The authors build a data-generation engine, a seven-task grounding/referring benchmark, and a model that localizes and reads text in document images better than existing MLLMs on that benchmark.
Tabfact : A large-scale dataset for table-based fact verification
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
-
DOGR: Towards Versatile Visual Document Grounding and Referring
The authors build a data-generation engine, a seven-task grounding/referring benchmark, and a model that localizes and reads text in document images better than existing MLLMs on that benchmark.