A new document understanding task and dataset (GraphDoc) that labels how text blocks, tables, and figures relate in space and in logic, with a baseline model reaching 57.6% graph mAP.
Image captioning with scene-graph based semantic concepts
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
-
Graph-based Document Structure Analysis
A new document understanding task and dataset (GraphDoc) that labels how text blocks, tables, and figures relate in space and in logic, with a baseline model reaching 57.6% graph mAP.