Video text spotting(VTS) is the task that requires simultaneously detecting, tracking and recognizing text in the video. Existing video text spotting methods typically develop sophisticated pipelines and multiple models, which is not friend for real-time applications. Here we propose a real-time end-to-end video text spotter with Contrastive Representation learning (CoText). Our contributions are three-fold: 1) CoText simultaneously address the three tasks (e.g., text detection, tracking, recognition) in a real-time end-to-end trainable framework. 2) With contrastive learning, CoText models long-range dependencies and learning temporal information across multiple frames. 3) A simple, lightweight architecture is designed for effective and accurate performance, including GPU-parallel detection post-processing, CTC-based recognition head with Masked RoI. Extensive experiments show the superiority of our method. Especially, CoText achieves an video text spotting IDF1 of 72.0% at 41.0 FPS on ICDAR2015video, with 10.5% and 32.0 FPS improvement the previous best method. The code can be found at github.com/weijiawu/CoText.

翻译：现有视频视频文本检测方法通常会开发复杂的管道和多种模型,对于实时应用程序来说并不友好。这里我们建议使用一个实时端到端视频文本检测器,同时进行对比性代表式学习(CoText),我们的贡献有三重:1) CoText同时在实时端到端可培训框架内处理这三项任务(如文本检测、跟踪、识别),2)通过对比性学习,COText模型的远程依赖性和跨多个框架学习时间信息。 3)为有效和准确的性能设计了一个简单、轻量级的结构,包括GPU-parllel检测后处理、基于CT的识别头和蒙面 RoI。广泛的实验显示了我们的方法的优势。特别是,CoText在ICDAR2015VE的41.0 FPS上,在41.0 FPS改进了10.5 % 和 32.0 FPS。代码可以在前最佳方法下找到。Cogithub.com/weiji。