Generative model-enhanced human motion prediction.
Generative model-enhanced human motion prediction.
复制标题
DOI：
10.1002/ail2.63
复制
发表时间：
2022-04
期刊：
影响因子：
--
通讯作者：
Nachev, Parashkev
中科院分区：
文献类型：
--
作者：
Bourached, Anthony;Griffiths, Ryan-Rhys;Gray, Robert;Jha, Ashwani;Nachev, Parashkev
预测人体运动的任务由于动作的自然异质性和组合性而变得复杂，因此需要对分布偏移（OoD）具有鲁棒性。在这里，我们制定了一个新的OoD基准的基础上的Human3.6M和卡内基梅隆大学（CMU）的运动捕捉数据集，并引入了一个混合框架，通过增强他们的生成模型，以硬化判别架构OoD故障。当应用于当前最先进的判别模型时，我们表明所提出的方法在不牺牲分布性能的情况下提高了OoD鲁棒性，并且在理论上可以促进模型的可解释性。我们建议人类运动预测器应该与OoD的挑战铭记，并提供了一个可扩展的一般框架硬化不同的歧视性架构，极端的分布变化。该代码可从以下网址获得：https://github.com/bouracha/OoDMotion。
The task of predicting human motion is complicated by the natural heterogeneity and compositionality of actions, necessitating robustness to distributional shifts as far as out‐of‐distribution (OoD). Here, we formulate a new OoD benchmark based on the Human3.6M and Carnegie Mellon University (CMU) motion capture datasets, and introduce a hybrid framework for hardening discriminative architectures to OoD failure by augmenting them with a generative model. When applied to current state‐of‐the‐art discriminative models, we show that the proposed approach improves OoD robustness without sacrificing in‐distribution performance, and can theoretically facilitate model interpretability. We suggest human motion predictors ought to be constructed with OoD challenges in mind, and provide an extensible general framework for hardening diverse discriminative architectures to extreme distributional shift. The code is available at: https://github.com/bouracha/OoDMotion.