|
|
|
|
|
Shengyu Pei and Xiaoping Fan
Existing person re-recognition (Re-ID) methods usually suffer from poor generalization capability and over-fitting problems caused by insufficient training samples. We find that high-level attributes, semantic information, and part-based local informatio...
ver más
|
|
|
|
|
|
|
|
|
Jacobo González-Cepeda, Álvaro Ramajo and José María Armingol
Security cameras have been proven to be particularly useful in preventing and combating crime through identification tasks. Here, two areas can be mainly distinguished: person and vehicle identification. Automatic license plate readers are the most widel...
ver más
|
|
|
|
|
|
|
|
|
Zhou Lei, Kangkang Yang, Kai Jiang and Shengbo Chen
Person re-Identification(Re-ID) based on deep convolutional neural networks (CNNs) achieves remarkable success with its fast speed. However, prevailing Re-ID models are usually built upon backbones that manually design for classification. In order to aut...
ver más
|
|
|
|
|
|
|
|
|
Chengyan Zhong, Guanqiu Qi, Neal Mazur, Sarbani Banerjee, Devanshi Malaviya and Gang Hu
Due to the variation in the image capturing process, the difference between source and target sets causes a challenge in unsupervised domain adaptation (UDA) on person re-identification (re-ID). Given a labeled source training set and an unlabeled target...
ver más
|
|
|
|
|
|
|
|
|
Shaojun Wu and Ling Gao
Most supervised person re-identification methods show their excellent performance, but using labeled datasets is very expensive, which limits its application in practical scenarios. To solve the scalability problem, we propose a Cross-camera Erased Featu...
ver más
|
|
|
|