While significant advancements have been made in video question answering (VideoQA), the potential benefits of enhancing model generalization through tailored difficulty scheduling have been largely overlooked in existing research. This paper seeks to bridge that gap by incorporating VideoQA into a curriculum learning (CL) framework that progressively trains models from simpler to more complex data. Recognizing that conventional self-paced CL methods rely on training loss for difficulty measurement, which might not accurately reflect the intricacies of video-question pairs, we introduce the concept of uncertainty-aware CL. Here, uncertainty serves as the guiding principle for dynamically adjusting the difficulty. Furthermore, we address the challenge posed by uncertainty by presenting a probabilistic modeling approach for VideoQA. Specifically, we conceptualize VideoQA as a stochastic computation graph, where the hidden representations are treated as stochastic variables. This yields two distinct types of uncertainty: one related to the inherent uncertainty in the data and another pertaining to the model's confidence. In practice, we seamlessly integrate the VideoQA model into our framework and conduct comprehensive experiments. The findings affirm that our approach not only achieves enhanced performance but also effectively quantifies uncertainty in the context of VideoQA.

翻译：尽管视频问答（VideoQA）领域已取得显著进展，但现有研究在很大程度上忽略了通过针对性难度调度增强模型泛化能力的潜在益处。本文旨在通过将VideoQA融入课程学习（CL）框架来弥合这一差距，该框架从简单到复杂的数据逐步训练模型。考虑到传统自步课程学习方法依赖训练损失进行难度度量，这可能无法准确反映视频-问题对的复杂性，我们引入了不确定性感知的课程学习概念。其中，不确定性作为动态调整难度的指导原则。此外，我们通过提出VideoQA的概率建模方法来解决不确定性带来的挑战。具体而言，我们将VideoQA概念化为一个随机计算图，其中隐藏表示被视为随机变量。这产生了两种不同类型的不确定性：一种与数据固有的不确定性相关，另一种与模型自身的置信度相关。在实践中，我们将VideoQA模型无缝集成到我们的框架中，并进行了全面实验。实验结果证实，我们的方法不仅实现了性能提升，还有效量化了VideoQA背景下的不确定性。