The paper introduces MegaHan97K, a 97,455-category Chinese character dataset and benchmark, and reports that existing OCR methods struggle with similar and zero-shot characters at this scale.
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
-
MegaHan97K: A Large-Scale Dataset for Mega-Category Chinese Character Recognition with over 97K Categories
The paper introduces MegaHan97K, a 97,455-category Chinese character dataset and benchmark, and reports that existing OCR methods struggle with similar and zero-shot characters at this scale.