In this paper, we propose a frame-part-activated deep reinforcement learning (FPA-DRL) for action prediction. Most existing methods for action prediction utilize the evolution of whole frames to model actions, which cannot avoid the noise of the current action, especially in the early prediction. Moreover, the loss of structural information of human body diminishes the capacity of features to describe actions. To address this, we design a FPA-DRL to exploit the structure of the human body by extracting skeleton proposals and reduce the redundancy of frames under a deep reinforcement learning framework. Specifically, we extract features from different parts of the human body individually, activate the action-related parts in features and the action-related frames in videos to enhance the representation. Our method not only exploits the structure information of the human body, but also considers the attention frame for expressing actions. We evaluate our method on three popular action prediction datasets: UT-Interaction, BIT-Interaction and UCF101. Our experimental results demonstrate that our method achieves the very competitive performance with state-of-the-arts.

中文翻译：

---

用于动作预测的框架部分激活深度强化学习

在本文中，我们提出了一种用于动作预测的框架部分激活深度强化学习（FPA-DRL）。大多数现有的动作预测方法利用整个帧的演化来对动作进行建模，这无法避免当前动作的噪声，尤其是在早期预测中。此外，人体结构信息的丢失降低了特征描述动作的能力。为了解决这个问题，我们设计了一个 FPA-DRL，通过提取骨架提案来利用人体结构，并在深度强化学习框架下减少帧的冗余。具体来说，我们分别从人体的不同部位提取特征，激活特征中与动作相关的部分以及视频中与动作相关的帧以增强表示。我们的方法不仅利用人体的结构信息，还考虑了表达动作的注意力框架。我们在三个流行的动作预测数据集上评估我们的方法：UT-Interaction、BIT-Interaction 和 UCF101。我们的实验结果表明，我们的方法在最先进的技术中实现了非常有竞争力的性能。