https://111qqz.com/en/tags/reid/Recent content in Reid on 111qqz's blogHugo -- gohugo.ioen© 2015-2026 111qqzSat, 24 Feb 2018 04:34:02 +0000https://111qqz.com/en/post/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0/%E8%AE%A1%E7%AE%97%E6%9C%BA%E8%A7%86%E8%A7%89/2018-02-24-reid-task-notes/Sat, 24 Feb 2018 04:34:02 +0000https://111qqz.com/en/post/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0/%E8%AE%A1%E7%AE%97%E6%9C%BA%E8%A7%86%E8%A7%89/2018-02-24-reid-task-notes/<p>被师兄（同事？）普及了一番实验规范orz&hellip;</p> <p>我还是太年轻了</p>https://111qqz.com/en/post/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0/%E8%AE%A1%E7%AE%97%E6%9C%BA%E8%A7%86%E8%A7%89/2018-02-22-pose-driven-deep-convolutional-model-for-person-re-identification/Thu, 22 Feb 2018 02:25:00 +0000https://111qqz.com/en/post/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0/%E8%AE%A1%E7%AE%97%E6%9C%BA%E8%A7%86%E8%A7%89/2018-02-22-pose-driven-deep-convolutional-model-for-person-re-identification/<p><a href="https://arxiv.org/abs/1709.08325" target="_blank" rel="noreferrer">1709.08325</a></p> <p>Reid问题指的是判断一个probe person 是否在被不同的camera捕获的gallery person 中出现。</p>https://111qqz.com/en/post/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0/%E8%AE%A1%E7%AE%97%E6%9C%BA%E8%A7%86%E8%A7%89/2018-02-17-persion-reid-paper-list/Sat, 17 Feb 2018 07:17:49 +0000https://111qqz.com/en/post/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0/%E8%AE%A1%E7%AE%97%E6%9C%BA%E8%A7%86%E8%A7%89/2018-02-17-persion-reid-paper-list/<p>Key:</p> <p>(1). Pose-driven, body part alignment, combine whole feature and body part feature, focus on alignment of part model,</p> <p>(2). Combine image label and human attributes classes, do classification with attributes and identity learning</p>