Parts-Mamba：通过部分级扫描增强关节联合上下文以处理遮挡的人体骨架
Parts-Mamba: Augmenting Joint Context with Part-Level Scanning for Occluded Human Skeleton
AI总结：
Parts-Mamba通过部分级扫描和身体融合模块提升遮挡环境下的人体骨架动作识别精度
摘要：
人体骨架动作识别涉及从人体骨架中识别人类动作。图卷积网络（GCNs）的使用已推动了这一识别任务的重大进展。在现实世界场景中，捕获的骨架不总是完美或完整的，因为人体部分的遮挡或通信质量差，导致骨架或视频中缺失部分帧。在存在此类非理想情况时，现有GCN模型由于缺少局部上下文而表现不佳。为了解决这一限制，我们提出了Parts-Mamba，一种混合的GCN-Mamba模型，旨在增强从远距离关节中捕捉和保持上下文信息的能力。所提出的Parts-Mamba模型通过其部分特定扫描特征有效捕捉部分特定信息，并通过部分-身体融合模块保留非邻接关节上下文。我们提出的模型在不同遮挡设置下评估了NTU RGB+D 60和NTU RGB+D 120数据集，实现了准确率高达12.9%的提升。
英文摘要：
Skeleton action recognition involves recognizing human action from human skeletons. The use of graph convolutional networks (GCNs) has driven major advances in this recognition task. In real-world scenarios, the captured skeletons are not always perfect or complete because of occlusions of parts of the human body or poor communication quality, leading to missing parts in skeletons or videos with missing frames. In the presence of such non-idealities, existing GCN models perform poorly due to missing local context. To address this limitation, we propose Parts-Mamba, a hybrid GCN-Mamba model designed to enhance the ability to capture and maintain contextual information from distant joints. The proposed Parts-Mamba model effectively captures part-specific information through its parts-specific scanning feature and preserves non-neighboring joint context via a parts-body fusion module. Our proposed model is evaluated on the NTU RGB+D 60 and NTU RGB+D 120 datasets under different occlusion settings, achieving up to 12.9% improvement in accuracy.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
