超越二值对比：用过渡锚框建模连续骨骼动作空间
Beyond Binary Contrast: Modeling Continuous Skeleton Action Spaces with Transitional Anchors
把二值对比目标替换为在动作流形上构造过渡锚框并做多层级几何校准，可直接迁移到任何需要建模连续类间过渡的自监督表征学习任务（如细粒度动作、时序分割边界）。
原文依据 existing methods rely on binary contrastive objectives that overlook the intrinsic continuity of human motion
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论自监督对比学习通过在嵌入空间中强制一致性，已成为基于骨骼的动作识别的一种强大范式。然而，现有方法依赖二值对比目标，忽略了人体运动的内在连续性，导致特征簇碎片化和类别边界僵化。为解决这些局限，我们提出 TranCLR，一个基于过渡锚框的对比学习框架，用于捕捉动作空间的连续几何结构。具体而言，所提出的动作过渡锚框构建（ATAC）显式建模过渡状态的几何结构，以增强模型对运动连续性的感知。在这些锚框的基础上，我们引入多层级几何流形校准（MGMC）机制，在多个连续性层级上自适应地校准动作流形，从而得到更平滑、更具判别性的表征空间。在 NTU RGB+D、NTU RGB+D 120 和 PKU-MMD 数据集上的大量实验表明，TranCLR 取得了更优的准确率与校准性能，有效学习到连续且具有不确定性感知能力的骨骼表征。代码将公开。
英文原文摘要 1237 字符
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. Code will be made publicly available.