论文标题
JOLO-GCN：基于骨架的动作识别的采矿中心的轻重量信息
JOLO-GCN: Mining Joint-Centered Light-Weight Information for Skeleton-Based Action Recognition
论文作者
论文摘要
近年来，基于骨架的动作识别引起了研究的关注。目前基于流行的骨架的人类动作识别方法中的一个常见缺点是，仅稀疏骨骼信息就不足以完全表征人类运动。该限制使几种现有的方法无法正确分类动作类别，而动作类别仅显示出细微的运动差异。在本文中，我们提出了一个新颖的框架，用于在两潮图卷积网络中共同采用人类姿势骨骼和以中心的轻重量信息，即JOLO-GCN。具体而言，我们使用联合一致的光流斑（JFP）作为关键中心的视觉信息来捕获每个关节周围的局部微妙运动。与基于纯骨架的基线相比，这种混合方案有效地提高了性能，同时保持计算和内存开销较低。在NTU RGB+D，NTU RGB+D 120和动力学 - 骨骼数据集上进行的实验表明，在基于最新的骨架的方法上，提出的方法获得了明确的准确性提高。
Skeleton-based action recognition has attracted research attentions in recent years. One common drawback in currently popular skeleton-based human action recognition methods is that the sparse skeleton information alone is not sufficient to fully characterize human motion. This limitation makes several existing methods incapable of correctly classifying action categories which exhibit only subtle motion differences. In this paper, we propose a novel framework for employing human pose skeleton and joint-centered light-weight information jointly in a two-stream graph convolutional network, namely, JOLO-GCN. Specifically, we use Joint-aligned optical Flow Patches (JFP) to capture the local subtle motion around each joint as the pivotal joint-centered visual information. Compared to the pure skeleton-based baseline, this hybrid scheme effectively boosts performance, while keeping the computational and memory overheads low. Experiments on the NTU RGB+D, NTU RGB+D 120, and the Kinetics-Skeleton dataset demonstrate clear accuracy improvements attained by the proposed method over the state-of-the-art skeleton-based methods.
