Scholarlink

<p>This paper introduces a novel Mask Transformer framework for unsupervised video object segmentation, focusing on enhancing segmentation accuracy and efficiency. Our approach leverages the power of transformers to capture long-range dependencies and spatial context, enabling precise segmentation of objects in videos without requiring manual annotations during training. By fusing appearance and motion features through a unique combination of pixel-level feature representation and object-level query processing, our model achieves state-of-the-art performance on benchmark datasets while maintaining a substantial training speed improvement. The proposed framework offers a significant step forward in the field, demonstrating the effectiveness of mask classification for UVOS tasks. We open-source our code and datasets to facilitate reproducibility and encourage further research in this area at <a href="https://github.com/Qudk23/MaskVOS?tab=readme-ov-file">https://github.com/Qudk23/MaskVOS?tab=readme-ov-file</a>.</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

Unsupervised video object segmentation with mask transformer: boosting accuracy and efficiency through feature fusion

  • 期刊论文

  • 发表日期：

    2025年2月7日

查看全文
  • Daikun Qu,
  • Hongwei Zhao,
  • Mingzhu Zhou

摘要

This paper introduces a novel Mask Transformer framework for unsupervised video object segmentation, focusing on enhancing segmentation accuracy and efficiency. Our approach leverages the power of transformers to capture long-range dependencies and spatial context, enabling precise segmentation of objects in videos without requiring manual annotations during training. By fusing appearance and motion features through a unique combination of pixel-level feature representation and object-level query processing, our model achieves state-of-the-art performance on benchmark datasets while maintaining a substantial training speed improvement. The proposed framework offers a significant step forward in the field, demonstrating the effectiveness of mask classification for UVOS tasks. We open-source our code and datasets to facilitate reproducibility and encourage further research in this area at https://github.com/Qudk23/MaskVOS?tab=readme-ov-file.