论文标题
SAR-NAS：基于骨架的动作识别通过神经架构搜索
SAR-NAS: Skeleton-based Action Recognition via Neural Architecture Searching
论文作者
论文摘要
本文介绍了基于骨架的动作识别的神经网络体系结构的自动设计研究。具体而言，我们将基于骨架的动作实例编码为张量，并仔细定义一组操作以构建两种类型的网络单元：正常单元和还原细胞。采用了最近开发的飞镖（可区分架构搜索）来搜索建立在两种类型的单元格上的有效网络体系结构。所有操作均基于2D，以减少整体计算和搜索空间。关于具有挑战性的NTU RGB+D和Kinectics数据集的实验已验证，迄今为止，基于骨架的动作识别开发的大多数网络可能不紧凑，有效。所提出的方法提供了一种方法，可以搜索这种紧凑的网络，该网络能够比最新方法实现比较甚至更好的性能。
This paper presents a study of automatic design of neural network architectures for skeleton-based action recognition. Specifically, we encode a skeleton-based action instance into a tensor and carefully define a set of operations to build two types of network cells: normal cells and reduction cells. The recently developed DARTS (Differentiable Architecture Search) is adopted to search for an effective network architecture that is built upon the two types of cells. All operations are 2D based in order to reduce the overall computation and search space. Experiments on the challenging NTU RGB+D and Kinectics datasets have verified that most of the networks developed to date for skeleton-based action recognition are likely not compact and efficient. The proposed method provides an approach to search for such a compact network that is able to achieve comparative or even better performance than the state-of-the-art methods.
