This paper addresses the problem of anticipating the next-active-object location in the future, for a given egocentric video clip where the contact might happen, before any action takes place. The problem is considerably hard, as we aim at estimating the position of such objects in a scenario where the observed clip and the action segment are separated by the so-called ``time to contact'' (TTC) segment. Many methods have been proposed to anticipate the action of a person based on previous hand movements and interactions with the surroundings. However, there have been no attempts to investigate the next possible interactable object, and its future location with respect to the first-person's motion and the field-of-view drift during the TTC window. We define this as the task of Anticipating the Next ACTive Object (ANACTO). To this end, we propose a transformer-based self-attention framework to identify and locate the next-active-object in an egocentric clip. We benchmark our method on three datasets: EpicKitchens-100, EGTEA+ and Ego4D. We also provide annotations for the first two datasets. Our approach performs best compared to relevant baseline methods. We also conduct ablation studies to understand the effectiveness of the proposed and baseline methods on varying conditions. Code and ANACTO task annotations will be made available upon paper acceptance.

翻译：本文探讨了在给定第一人称视频片段中，在任何动作发生之前，预测未来可能发生接触的下一个活动对象位置的问题。该问题极具挑战性，因为我们的目标是估计在观察到的片段与动作段之间存在所谓“接触时间”（TTC, Time to Contact）间隔的 scenario 中这些对象的位置。已有许多方法基于先前的手部运动及与环境的交互来预测人的动作。然而，尚未有研究尝试探究在TTC窗口内，基于第一人称的运动及视场漂移，下一个可能的可交互对象及其未来位置。我们将此定义为“下一活动对象预测”（ANACTO, Anticipating the Next ACTive Object）任务。为此，我们提出了一种基于Transformer的自注意力框架，用于在第一人称视频片段中识别并定位下一个活动对象。我们在EpicKitchens-100、EGTEA+和Ego4D三个数据集上对我们的方法进行了基准测试，并为前两个数据集提供了标注。与相关基线方法相比，我们的方法取得了最佳性能。我们还进行了消融研究，以理解所提出方法及基线方法在不同条件下的有效性。代码及ANACTO任务标注将在论文接收后公开。