论文标题
苏格兰和苏打水：变压器视频阴影检测框架
SCOTCH and SODA: A Transformer Video Shadow Detection Framework
论文作者
论文摘要
由于框架之间的阴影变形很大，因此很难检测到视频中的阴影。在这项工作中，我们认为在设计视频阴影检测方法时，考虑阴影变形是必不可少的。为此，我们介绍了阴影变形注意轨迹（SODA），这是一种新型的视频自我发场模块，专门设计用于处理视频中的大阴影变形。此外，我们提出了一种新的影子对比学习机制（Scotch），旨在指导网络从不同视频的巨大积极影子对学习统一的影子表示。我们从经验上证明了两项贡献在消融研究中的有效性。此外，我们表明苏格兰威士忌和苏打水大大优于现有的视频阴影检测技术。代码可在项目页面上找到：https：//lihaoliu-cambridge.github.io/scotch_and_soda/
Shadows in videos are difficult to detect because of the large shadow deformation between frames. In this work, we argue that accounting for shadow deformation is essential when designing a video shadow detection method. To this end, we introduce the shadow deformation attention trajectory (SODA), a new type of video self-attention module, specially designed to handle the large shadow deformations in videos. Moreover, we present a new shadow contrastive learning mechanism (SCOTCH) which aims at guiding the network to learn a unified shadow representation from massive positive shadow pairs across different videos. We demonstrate empirically the effectiveness of our two contributions in an ablation study. Furthermore, we show that SCOTCH and SODA significantly outperforms existing techniques for video shadow detection. Code is available at the project page: https://lihaoliu-cambridge.github.io/scotch_and_soda/
