Scholarlink

We present an effective approach for adapting the Segment Anything Model 2 (SAM2) to the Visual Object Tracking (VOT) task. Our method leverages the powerful pre-trained capabilities of SAM2 and incorporates several key techniques to enhance its performance in VOT applications. By combining SAM2 with our proposed optimizations, we achieved a first place AUC score of 89.4 on the 2024 ICPR Multi-modal Object Tracking challenge, demonstrating the effectiveness of our approach. This paper details our methodology, the specific enhancements made to SAM2, and a comprehensive analysis of our results in the context of VOT solutions along with the multi-modality aspect of the dataset.

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

Adapting SAM 2 for Visual Object Tracking: 1st Place Solution for MMVPR Challenge Multi-modal Tracking

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Cheng-Yen Yang,
  • Hsiang-Wei Huang,
  • Pyong-Kun Kim,
  • Chien-Kai Kuo,
  • Jui-Wei Chang,
  • Kwang-Ju Kim,
  • Chung-I Huang,
  • Jenq-Neng Hwang

摘要

We present an effective approach for adapting the Segment Anything Model 2 (SAM2) to the Visual Object Tracking (VOT) task. Our method leverages the powerful pre-trained capabilities of SAM2 and incorporates several key techniques to enhance its performance in VOT applications. By combining SAM2 with our proposed optimizations, we achieved a first place AUC score of 89.4 on the 2024 ICPR Multi-modal Object Tracking challenge, demonstrating the effectiveness of our approach. This paper details our methodology, the specific enhancements made to SAM2, and a comprehensive analysis of our results in the context of VOT solutions along with the multi-modality aspect of the dataset.