Capturing long-range dependencies has proven effective on video understanding tasks. However, previous works address this problem in a pixel pairs manner, which might be inaccurate since pixel pairs contain too limited semantic information. Besides, considerable computations and parameters will be introduced in those methods. Following the pattern of features aggregation in Graph Convolutional Networks (GCNs), we aggregate pixels with their neighbors into semantic units, which contain stronger semantic information than pixel pairs. We designed an efficient, parameter-free, semantic units-based dependencies capturing framework, named as Multi-semantic Long-range Dependencies Capturing (MLDC) block. We verified our methods on large-scale challenging video classification benchmark, such as Kinetics. Experiments demonstrate that our method highly outperforms pixel pairs-based methods and achieves the state-of-the-art performance, without introducing any parameters and much computations.

事实证明，捕获远程依存关系对视频理解任务有效。但是，先前的工作以像素对的方式解决了这个问题，由于像素对包含的语义信息太有限，这可能是不准确的。此外，在那些方法中将引入大量的计算和参数。遵循图卷积网络（GCN）中的特征聚合模式，我们将像素及其相邻像素聚合到语义单元中，该语义单元比像素对包含更强的语义信息。我们设计了一个高效的，无参数的，基于语义单元的依存关系捕获框架，称为多语义远程依存关系捕获（MLDC）块。我们在大规模的具有挑战性的视频分类基准（例如Kinetics）上验证了我们的方法。