论文标题
时代：早期行动预测的专家检索和组装
ERA: Expert Retrieval and Assembly for Early Action Prediction
论文作者
论文摘要
早期动作预测旨在在完全执行动作之前成功预测其类标签。这是一个具有挑战性的任务，因为不同动作的开始阶段可能非常相似，只有微妙的差异来歧视。在本文中，我们提出了一个新颖的专家检索和组装（ERA）模块，该模块检索并组装了一组最专业的专家，旨在使用歧视性微妙的差异，以将输入样本与其他高度相似的样本区分开来。为了鼓励我们的模型有效地使用细微的差异来进行早期行动预测，我们促使专家仅区分高度相似的样本，迫使这些专家学习使用这些样本之间存在的细微差异。此外，我们设计了一种有效的专家学习率优化方法，可以平衡专家的优化并带来更好的性能。我们在四个公共行动数据集上评估了我们的ERA模块，并实现了最先进的性能。
Early action prediction aims to successfully predict the class label of an action before it is completely performed. This is a challenging task because the beginning stages of different actions can be very similar, with only minor subtle differences for discrimination. In this paper, we propose a novel Expert Retrieval and Assembly (ERA) module that retrieves and assembles a set of experts most specialized at using discriminative subtle differences, to distinguish an input sample from other highly similar samples. To encourage our model to effectively use subtle differences for early action prediction, we push experts to discriminate exclusively between samples that are highly similar, forcing these experts to learn to use subtle differences that exist between those samples. Additionally, we design an effective Expert Learning Rate Optimization method that balances the experts' optimization and leads to better performance. We evaluate our ERA module on four public action datasets and achieve state-of-the-art performance.
