InstructOCR conditions an autoregressive scene text spotter on human-language instruction templates and reports gains on Total-Text, ICDAR2015, ICDAR2013, TextVQA, and ST-VQA.
In 2017 14th IAPR international con- ference on document analysis and recognition (ICDAR), vol- ume 1, 1454–1459
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
InstructOCR: Instruction Boosting Scene Text Spotting
InstructOCR conditions an autoregressive scene text spotter on human-language instruction templates and reports gains on Total-Text, ICDAR2015, ICDAR2013, TextVQA, and ST-VQA.