We propose a new method for learning videos by aggregating multiple models by sequentially extracting video clips from untrimmed video. The proposed method reduces the correlation between clips by feeding clips to multiple models in turn and synchronizes these models through federated learning. Experimental results show that the proposed method improves the performance compared to the no synchronization.

翻译：我们提出了一种新方法，通过从未修剪视频中顺序提取视频片段并聚合多个模型来实现视频学习。该方法通过将视频片段依次输入多个模型来降低片段间的相关性，并通过联邦学习同步这些模型。实验结果表明，与未进行同步的方法相比，所提方法显著提升了性能。