将图像文本检测器升级为视频文本定位器，仅用少量数据就大幅提效。
GoMatching++: Parameter- and Data-Efficient Arbitrary-Shaped Video Text Spotting and Benchmarking
- 冻结原有图像检测模型，加轻量追踪器实现视频适配。
- 在ICDAR15-video等数据集上刷新性能纪录，训练成本显著降低。
- 新增含30%弯曲文字的ArTVideo数据集，助力研究深入。
视频文本定位（VTS）在图像文本定位（ITS）基础上增加了文本跟踪，显著提升任务复杂度。尽管已有进展，现有方法性能仍远低于ITS。本文发现当前视频文本定位器的核心瓶颈在于识别能力受限，即使经过大量端到端训练亦然。为此，我们提出GoMatching++，一种参数与数据高效的方法，可将现成的图像文本定位器快速转化为视频专用模型。核心思路是冻结图像定位器，引入轻量可训练追踪器，以极小训练数据高效优化。方法包含两个关键组件：(1) 重评分机制以弥合图像与视频数据间的领域差距；(2) LST-Matcher，增强冻结模型处理视频文本的能力。我们探索多种LST-Matcher架构以兼顾参数与数据效率。结果表明，GoMatching++在ICDAR15-video、DSText和BOVText等挑战性基准上创下新纪录，同时大幅降低训练成本。为弥补现有数据集中弯曲文本缺失问题，我们构建了ArTVideo——一个含超30%弯曲文本并具精细标注的新基准，并提供全面统计分析与实验结果。我们相信，GoMatching++与ArTVideo将推动视频文本定位未来发展。源码、模型与数据集已公开于https://github.com/Hxyz-123/GoMatching。
原文摘要 · Abstract (English)
Video text spotting (VTS) extends image text spotting (ITS) by adding text tracking, significantly increasing task complexity. Despite progress in VTS, existing methods still fall short of the performance seen in ITS. This paper identifies a key limitation in current video text spotters: limited recognition capability, even after extensive end-to-end training. To address this, we propose GoMatching++, a parameter- and data-efficient method that transforms an off-the-shelf image text spotter into a video specialist. The core idea lies in freezing the image text spotter and introducing a lightweight, trainable tracker, which can be optimized efficiently with minimal training data. Our approach includes two key components: (1) a rescoring mechanism to bridge the domain gap between image and video data, and (2) the LST-Matcher, which enhances the frozen image text spotter's ability to handle video text. We explore various architectures for LST-Matcher to ensure efficiency in both parameters and training data. As a result, GoMatching++ sets new performance records on challenging benchmarks such as ICDAR15-video, DSText, and BOVText, while significantly reducing training costs. To address the lack of curved text datasets in VTS, we introduce ArTVideo, a new benchmark featuring over 30% curved text with detailed annotations. We also provide a comprehensive statistical analysis and experimental results for ArTVideo. We believe that GoMatching++ and the ArTVideo benchmark will drive future advancements in video text spotting. The source code, models and dataset are publicly available at https://github.com/Hxyz-123/GoMatching.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。