提出轻量级视频隐匿物体检测方法，通过时空邻域建模提升检测精度。
Green Video Camouflaged Object Detection
- 基于绿色图像隐匿检测框架，引入长短时邻域捕捉时空上下文
- 在多个基准上达到与顶尖方法相当的检测性能
- 适合资源受限场景下的高效隐匿物体检测应用
隐匿物体检测（COD）旨在识别嵌入环境背景中外观高度相似的隐藏物体。传统视频隐匿检测（VCOD）方法通常显式提取运动线索或使用复杂的深度网络处理时序信息，存在计算复杂度高、性能不稳定等问题。本文提出一种轻量级视频隐匿检测方法GreenVCOD，基于绿色图像隐匿检测（GreenICOD）框架，利用长短期时序邻域（TN）捕获联合空间-时序上下文信息以优化决策。实验结果表明，GreenVCOD在多个基准上表现优异，性能媲美当前最优的VCOD方法。
原文摘要 · Abstract (English)
Camouflaged object detection (COD) aims to distinguish hidden objects embedded in an environment highly similar to the object. Conventional video-based COD (VCOD) methods explicitly extract motion cues or employ complex deep learning networks to handle the temporal information, which is limited by high complexity and unstable performance. In this work, we propose a green VCOD method named GreenVCOD. Built upon a green ICOD method, GreenVCOD uses long- and short-term temporal neighborhoods (TN) to capture joint spatial/temporal context information for decision refinement. Experimental results show that GreenVCOD offers competitive performance compared to state-of-the-art VCOD benchmarks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。