论文标题
不确定性驱动的行动质量评估
Uncertainty-Driven Action Quality Assessment
论文作者
论文摘要
自动行动质量评估（AQA）由于其广泛的应用而引起了人们越来越多的关注。但是，大多数现有的AQA方法都采用确定性模型来预测每个动作的最终分数，同时忽略了评分过程中专家法官之间的主观性和多样性。在本文中，我们提出了一个新颖的概率模型，称为不确定性驱动的AQA（UD-AQA），以利用和捕获多个法官分数之间的多样性。具体而言，我们设计了一个有条件的变异自动编码器（CVAE）模块来编码专家评估中的不确定性，在这些模块中可以通过多次从学习潜在空间中抽样潜在特征来产生多个法官分数。为了进一步利用不确定性，我们为每个预测产生不确定性的估计，该预测被用来重新体重AQA回归损失，有效地减少了训练过程中不确定样本的影响。此外，我们进一步设计了一种不确定性引导的培训策略，以动态调整样本的学习顺序，从低不确定性到高不确定性。实验表明，我们提出的方法在包括奥林匹克事件MTL-AQA和罚款的三个基准上取得了竞争成果，以及手术技能jigsaws数据集。
Automatic action quality assessment (AQA) has attracted increasing attention due to its wide applications. However, most existing AQA methods employ deterministic models to predict the final score for each action, while overlooking the subjectivity and diversity among expert judges during the scoring process. In this paper, we propose a novel probabilistic model, named Uncertainty-Driven AQA (UD-AQA), to utilize and capture the diversity among multiple judge scores. Specifically, we design a Conditional Variational Auto-Encoder (CVAE)-based module to encode the uncertainty in expert assessment, where multiple judge scores can be produced by sampling latent features from the learned latent space multiple times. To further utilize the uncertainty, we generate the estimation of uncertainty for each prediction, which is employed to re-weight AQA regression loss, effectively reducing the influence of uncertain samples during training. Moreover, we further design an uncertainty-guided training strategy to dynamically adjust the learning order of the samples from low uncertainty to high uncertainty. The experiments show that our proposed method achieves competitive results on three benchmarks including the Olympic events MTL-AQA and FineDiving, and the surgical skill JIGSAWS datasets.
