研究人员开发了TraRA，一种用于视频文本识别的新方法，旨在提高城市监控场景下的准确性。与之前独立分析帧的方法不同，TraRA在整个轨迹中聚合文本识别。该方法使用时间聚类来分组连贯的文本实例，并使用增强了低秩自适应（Low-Rank Adaptation）的视觉语言模型来融合视觉和语言信息。TraRA在多个基准测试中都表现出改进的性能，即使在运动模糊和遮挡等挑战性条件下也是如此。 AI
影响 提高了现实世界视频监控中AI驱动的文本识别的准确性。
排序理由 arXiv上发布了关于新方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.07161v1 Announce Type: new Abstract: Video Text Spotting (VTS) is essential for urban surveillance and intelligent transportation systems, enabling automated reading of street signs, vehicle markings, and scene text in video streams. However, reliable recognition remai…
Video Text Spotting (VTS) is essential for urban surveillance and intelligent transportation systems, enabling automated reading of street signs, vehicle markings, and scene text in video streams. However, reliable recognition remains challenging due to dynamic video factors comm…