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:
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:
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