用过渡锚点建模动作连续性，提升骨骼动作识别精度
Beyond Binary Contrast: Modeling Continuous Skeleton Action Spaces with Transitional Anchors
- 引入过渡锚点捕捉动作间的几何连续性
- 多层级流形校准使特征空间更平滑，准确率显著提升
- 适合需要连续动作理解的视频分析任务
自监督对比学习在基于骨骼的动作识别中表现出色，但现有方法依赖二元对比目标，忽视了人类运动的内在连续性，导致特征簇碎片化、类别边界僵硬。为此，本文提出TranCLR框架，通过显式建模过渡状态的几何结构，增强对运动连续性的感知。具体地，提出动作过渡锚点构建（ATAC）机制，并设计多层级几何流形校准（MGMC）以自适应调节不同连续层次上的动作流形，获得更平滑且更具判别性的表示空间。在NTU RGB+D、NTU RGB+D 120和PKU-MMD数据集上的实验表明，TranCLR在准确率和校准性能上均优于现有方法，有效学习到连续且具备不确定性感知能力的骨骼表示。代码已开源。
原文摘要 · Abstract (English)
Self-supervised contrastive learning has emerged as a powerful paradigm for skeleton-based action recognition by enforcing consistency in the embedding space. However, existing methods rely on binary contrastive objectives that overlook the intrinsic continuity of human motion, resulting in fragmented feature clusters and rigid class boundaries. To address these limitations, we propose TranCLR, a Transitional anchor-based Contrastive Learning framework that captures the continuous geometry of the action space. Specifically, the proposed Action Transitional Anchor Construction (ATAC) explicitly models the geometric structure of transitional states to enhance the model's perception of motion continuity. Building upon these anchors, a Multi-Level Geometric Manifold Calibration (MGMC) mechanism is introduced to adaptively calibrate the action manifold across multiple levels of continuity, yielding a smoother and more discriminative representation space. Extensive experiments on the NTU RGB+D, NTU RGB+D 120 and PKU-MMD datasets demonstrate that TranCLR achieves superior accuracy and calibration performance, effectively learning continuous and uncertainty-aware skeleton representations. The code is available at https://github.com/Philchieh/TranCLR.
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。