TiCLS : 紧密耦合的语言文本定位器
TiCLS : Tightly Coupled Language Text Spotter
AI总结：
TiCLS通过整合字符级预训练语言模型的外部语言知识，实现了对模糊或碎片化文本的高效识别，验证了PLM引导的语言整合在场景文本定位中的有效性。
摘要：
场景文本定位旨在检测和识别现实世界图像中的文本，其中实例往往简短、碎片化或视觉模糊。现有方法主要依赖视觉线索并隐式捕捉局部字符依赖性，但忽略了外部语言知识的好处。先前尝试整合语言模型的要么在没有外部知识的情况下适应语言建模目标，要么应用预训练模型，这些模型与场景文本的词级粒度不匹配。我们提出了TiCLS，一种端到端的文本定位器，它明确整合了来自字符级预训练语言模型的外部语言知识。TiCLS引入了一个语言解码器，融合视觉和语言特征，但可以由预训练语言模型初始化，从而实现对模糊或碎片化文本的稳健识别。在ICDAR 2015和Total-Text上的实验表明，TiCLS实现了最先进的性能，验证了PLM引导的语言整合在场景文本定位中的有效性。
英文摘要：
Scene text spotting aims to detect and recognize text in real-world images, where instances are often short, fragmented, or visually ambiguous. Existing methods primarily rely on visual cues and implicitly capture local character dependencies, but they overlook the benefits of external linguistic knowledge. Prior attempts to integrate language models either adapt language modeling objectives without external knowledge or apply pretrained models that are misaligned with the word-level granularity of scene text. We propose TiCLS, an end-to-end text spotter that explicitly incorporates external linguistic knowledge from a character-level pretrained language model. TiCLS introduces a linguistic decoder that fuses visual and linguistic features, yet can be initialized by a pretrained language model, enabling robust recognition of ambiguous or fragmented text. Experiments on ICDAR 2015 and Total-Text demonstrate that TiCLS achieves state-of-the-art performance, validating the effectiveness of PLM-guided linguistic integration for scene text spotting.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
