SCOB: Universal Text Understanding via Character-wise Supervised Contrastive Learning with...

[PDF] arxiv.org

InstructOCR: Instruction Boosting Scene Text Spotting

C Duan, Q Jiang, P Fu, J Chen, S Li, Z Wang… - arXiv preprint arXiv …, 2024 - arxiv.org
In the field of scene text spotting, previous OCR methods primarily relied on image encoders
and pre-trained text information, but they often overlooked the advantages of incorporating …
相关文章 所有 2 个版本
[PDF] arxiv.org

TableVQA-Bench: A Visual Question Answering Benchmark on Multiple Table Domains

Y Kim, M Yim, KY Song - arXiv preprint arXiv:2404.19205, 2024 - arxiv.org
In this paper, we establish a benchmark for table visual question answering, referred to as
the TableVQA-Bench, derived from pre-existing table question-answering (QA) and table …
被引用次数：8 相关文章 所有 2 个版本