Direct line-level recognition with PARSeq (trained on synthetic line images) beats word-level pipelines by 5.4% FCA and runs 4x faster on the authors' 251-page English dataset.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Why Stop at Words? Unveiling the Bigger Picture through Line-Level OCR
Direct line-level recognition with PARSeq (trained on synthetic line images) beats word-level pipelines by 5.4% FCA and runs 4x faster on the authors' 251-page English dataset.