Scholarlink

<p>A novel half-To-All multiple object tracking and recognition (HTAMotr) approach is proposed to address the challenges posed by incomplete annotations in video text tracking. Three key strategies were introduced: rotated queries to improve anchor alignment with text regions, the Proposal-For-Groundtruth Strong Correlation (PForG) strategy to mitigate the negative effects of incomplete annotations, and an overlapping anchor filter to resolve ID switching issues. Experiments conducted on the DSText dataset and ICDAR2015 Video dataset demonstrate the effectiveness of HTAMotr, achieving state-of-the-art performance without requiring additional pre-training data or extensive epochs. By addressing the limitations of traditional MOTR paradigms, this work contributes to advancing video text tracking techniques and facilitating the development of more robust and efficient algorithms. The code and datasets are available at <a href="https://github.com/Paige-Norton/HTAMotr">https://github.com/Paige-Norton/HTAMotr</a>, complete with usage guides to facilitate the reproduction of experimental results.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A novel Half-To-All MOTR approach for robust video text tracking with incomplete annotations

  • 期刊论文

  • 发表日期：

    2025年4月7日

查看全文
  • Peiqi Xie,
  • Minglong Xue,
  • Chengyun Song

摘要

A novel half-To-All multiple object tracking and recognition (HTAMotr) approach is proposed to address the challenges posed by incomplete annotations in video text tracking. Three key strategies were introduced: rotated queries to improve anchor alignment with text regions, the Proposal-For-Groundtruth Strong Correlation (PForG) strategy to mitigate the negative effects of incomplete annotations, and an overlapping anchor filter to resolve ID switching issues. Experiments conducted on the DSText dataset and ICDAR2015 Video dataset demonstrate the effectiveness of HTAMotr, achieving state-of-the-art performance without requiring additional pre-training data or extensive epochs. By addressing the limitations of traditional MOTR paradigms, this work contributes to advancing video text tracking techniques and facilitating the development of more robust and efficient algorithms. The code and datasets are available at https://github.com/Paige-Norton/HTAMotr, complete with usage guides to facilitate the reproduction of experimental results.