探索自适应掩码重建用于自监督骨架动作识别
Exploring Adaptive Masked Reconstruction for Self-Supervised Skeleton-Based Action Recognition
把解码器与编码器解耦、用更大的时空图像块做掩码重建，并用运动信息量自适应引导重建难度，这套思路可直接迁移到视频/骨架等时序视觉表征的预训练中，在缩短训练时间的同时提升下游识别精度。
原文依据 We first decouple the decoder from the encoder, enabling flexible prediction of larger spatiotemporal patches
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近来，掩码骨架重建模型已成为强大的动作表征学习器，推动了自监督骨架动作识别的显著进展。然而，现有最优方法必须预测数量极多的时空图像块，显著延长了训练时间。此外，这些模型在重建时对所有时空区域一视同仁，因而被分散了注意力，难以学习构成动作语义的关键运动模式。为应对这些挑战，我们提出自适应掩码重建（AMR），一个更快且更强的预训练框架。我们首先将解码器与编码器解耦，从而能够灵活地预测更大的时空图像块，并大幅降低重建复杂度。鉴于更大的图像块包含更复杂的信息，预测难度更高并因此导致性能下降，我们相应地引入自适应引导模块。该模块识别运动信息量高的区域，引导模型关注每个图像块中最具判别性的部分，从而缓解重建难度。在 NTU RGB+D 60、NTU RGB+D 120 和 PKU-MMD 数据集上的实验表明，AMR 不仅大幅加速了预训练，还提升了下游识别准确率，超越了当前最优方法。
英文原文摘要 1403 字符
Recently, masked skeleton reconstruction models have emerged as strong action representation learners, driving significant progress in self-supervised skeleton-based action recognition. However, existing state-of-the-art methods must predict an exceedingly large number of spatiotemporal patches, significantly prolonging training time. Besides, by treating all spatiotemporal regions equally during reconstruction, these models are distracted from learning the critical motion patterns that underlie action semantics. To address these challenges, we propose Adaptive Masked Reconstruction (AMR), a faster and stronger pre-training framework. We first decouple the decoder from the encoder, enabling flexible prediction of larger spatiotemporal patches and dramatically reducing reconstruction complexity. Given that larger patches contain more complex information, which is challenging to predict and consequently degrades performance, we accordingly introduce an adaptive guidance module. This module identifies regions of high motion informativeness, guiding the model to focus on the most discriminative parts of each patch and alleviating reconstruction difficulty. Experiments on NTU RGB+D 60, NTU RGB+D 120, and PKU-MMD datasets demonstrate that AMR not only accelerates pre-training substantially but also improves downstream recognition accuracy, surpassing current state-of-the-art approaches.