共被期刊论文引用了2次
您的检索式：您选中1篇文献正在查看引证文献汇总
|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Uncertainty-optimized deep learning model for small-scale person re-identification显示文摘In recent years, deep learning has developed rapidly and is widely used in various fields, such as computer vision, speech recognition, and natural language processing. For end-to-end person re-identification,most deep learning methods rely on large-scale datasets. Relatively few methods work with small-scale datasets. Insufficient training samples will affect neural network accuracy significantly. This problem limits the practical application of person re-identification. For small-scale person re-identification, the uncertainty of person representation and the overfitting problem associated with deep learning remain to be solved.Quantifying the uncertainty is difficult owing to complex network structures and the large number of hyperparameters. In this study, we consider the uncertainty of pedestrian representation for small-scale person re-identification. To reduce the impact of uncertain person representations, we transform parameters into distributions and conduct multiple sampling by using multilevel dropout in a testing process. We design an improved Monte Carlo strategy that considers both the average distance and shortest distance for matching and ranking. When compared with state-of-the-art methods, the proposed method significantly improve accuracy on two small-scale person re-identification datasets and is robust on four large-scale datasets. | Cairong ZHAO Kang CHEN Di ZANG Zhaoxiang ZHANG Wangmeng ZUO Duoqian MIAO | 2019 | Science China(Information Sciences)2019，62，12： | 6 |
| 2 | 基于人体骨架信息的行人再识别研究综述显示文摘行人再识别的主要任务是利用计算机视觉从不同的摄像机中检索出相同身份的人,对特定的行人进行匹配和检索,此研究可以广泛应用于智能视频监控、智能安保等领域。相比于其他易受改变的人体外观特征,提取人的骨架信息作为鉴别特征更具有鲁棒性。为了了解该领域的发展现状,辅助该领域的研究者们进行更深入的探索,本文重点研究了基于人体骨架信息的行人再识别方法,根据算法包含的特征信息,将其分为独立式和混合式,混合式除人体骨架信息外还分别包括RGB-D图像特征和步态特征,之后对不同方法进行了比较,其次在主要数据集上对不同方法进行了评估,最后对此研究的问题与挑战进行了总结并对未来发展趋势进行了展望。 | 贾梦瑜 张继凯 马茹 吕晓琪 | 2023 | 光学精密工程2023，31，8： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员