论文标题
诊断人类对象互动检测的罕见性
Diagnosing Rarity in Human-Object Interaction Detection
论文作者
论文摘要
人类对象相互作用（HOI）检测是计算机视觉中的核心任务。目的是将所有人类对象对定位并认识到它们的相互作用。由<动词，名词培训定义的相互作用会导致长尾视觉识别挑战，因为许多组合很少代表。拟议模型的性能尤其是限制在尾巴类别中，但是几乎没有做到理解原因。为此，在本文中，我们建议诊断HOI检测中的稀有性。我们提出了一个三步策略，即检测，识别和识别，在其中我们通过研究最先进的模型仔细分析了限制因素。我们的发现表明，检测和识别步骤会因遮挡和相对位置等相互作用信号而改变，从而限制了识别精度。
Human-object interaction (HOI) detection is a core task in computer vision. The goal is to localize all human-object pairs and recognize their interactions. An interaction defined by a <verb, noun> tuple leads to a long-tailed visual recognition challenge since many combinations are rarely represented. The performance of the proposed models is limited especially for the tail categories, but little has been done to understand the reason. To that end, in this paper, we propose to diagnose rarity in HOI detection. We propose a three-step strategy, namely Detection, Identification and Recognition where we carefully analyse the limiting factors by studying state-of-the-art models. Our findings indicate that detection and identification steps are altered by the interaction signals like occlusion and relative location, as a result limiting the recognition accuracy.
