Conceptio
›
Archive
›
arXiv (All)
arXiv (All)
open access
Synth-JDoc: Synthesizing a Japanese Document Image Dataset for OCR with Diverse Layouts and Embedded Images
Sasagawa, Keito et al.
arXiv (All) · Papers · License: Open Access
Open Source ↗
Direct PDF ↓
computation-and-language
computer-vision-and-pattern-recognition
computer vision and pattern recognition, computation and language
This document is indexed with metadata only — full text is not available in the archive for this record.
Open the official source ↗
Related documents
FORGE: Form-Optimal Routing of Grounded Evidence for Frozen LLM Agents
#1119431
SyncRA: Learning Temporal Correspondence in Omni-Modal Models
#1119436
When Harness Beats Scale, and When Reading Beats Both
#1119439
Rate-Distortion Adaptive Primitive Selection for Omnidirectional Gaussian Splatting
#1119440
Record
· ID 784998
Retrieved via
Conceptio
— every document is proof-bundled with source, license, and retrieval metadata.