2 papers
cs.CV2025
OmniDocLayout: Towards Diverse Document Layout Generation via Coarse-to-Fine LLM Learning
Hengrui Kang, Zhuangcheng Gu, Zhiyuan Zhao +4
Document AI has advanced rapidly and is attracting increasing attention. Yet, while most efforts have focused on document layout analysis (DLA), its generative counterpart, layout…
cs.CV2024
Parrot Captions Teach CLIP to Spot Text
Yiqi Lin, Conghui He, Alex Jinpeng Wang +3
Despite CLIP being the foundation model in numerous vision-language applications, the CLIP suffers from a severe text spotting bias. Such bias causes CLIP models to `Parrot' the vi…