更多动作并不总是更好的动作：语料库构成决定数据增强是否有助于基于SMPL的帕金森病步态严重程度估计
More Motion Is Not Always Better Motion: Corpus Composition Governs Whether Augmentation Helps SMPL-Based Parkinsonian Gait Severity Estimation
浏览论文内容
中文总结 AI 辅助
该研究针对基于SMPL的帕金森病步态严重程度估计，发现动作语料库的速度对比而非数据量决定数据增强效果，合成动作与网络视频无法提升性能，修改表示本身的尝试均失败。
中文摘要 AI 辅助
我们使用三个冻结的MotionAGFormer编码器作为特征提取器，从SMPL动作中对MDS-UPDRS步态严重程度进行分级，在一个隐藏的多站点测试集上达到了宏F1值0.58。由于这些编码器的区别仅在于其用于训练的语料库，因此在该测试集上单独评估编码器可分离出该语料库的贡献。从一个惯性数据集抽取的六个数据集池，仅在包含的步行任务上存在差异，其得分在0.32至0.53之间，其中仅有一个池优于未使用外部动作的编码器的0.51得分。区分它们的因素不是数据量，而是是否包含步行速度的对比，该表示似乎依赖于这种变化；在固定任务构成下添加第三个站点的进一步池表现更差。相同的规则解释了为何精确合成动作和单目重建的网络视频均无法提供帮助。修改学习到的表示本身而非其背后的语料库，使所有尝试此操作的变体均付出了代价。
英文摘要
We grade MDS-UPDRS gait severity from SMPL motion using three frozen MotionAGFormer encoders as featurizers, reaching macro-F1 0.58 on a hidden, multi-site test set. Because the system's members differ only in their lifting corpus, evaluating encoders singly on that test set isolates what that corpus contributes. Six pools drawn from one inertial dataset, varying only in which walking tasks they include, score between 0.32 and 0.53, and just one of them beats the 0.51 of an encoder given no outside motion at all. What separates them is not how much data they hold but whether they carry a contrast in walking speed, the variation this representation appears to depend : a further pool adding a third collection site at fixed task composition does worse still. The same rule explains why exact synthetic motion and monocularly reconstructed web video both fail to help. Modifying the learned representation itself, rather than the corpus behind it, cost every variant that attempted it.
发表机构
- Credence（克瑞登斯公司）
机构由 AI 辅助整理，请以论文原文为准。
