arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.06358cs.CV
收藏

面向第一人称视频的下一主动对象预测

Anticipating Next Active Objects for Egocentric Videos

Istituto Italiano di Tecnologia (IIT)(意大利技术研究院);University of Genoa(热那亚大学);University of Trento(特伦托大学);University of Verona(维罗纳大学)

Sanket Thakur, Cigdem Beyan, Pietro Morerio, Vittorio Murino, Alessio Del Bue

AI总结:

本文提出ANACTO任务,利用基于Transformer的自注意力框架预测第一人称视频中下一主动对象的位置,并在多个数据集上取得优于基线方法的效果。

摘要:

本文研究的问题是:给定一段第一人称视频片段,在可能发生接触但尚未发生任何动作之前,预测未来下一主动对象的位置。该问题相当困难,因为我们要在观测片段与动作片段被所谓的“接触时间”(TTC)片段分隔开的情况下,估计这些对象的位置。已有许多方法基于先前的手部运动以及与周围环境的交互来预测人的动作。然而,目前还没有工作尝试研究下一个可能可交互的对象,以及其在第一人称运动与TTC窗口期间视场漂移影响下的未来位置。我们将此任务定义为“预测下一主动对象”(ANACTO)。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主动对象。我们在三个数据集上对所提方法进行了基准测试:EpicKitchens-100、EGTEA+和Ego4D。我们还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,以理解所提方法和基线方法在不同条件下的有效性。代码和ANACTO任务标注将在论文被接收后公开。

英文摘要:

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.

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。

↑