The problem of anticipating human actions is an inherently uncertain one. However, we can reduce this uncertainty if we have a sense of the goal that the actor is trying to achieve. Here, we present an action anticipation model that leverages goal information for the purpose of reducing the uncertainty in future predictions. Since we do not possess goal information or the observed actions during inference, we resort to visual representation to encapsulate information about both actions and goals. Through this, we derive a novel concept called abstract goal which is conditioned on observed sequences of visual features for action anticipation. We design the abstract goal as a distribution whose parameters are estimated using a variational recurrent network. We sample multiple candidates for the next action and introduce a goal consistency measure to determine the best candidate that follows from the abstract goal. Our method obtains impressive results on the very challenging Epic-Kitchens55 (EK55), EK100, and EGTEA Gaze+ datasets. We obtain absolute improvements of +13.69, +11.24, and +5.19 for Top-1 verb, Top-1 noun, and Top-1 action anticipation accuracy respectively over prior state-of-the-art methods for seen kitchens (S1) of EK55. Similarly, we also obtain significant improvements in the unseen kitchens (S2) set for Top-1 verb (+10.75), noun (+5.84) and action (+2.87) anticipation. Similar trend is observed for EGTEA Gaze+ dataset, where absolute improvement of +9.9, +13.1 and +6.8 is obtained for noun, verb, and action anticipation. It is through the submission of this paper that our method is currently the new state-of-the-art for action anticipation in EK55 and EGTEA Gaze+ https://competitions.codalab.org/competitions/20071#results Code available at https://github.com/debadityaroy/Abstract_Goal

翻译：人类行为预测本质上是一个充满不确定性的问题。然而，若我们了解行为主体试图达成的目标，便能降低这种不确定性。本文提出一种利用目标信息减少未来预测不确定性的行为预测模型。由于推理过程中无法获取目标信息或已观测行为，我们借助视觉表征来封装行为与目标的双重信息。据此，我们推导出一个新颖概念——抽象目标，它基于观测到的视觉特征序列，用于行为预测。我们将抽象目标设计为一种分布，其参数通过变分循环网络进行估计。我们为下一步动作采样多个候选，并引入目标一致性度量以确定最符合抽象目标的优选方案。本方法在极具挑战性的Epic-Kitchens55 (EK55)、EK100和EGTEA Gaze+数据集上取得了显著成果。在EK55的已见厨房场景（S1）中，我们相较于先前最先进方法在Top-1动词、Top-1名词和Top-1动作预测准确率上分别实现了+13.69、+11.24和+5.19的绝对提升。类似地，在未见厨房场景（S2）的Top-1动词（+10.75）、名词（+5.84）和动作（+2.87）预测中亦获得显著改进。EGTEA Gaze+数据集呈现相同趋势，名词、动词和动作预测的绝对提升分别达到+9.9、+13.1和+6.8。通过本文提交，我们的方法已成为EK55和EGTEA Gaze+上行为预测的最新最先进方案 https://competitions.codalab.org/competitions/20071#results 代码地址：https://github.com/debadityaroy/Abstract_Goal