通过建模抽象目标预测下一个动作
Predicting the Next Action by Modeling the Abstract Goal
AI总结：
本文提出一种基于抽象目标建模的动作预测方法，利用变分循环网络估计目标分布，并通过目标一致性度量选择最佳候选，在EK55、EK100和EGTEA Gaze+数据集上显著超越现有最先进方法。
摘要：
预测人类动作的问题本质上具有不确定性。然而，如果我们能够感知到行为者试图实现的目标，就可以减少这种不确定性。在此，我们提出了一种动作预测模型，利用目标信息来降低未来预测中的不确定性。由于在推理过程中我们不具备目标信息或观察到的动作，我们借助视觉表征来封装关于动作和目标的信息。通过这种方式，我们提出了一个名为“抽象目标”的新概念，它基于观察到的视觉特征序列来条件化动作预测。我们将抽象目标设计为一个分布，其参数通过变分循环网络进行估计。我们为下一个动作采样多个候选，并引入一种目标一致性度量来确定遵循抽象目标的最佳候选。我们的方法在极具挑战性的Epic-Kitchens55（EK55）、EK100和EGTEA Gaze+数据集上取得了令人印象深刻的结果。在EK55的已知厨房（S1）上，我们在Top-1动词、Top-1名词和Top-1动作预测准确率上分别比先前最先进的方法取得了+13.69、+11.24和+5.19的绝对提升。同样，在未知厨房（S2）集合中，我们在Top-1动词（+10.75）、名词（+5.84）和动作（+2.87）预测上也取得了显著改进。在EGTEA Gaze+数据集上也观察到了类似趋势，在名词、动词和动作预测上分别获得了+9.9、+13.1和+6.8的绝对提升。通过提交本文，我们的方法目前是EK55和EGTEA Gaze+上动作预测的最新最先进方法，参见https://competitions.codalab.org/competitions/20071#results。代码可在https://github.com/debadityaroy/Abstract_Goal获取。
英文摘要：
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
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
