Login / Signup
DocXPand-25k: a large and diverse benchmark dataset for identity documents analysis.
Julien Lerouge
Guillaume Betmont
Thomas Bres
Evgeny Stepankevich
Alexis Bergès
Published in:
CoRR (2024)
Keyphrases
</>
benchmark datasets
statistical analysis
multimedia
wide variety
text analysis
neural network
information retrieval
learning algorithm
metadata
xml documents
co occurrence
information retrieval systems
query expansion
web documents
document analysis