AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features

Byeonghu Na, Yoonsik Kim, Sungrae Park

ECCV 2022 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modal object re-identification · 98 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 multi-modal transformer feature enhancement to ABINet (ablation)ABINet · Total (six benchmarks)word accuracy (%): 92.6 -> 93.0Improved
add spatial encoding to semantic features (SES) (ablation)ABINet + multi-modal transformer · Total (six benchmarks)word accuracy (%): 93.0 -> 93.3Improved
add visual clue masking (ablation)ABINet + multi-modal transformer + SES · Total (six benchmarks)word accuracy (%): 93.3 -> 93.5Improved
add visual clue masking (ablation)ABINet + multi-modal transformer + SES · IC15 (1811)word accuracy (%): 86.9 -> 86.6Hurt
add visual clue masking (ablation)ABINet + multi-modal transformer + SES · CUTE80word accuracy (%): 89.9 -> 93.5Improved
update both visual and semantic features instead of only one modality (ablation)ABINet with SES · Total (six benchmarks)word accuracy (%): 92.8 -> 93.3Improved
enhance only semantic features (uni-modal FE) (ablation)ABINet with SES · Total (six benchmarks)word accuracy (%): 92.7 -> 92.8No clear effect
enhance only visual features (uni-modal FE) (ablation)ABINet with SES · Total (six benchmarks)word accuracy (%): 92.7 -> 92.8No clear effect
replace ABINet with MATRNABINet (reproduced) · CUTE80word accuracy (%): 89.0 -> 93.5Improved
replace ABINet with MATRNABINet (reproduced) · SVTword accuracy (%): 93.7 -> 95.0Improved
scale up ABINet visual model to match MATRN parameters (VM-Big) (ablation)ABINet · Total (six benchmarks)word accuracy (%): 92.6 -> 92.9Improved
scale up ABINet visual model to match MATRN speed (VM-Bigger) (ablation)ABINet · Total (six benchmarks)word accuracy (%): 92.6 -> 93.1Improved

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