AI Paper Atlas

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

LISTER: Neighbor Decoding for Length-Insensitive Scene Text Recognition

Changxu Cheng, Peng Wang, Cheng Da, Qi Zheng, Cong Yao

ICCV 2023 · Vision-language and multimodal › Human and embodied modeling · approach: Language-grounded scene text and structure · 33 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
replace the neighbor decoder with a parallel attention decoder (ablation)LISTER-T* · TULaccuracy (%): 76.8 -> 61.6Hurt
use neighbor decoder instead of serial attention decoder (ablation)LISTER-T* · TULaccuracy (%): 66.5 -> 76.8Improved
use neighbor decoder instead of CTC (ablation)LISTER-T* · common benchmarksaverage accuracy (%): 90.2 -> 91.7Improved
add attention sharpening at inference (ablation)Neighbor Decoder · TUL unseen lengths (trained on lengths <=16)accuracy (%): 47.1 -> 58.4Improved
add Feature Enhancement Module on top of attention sharpening (ablation)Neighbor Decoder · TUL unseen lengths (trained on lengths <=16)accuracy (%): 58.4 -> 61.4Improved
add both Transformer layer and convolution block in FEM (ablation)LISTER-T · common benchmarksaverage accuracy (%): 92.0 / 92.2 -> 92.8Improved
increase FEM iterations from 1 to 2 (2 Transformer, 2 conv) (ablation)LISTER-T · TULaccuracy (%): 77.2 -> 77.8Improved
place Transformer layers at the end of the feature extractor instead of using FEM (ablation)LISTER-T · common benchmarksaverage accuracy (%): 92.8 -> 92.0Hurt
pad images instead of resizing to fixed width (ablation)Neighbor Decoder · TULaccuracy (%): 65.9 -> 76.8Improved
scale model from LISTER-T* to LISTER-BLISTER · TULaccuracy (%): 76.8 -> 79.2Improved
use a feature map of height 4 instead of 1 (ablation)LISTER-B · ArT (synthetic training)average accuracy (%): 56.2 -> 57.4Improved
add 3-scale test-time ensembleLISTER-B · common benchmarksaverage accuracy (%): 93.3 -> 93.5Improved

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