用稀疏令牌预测骨骼特征，显著降低计算量并提升动作表征能力。
Less is More: Compact-Token Masked Feature Prediction for Skeleton Representation Learning
- 以特征预测替代坐标重建，使用稀疏令牌和共享编码器统一学习机制。
- 在多个任务上达到顶尖性能，推理计算量比密集令牌方法降低7.89倍。
- 通过语义管掩码与骨骼感知增强，防止偷懒学习，提升骨骼时空一致性。
当前骨骼表征学习方法存在明显局限：对比学习常忽略精细运动细节，而掩码自编码器依赖坐标级重建。后者需密集令牌序列和重型解码器，导致预训练计算浪费在被丢弃的组件上，并迫使下游推理处理密集令牌网格。为解决此瓶颈，我们提出SLiM（Skeleton Less is More），一种基于稀疏令牌的统一框架，通过共享编码器融合掩码特征预测与对比学习。将目标从原始坐标重建转向无解码器、教师引导的特征预测，打破对密集分词的依赖，实现高效学习。关键在于，为防止由人体关节间强相关性引发的简化学习陷阱，引入语义管掩码与骨骼感知增强，强制深层骨骼-时序推理与解剖一致性。在多个下游协议上的实验表明，SLiM不仅取得最先进性能，且相比密集令牌MAE基线，结构上减少7.89倍推理计算量。
原文摘要 · Abstract (English)
Current skeleton representation learning paradigms face distinct limitations: Contrastive Learning (CL) often overlooks fine-grained motion details, while Masked Auto-Encoders (MAE) rely on coordinate-level reconstruction. This reconstruction inherently demands dense token sequences and heavy decoders, wasting pre-training computation on discarded components and forcing downstream inference to process dense token grids. To resolve these bottlenecks, we propose SLiM (Skeleton Less is More), a compact-token framework that unifies masked feature prediction and contrastive learning via a shared encoder. By shifting the objective from raw coordinate reconstruction to decoder-free, teacher-guided feature prediction, SLiM breaks the reliance on dense tokenization and enables effective learning with a highly compact token grid. Crucially, to prevent trivial shortcut learning arising from strong inter-joint dependencies of human, we introduce Semantic Tube Masking together with Skeleton-Aware Augmentations to enforce deep skeletal-temporal reasoning and anatomical consistency. Extensive experiments across multiple downstream protocols demonstrate that SLiM achieves state-of-the-art performance while structurally reducing inference computation by 7.89$\times$ compared to dense-token MAE baselines.
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。