Scholarlink

<p>Target tracking in dynamic environments faces challenges such as occlusions and appearance changes, especially long-time tracking. To address this, we propose GANMem-Siamese, integrating Generative Adversarial Networks (GANs) with Siamese networks, enhanced by a cycle memory mechanism and channel attention. The cycle memory mechanism selects key historical frames based on confidence scores, ensuring effective long-term representation. Within the selected frames, we introduce a channel attention-based feature fusion strategy, which adaptively integrates GAN-generated features with intermediate template features, enhancing feature diversity while maintaining temporal coherence. This approach mitigates feature drift and improves tracking robustness. Experimental results on benchmark datasets, including OTB100, VOT2016, and UAV123-20L, demonstrate that our method achieves state-of-the-art performance among unsupervised trackers, significantly improving long-term tracking stability and accuracy.</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

GANMem-Siamese: GAN-enhanced deep feature generation for robust object tracking with memory fusion

  • 期刊论文

  • 发表日期：

    2025年10月23日

查看全文
  • Yashuo Bai,
  • Li Wang,
  • Yingbo He,
  • Ya Zhou,
  • Meng Zheng,
  • Yiqian Huang,
  • Hongyu He,
  • Shuqi Liu,
  • Teng Luo,
  • Nan Wang,
  • Yong Song

摘要

Target tracking in dynamic environments faces challenges such as occlusions and appearance changes, especially long-time tracking. To address this, we propose GANMem-Siamese, integrating Generative Adversarial Networks (GANs) with Siamese networks, enhanced by a cycle memory mechanism and channel attention. The cycle memory mechanism selects key historical frames based on confidence scores, ensuring effective long-term representation. Within the selected frames, we introduce a channel attention-based feature fusion strategy, which adaptively integrates GAN-generated features with intermediate template features, enhancing feature diversity while maintaining temporal coherence. This approach mitigates feature drift and improves tracking robustness. Experimental results on benchmark datasets, including OTB100, VOT2016, and UAV123-20L, demonstrate that our method achieves state-of-the-art performance among unsupervised trackers, significantly improving long-term tracking stability and accuracy.