arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2003.10469cs.CV
收藏

从视频中学习对象持久性

Learning Object Permanence from Video

Bar-Ilan University(巴伊兰大学);Tel Aviv University(特拉维夫大学);NVIDIA Research(英伟达研究院)

Aviv Shamsian, Ofri Kleinfeld, Amir Globerson, Gal Chechik

摘要:

对象永久性允许人们推理不可见对象的位置,通过理解它们即使在不直接感知时也会继续存在。对象持久性对于构建世界模型至关重要,因为自然视觉场景中的对象动态地相互遮挡和包含。发展心理学的深入研究表明,客体恒存是一项具有挑战性的任务,需要通过丰富的经验来学习。在这里,我们介绍从数据中学习对象持久性的设置。我们解释了为什么这个学习问题应该被分解为四个部分,其中对象是(1)可见的,(2)被遮挡,(3)被另一个对象包含,(4)被包含对象携带。第四子任务,其中目标对象由包含对象携带,是特别具有挑战性的,因为它需要一个系统来推理不可见对象的移动位置。然后,我们提出了一个统一的深度架构,学习在这四种情况下预测对象的位置。我们在基于CATER的新数据集上评估了架构和系统,发现它优于以前的本地化方法和各种基线。

英文摘要:

Object Permanence allows people to reason about the location of non-visible objects, by understanding that they continue to exist even when not perceived directly. Object Permanence is critical for building a model of the world, since objects in natural visual scenes dynamically occlude and contain each-other. Intensive studies in developmental psychology suggest that object permanence is a challenging task that is learned through extensive experience. Here we introduce the setup of learning Object Permanence from data. We explain why this learning problem should be dissected into four components, where objects are (1) visible, (2) occluded, (3) contained by another object and (4) carried by a containing object. The fourth subtask, where a target object is carried by a containing object, is particularly challenging because it requires a system to reason about a moving location of an invisible object. We then present a unified deep architecture that learns to predict object location under these four scenarios. We evaluate the architecture and system on a new dataset based on CATER, and find that it outperforms previous localization methods and various baselines.

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。

↑