论文标题
互动自然语言的人搜索
Interactive Natural Language-based Person Search
论文作者
论文摘要
在这项工作中，我们考虑了在不受限制的环境中以自然语言描述在不受限制的环境中搜索人员的问题。具体而言，我们研究了如何系统地设计算法以有效地从人类那里获取描述。通过适应模型，用于视觉和语言理解，以一种原则性的方式搜索感兴趣的人（POI），提出了一种算法，从而实现了有希望的结果，而无需重新设计另一个复杂的模型。然后，我们研究了一种迭代问题 - QA（QA）策略，该策略使机器人能够从用户那里索取有关POI出现的其他信息。为此，我们引入了一种贪婪的算法，以根据其重要性对问题进行排名，并使该算法能够根据模型的不确定性动态调整人类机器人相互作用的长度。我们的方法不仅在基准数据集上，还可以在移动机器人上验证，在动态和拥挤的环境中移动。
In this work, we consider the problem of searching people in an unconstrained environment, with natural language descriptions. Specifically, we study how to systematically design an algorithm to effectively acquire descriptions from humans. An algorithm is proposed by adapting models, used for visual and language understanding, to search a person of interest (POI) in a principled way, achieving promising results without the need to re-design another complicated model. We then investigate an iterative question-answering (QA) strategy that enable robots to request additional information about the POI's appearance from the user. To this end, we introduce a greedy algorithm to rank questions in terms of their significance, and equip the algorithm with the capability to dynamically adjust the length of human-robot interaction according to model's uncertainty. Our approach is validated not only on benchmark datasets but on a mobile robot, moving in a dynamic and crowded environment.
