论文标题
通过连续的关系预期模型的组活动预测
Group Activity Prediction with Sequential Relational Anticipation Model
论文作者
论文摘要
在本文中，我们提出了一种新颖的方法，以预测具有不完整活动执行的起点框架。现有的行动预测方法学会增强部分观察的表示能力。但是，对于小组活动预测，人们活动的关系及其位置随着时间的流逝是预测小组活动的重要提示。为此，我们提出了一个顺序的关系预期模型（SRAM），该模型总结了部分观察中的关系动力学，并逐渐预测了具有丰富歧视性信息的组表示。我们的模型可以通过两个图自动编码器明确预测活动特征和位置，旨在学习一个分组活动预测的判别组表示。对两个普遍使用的数据集的实验结果表明，我们的方法显着优于最先进的活动预测方法。
In this paper, we propose a novel approach to predict group activities given the beginning frames with incomplete activity executions. Existing action prediction approaches learn to enhance the representation power of the partial observation. However, for group activity prediction, the relation evolution of people's activity and their positions over time is an important cue for predicting group activity. To this end, we propose a sequential relational anticipation model (SRAM) that summarizes the relational dynamics in the partial observation and progressively anticipates the group representations with rich discriminative information. Our model explicitly anticipates both activity features and positions by two graph auto-encoders, aiming to learn a discriminative group representation for group activity prediction. Experimental results on two popularly used datasets demonstrate that our approach significantly outperforms the state-of-the-art activity prediction methods.
