The task of pedestrian re-identification aims to capture images belonging to the same individual from different camera viewpoints. In recent years, supervised methods for pedestrian re-identification have made significant progress. However, these methods rely on a large and expensive labeled dataset. As a result, more and more researchers are focusing on unsupervised learning. Compared to supervised learning, unsupervised learning is more applicable to real-world scenarios and thus has greater research value

帮我把下面这段话按照论文的风格翻译成英文:行人重识别的任务目标是从跨摄像头视角中捕获属于同一个行人的图像。近年来有监督行人重识别方法取得了显著进展但是它们依赖于大量且昂贵的标签数据。因此越来越多的人投入到研究无监督学习中。与有监督学习相比无监督学习更贴近真实的应用场景因此具有更大的研究价值。

原文地址: https://www.cveoy.top/t/topic/cnrG 著作权归作者所有。请勿转载和采集!

免费AI点我,无需注册和登录