摘要:
Motivation 图像经过CNN进行分类,FC层内的权重向量往往具有很高的相关性。原因有二:①训练样本的分布不是标准的(non-uniform distribution of training samples),如图一中绿色和黑色的虚线向量经过权重矩阵映射后得到红色、紫红色和蓝色的实线向量,其中 阅读全文
摘要:
Title: Person Re-Identification Using CNN Features Learned from Combination of Attributes Authors: Tetsu Matsukawa, Einoshin Suzuki Affliation: Facult 阅读全文
摘要:
Papers about "Person Re-Identification" via deep learning methods 行人重识别深度学习方法相关论文整理 阅读全文
摘要:
Authors:Tong Xiao, Hongsheng Li, Wanli Ouyang, Xiaogang Wang PDF 一篇很好的文章 我水平有限,首次在person reid中看到domain 前面的文章(见整理)都是采用孪生网络或者triplet网络,计算图像之间的相似性,以此判断是否 阅读全文
摘要:
研究生导师:这种学生,才是我眼中的科研好苗子! 阅读全文
摘要:
Title: Person re-identifcation by multi-channel parts-based cnn with improved triplet loss function Authors: De Cheng, Yihong Gong, Sanping Zhou, Jinj 阅读全文
摘要:
Title: A Siamese Long Short-Term Memory Architecture for Human Re-Identification Authors: Rahul Rama Variora1, Bing Shuaia1, Jiwen Lub2, Dong Xuc3, Ga 阅读全文
摘要:
RNN 莫烦Python视频 | LSTM 莫烦Python视频 | [译] 理解 LSTM 网络 | 详解 LSTM | LSTM python 代码 ↓ 阅读全文
摘要:
Title: PersonNet: Person Re-identification with Deep Convolutional Neural Networks Authors: Lin Wu, Chunhua Shen, Anton van den Hengel 论文地址 论文主要是在另一篇文 阅读全文
摘要:
Title: Scalable Person Re-identification: A Benchmark Authors: Liang Zheng13∗, Liyue Shen1∗, Lu Tian1∗, Shengjin Wang1 , Jingdong Wang3 , Qi Tian2 Aff 阅读全文