By feeding a montage of text crops with numbered boxes to a vision-language model, DLaVA localizes answers in documents and reports stronger accuracy and localization than the baselines it compares against.
Vision transformer for fast and efficient scene text recognition
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
DLaVA: Document Language and Vision Assistant for Answer Localization with Enhanced Interpretability and Trustworthiness
By feeding a montage of text crops with numbered boxes to a vision-language model, DLaVA localizes answers in documents and reports stronger accuracy and localization than the baselines it compares against.