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.".
翻译:识别不同对象(人和杯)本身是一个重要问题,但识别它们之间的关系(持有)对于许多真实世界使用的案例至关重要。 本文描述了减少视觉关系探测问题的方法, 以降低目标探测问题的视觉关系探测问题。 这种方法适用于谷歌 AI 开放图像 V4 视觉关系跟踪挑战, 该方法与2018年欧洲计算机愿景会议(ECCV 2018)同时举行, 并且以获奖者的身份完成。 挑战在于构建一种算法, 检测特定关系中的两对对象: 比如“ 女人弹吉他 ” 、 “ 啤酒在桌上 ” 或“ 汽车内狗 ” 。