将信息瓶颈归因扩展至视频序列
Extending Information Bottleneck Attribution to Video Sequences
AI总结：
本文提出VIBA方法，将信息瓶颈归因（IBA）适配至视频序列，通过结合Xception和VGG11模型生成时空一致的解释，为视频分类特别是deepfake检测提供可解释性。
摘要：
我们引入了VIBA，这是一种通过将信息瓶颈归因（IBA）适配至视频序列来实现可解释视频分类的新方法。尽管多数传统可解释性方法专为图像模型设计，我们的IBA框架满足了视频分析中时序模型的可解释性需求。为展示其有效性，我们将VIBA应用于视频deepfake检测，并在两种架构上进行测试：用于提取空间特征的Xception模型，以及通过光流捕捉运动动态的基于VGG11的模型。使用反映最新deepfake生成技术的自定义数据集，我们适配IBA以创建相关性和光流图，直观地突出被篡改区域与运动不一致性。结果表明，VIBA能生成时空一致的解释，与人类标注高度吻合，从而为视频分类特别是deepfake检测提供可解释性。
英文摘要：
We introduce VIBA, a novel approach for explainable video classification by adapting Information Bottlenecks for Attribution (IBA) to video sequences. While most traditional explainability methods are designed for image models, our IBA framework addresses the need for explainability in temporal models used for video analysis. To demonstrate its effectiveness, we apply VIBA to video deepfake detection, testing it on two architectures: the Xception model for spatial features and a VGG11-based model for capturing motion dynamics through optical flow. Using a custom dataset that reflects recent deepfake generation techniques, we adapt IBA to create relevance and optical flow maps, visually highlighting manipulated regions and motion inconsistencies. Our results show that VIBA generates temporally and spatially consistent explanations, which align closely with human annotations, thus providing interpretability for video classification and particularly for deepfake detection.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
