> 70.6Improved
add the focusing network (FN) to the attention network (ablation)AN with ResNet encoder · IC13 (lexicon-free)accuracy (%): 89.4 -> 93.3Improved
add the focusing network (FN) to the attention network (ablation)AN with ResNet encoder · IIIT5k (lexicon-free)total normalized edit distance: 188.9 -> 145.2Improved
add the focusing network (FN) to the attention network (ablation)AN with Shi et al. encoder · IIIT5k (lexicon-free)accuracy (%): 79.5 -> 81.7Improved
add the focusing network (FN) to the attention network (ablation)AN with Shi et al. encoder · IC15 (lexicon-free)accuracy (%): 58.2 -> 61.0Improved
add the focusing network (FN) to the attention network (ablation)AN with Shi et al. encoder · IIIT5k (lexicon-free)total normalized edit distance: 248.0 -> 213.4Improved
replace the Shi et al. encoder with the 32-layer ResNet-based encoder (ablation)AN · IIIT5k (lexicon-free)accuracy (%): 79.5 -> 83.7Improved
raise lambda from 0.001 to 0.01 (ablation)FAN · IC13 (lexicon-free)accuracy (%): 92.7 -> 93.3Improved
raise lambda from 0.01 to 0.1 (ablation)FAN · IC13 (lexicon-free)accuracy (%): 93.3 -> 92.1Hurt
raise lambda from 0.01 to 0.1 (ablation)FAN · IC15 (lexicon-free)accuracy (%): 70.6 -> 70.7No clear effect
add pixel-level character labels for 1% of training samples (ablation)FAN · IC15 (lexicon-free)accuracy (%): 63.3 -> 70.0Improved

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