arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.05728cs.CV
收藏

人机交互检测中的稀有性诊断

Diagnosing Rarity in Human-Object Interaction Detection

QUvA Deep Vision Lab(QUvA深度视觉实验室)

Mert Kilickaya, Arnold Smeulders

摘要:

人机交互检测是计算机视觉的核心任务。我们的目标是定位所有的人-物对,并识别它们之间的交互。由<verb,noun>元组定义的交互导致长尾视觉识别挑战,因为许多组合很少表示。所提出的模型的性能是有限的,特别是对于尾部类别,但很少有人做,以了解原因。为此,在本文中,我们建议诊断罕见的HOI检测。我们提出了一个三步策略,即检测,识别和识别,我们通过研究最先进的模型来仔细分析限制因素。我们的研究结果表明,检测和识别步骤被相互作用信号(如遮挡和相对位置)改变,从而限制了识别精度。

英文摘要:

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.

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。

↑