arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1809.09828cs.CV
收藏

一种视觉关系检测的问题约简方法

A Problem Reduction Approach for Visual Relationships Detection

Toshiyuki Fukuzawa

摘要:

识别不同的对象(人和杯子)本身就是一个重要的问题,但是识别它们之间的关系(拿着)对于许多现实世界的用例来说是至关重要的。本文描述了一种将视觉关系检测问题简化为目标检测问题的方法。该方法被应用于Google AI Open Images V4 Visual Relationship Track Challenge,该挑战赛与2018年欧洲计算机视觉会议(ECCV 2018)联合举办,并最终获奖。挑战在于建立一种算法,检测特定关系中的成对对象:比如“女人弹吉他”、“桌上的啤酒”或“车里的狗”。".

英文摘要:

Identifying different objects (man and cup) is an important problem on its own, but identifying the relationship between them (holding) is critical for many real world use cases. This paper describes an approach to reduce a visual relationship detection problem to object detection problems. The method was applied to Google AI Open Images V4 Visual Relationship Track Challenge, which was held in conjunction with 2018 European Conference on Computer Vision (ECCV 2018) and it finished as a prize winner. The challenge was to build an algorithm that detects pairs of objects in particular relations: things like "woman playing guitar," "beer on table," or "dog inside car.".

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。

↑