Feb. 20, 2024, 5:47 a.m. | Longhuang Wu, Shangxuan Tian, Youxin Wang, Pengfei Xiong

cs.CV updates on arXiv.org arxiv.org

arXiv:2402.11540v1 Announce Type: new
Abstract: Existing methods for scene text detection can be divided into two paradigms: segmentation-based and anchor-based. While Segmentation-based methods are well-suited for irregular shapes, they struggle with compact or overlapping layouts. Conversely, anchor-based approaches excel for complex layouts but suffer from irregular shapes. To strengthen their merits and overcome their respective demerits, we propose a Complementary Proposal Network (CPN) that seamlessly and parallelly integrates semantic and geometric information for superior performance. The CPN comprises two efficient …

abstract anchor arxiv cs.cv detection excel network segmentation struggle text type

Lead Developer (AI)

@ Cere Network | San Francisco, US

Research Engineer

@ Allora Labs | Remote

Ecosystem Manager

@ Allora Labs | Remote

Founding AI Engineer, Agents

@ Occam AI | New York

AI Engineer Intern, Agents

@ Occam AI | US

AI Research Scientist

@ Vara | Berlin, Germany and Remote