AI Paper Atlas

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

Context Perception Parallel Decoder for Scene Text Recognition

Yongkun Du, Zhineng Chen, Caiyan Jia, Xiaoting Yin, Chenxia Li, Yuning Du, Yu–Gang Jiang

TPAMI 2025 · Vision-language and multimodal › Human and embodied modeling · approach: Language-grounded scene text and structure · 54 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 character ordering module without side loss (ablation)SVTR-B-CPPD · six English benchmarksavg accuracy: 92.01 -> 92.97Improved
add character counting module without side loss (ablation)SVTR-B-CPPD · six English benchmarksavg accuracy: 92.01 -> 92.49Improved
add CC side loss to CC module (ablation)SVTR-B-CPPD · six English benchmarksavg accuracy: 92.49 -> 93.35Improved
add CO side loss to CO module (ablation)SVTR-B-CPPD · six English benchmarksavg accuracy: 92.97 -> 93.29Improved
add both modules and both side losses (ablation)SVTR-B-CPPD · six English benchmarksavg accuracy: 92.01 -> 93.80Improved
use CC loss instead of ACE loss (ablation)SVTR-B-CPPD · six English benchmarksavg accuracy: 93.31 -> 93.80Improved
use binary CO loss instead of standard CE (ablation)SVTR-B-CPPD · six English benchmarksavg accuracy: 93.50 -> 93.80Improved
add pre-decoding side loss to PD decoder (ablation)SVTR-T-NRTR variants · six English benchmarksavg accuracy: 89.60 -> 90.43Improved
replace AR decoder with standard PD decoderSVTR-T-NRTR · six English benchmarksavg accuracy: 91.49 -> 89.60Hurt
train AR decoder with permuted sequences (ablation)SVTR-T-NRTR · six English benchmarksavg accuracy: 91.49 -> 91.78Improved
remove linguistic self-attention from AR decoder (AR-L) (ablation)SVTR-T-NRTR · six English benchmarksavg accuracy: 91.49 -> 91.13No clear effect
replace CNN encoder NRTR with SVTR-T encoderNRTR · six English benchmarksavg accuracy: 89.62 -> 91.49Improved

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