Recent studies have achieved outstanding success in explaining 2D image
recognition ConvNets. On the other hand, due to the computation cost and
complexity of video data, the explanation of 3D video recognition ConvNets is
relatively less studied. In this paper, we present a 3D ACE (Automatic
Concept-based Explanation) framework for interpreting 3D ConvNets. In our
approach: (1) videos are represented using high-level supervoxels, which is
straightforward for human to understand; and (2) the interpreting framework
estimates a score for each voxel, which reflects its importance in the decision
procedure. Experiments show that our method can discover spatial-temporal
concepts of different importance-levels, and thus can explore the influence of
the concepts on a target task, such as action classification, in-depth. The
codes are publicly available.

本文介绍了一种用于解释三维卷积神经网络的自动概念解释（ACE）框架，该框架基于高水平的 supervoxels 表示视频，并估计每个 Supervoxel 的重要性得分，可以发现不同重要级别的时空概念，并深入探索这些概念对目标任务（例如动作分类）的影响。