arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.13682cs.CV
收藏

HOTR:使用Transformers的端到端人机交互检测

HOTR: End-to-End Human-Object Interaction Detection with Transformers

Kakao Brain;Korea University(高丽大学)

Bumsoo Kim, Junhyun Lee, Jaewoo Kang, Eun-Sol Kim, Hyunwoo J. Kim

摘要:

人-物体交互(HOI)检测是识别图像中的“一组交互”的任务,其涉及i)对象的定位(即,人)和目标(即,对象)的交互,以及ii)交互标签的分类。大多数现有的方法间接地解决了这个任务,通过检测人和对象的实例,并单独推断每对检测到的实例。在本文中,我们提出了一种新的框架,称为HOTR,它直接预测一组<人,对象,互动>三元组从一个Transformer编码器-解码器架构的基础上的图像。通过集合预测,我们的方法有效地利用了图像中固有的语义关系,并且不需要耗时的后处理,这是现有方法的主要瓶颈。我们提出的算法实现了国家的最先进的性能在两个HOI检测基准与推理时间在1 ms以下的目标检测后。

英文摘要:

Human-Object Interaction (HOI) detection is a task of identifying "a set of interactions" in an image, which involves the i) localization of the subject (i.e., humans) and target (i.e., objects) of interaction, and ii) the classification of the interaction labels. Most existing methods have indirectly addressed this task by detecting human and object instances and individually inferring every pair of the detected instances. In this paper, we present a novel framework, referred to by HOTR, which directly predicts a set of <human, object, interaction> triplets from an image based on a transformer encoder-decoder architecture. Through the set prediction, our method effectively exploits the inherent semantic relationships in an image and does not require time-consuming post-processing which is the main bottleneck of existing methods. Our proposed algorithm achieves the state-of-the-art performance in two HOI detection benchmarks with an inference time under 1 ms after object detection.

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。

↑