Video summarization is a crucial technique for social understanding, enabling efficient browsing of massive multimedia content and extraction of key information from social platforms. Most existing unsupervised summarization methods rely on Generative Adversarial Networks (GANs) to enhance keyframe selection and generate coherent, video summaries through adversarial training. However, such approaches primarily exploit unimodal features, overlooking the guiding role of semantic information in keyframe selection, and often suffer from unstable training. To address these limitations, we propose a novel Semantic-Guided Unsupervised Video Summarization method. Specifically, we design a novel frame-level semantic alignment attention mechanism and integrate it into a keyframe selector, which guides the Transformer-based generator within the adversarial framework to better reconstruct videos. In addition, we adopt an incremental training strategy to progressively update the model components, effectively mitigating the instability of GAN training. Experimental results demonstrate that our approach achieves superior performance on multiple benchmark datasets.

翻译：视频摘要是一项关键的社会理解技术，能够实现对海量多媒体内容的高效浏览，并从社交平台中提取关键信息。现有的大多数无监督摘要方法依赖于生成对抗网络，通过对抗训练来增强关键帧选择并生成连贯的视频摘要。然而，此类方法主要利用单模态特征，忽视了语义信息在关键帧选择中的引导作用，且常面临训练不稳定的问题。为克服这些局限性，本文提出了一种新颖的语义引导无监督视频摘要方法。具体而言，我们设计了一种新颖的帧级语义对齐注意力机制，并将其集成到关键帧选择器中，从而在对抗框架内引导基于Transformer的生成器更好地重建视频。此外，我们采用增量训练策略逐步更新模型组件，有效缓解了GAN训练的不稳定性。实验结果表明，我们的方法在多个基准数据集上取得了优异的性能。