通过提取骨骼动作的局部运动原型，提升相似动作识别精度。
Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition
- 用可学习的运动原型分解骨骼序列，捕捉局部细微动态
- 在多个数据集上达到当前最优性能，最高准确率86.3%
- 适合需要精细动作区分的场景，如医疗康复分析
基于骨骼的动作识别面临挑战：由于骨骼表示缺乏图像级细节，难以区分轨迹相似的动作。我们发现，区分相似动作的关键在于特定身体部位的细微运动差异。为此，提出ProtoGCN——一种基于图卷积网络（GCN）的模型，将完整骨骼序列的动力学分解为可学习的原型，代表动作单元的核心运动模式。通过对比原型重建结果，模型能有效识别并增强相似动作的判别性表征。无需复杂组件，ProtoGCN在多个基准数据集上取得领先性能，包括NTU RGB+D、NTU RGB+D 120、Kinetics-Skeleton和FineGYM，验证了方法的有效性。
原文摘要 · Abstract (English)
In skeleton-based action recognition, a key challenge is distinguishing between actions with similar trajectories of joints due to the lack of image-level details in skeletal representations. Recognizing that the differentiation of similar actions relies on subtle motion details in specific body parts, we direct our approach to focus on the fine-grained motion of local skeleton components. To this end, we introduce ProtoGCN, a Graph Convolutional Network (GCN)-based model that breaks down the dynamics of entire skeleton sequences into a combination of learnable prototypes representing core motion patterns of action units. By contrasting the reconstruction of prototypes, ProtoGCN can effectively identify and enhance the discriminative representation of similar actions. Without bells and whistles, ProtoGCN achieves state-of-the-art performance on multiple benchmark datasets, including NTU RGB+D, NTU RGB+D 120, Kinetics-Skeleton, and FineGYM, which demonstrates the effectiveness of the proposed method. The code is available at https://github.com/firework8/ProtoGCN.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。