|
| 论文编号: |
|
| 第一作者所在部门: |
|
| 中文论文题目: |
Multi-label convolutional neural network based pedestrian attribute classification
|
| 英文论文题目: |
Multi-label convolutional neural network based pedestrian attribute classification
|
| 论文题目英文: |
|
| 作者: |
Zhu, Jianqing
|
| 论文出处: |
|
| 刊物名称: |
IMAGE AND VISION COMPUTING
|
| 年: |
2017
|
| 卷: |
58 |
| 期: |
|
| 页: |
224-229 |
| 联系作者: |
|
| 收录类别: |
|
| 影响因子: |
|
| 摘要: |
Recently, pedestrian attributes like gender, age, clothing etc., have been used as soft biometric traits for recognizing people. Unlike existing methods that assume the independence of attributes during their prediction, we propose a multi-label convolutional neural network(MLCNN) to predict multiple attributes together in a unified framework. Firstly, a pedestrian image is roughly divided into multiple overlapping body parts, which are simultaneously integrated in the multi-label convolutional neural network. Secondly, these parts are filtered independently and aggregated in the cost layer. The cost function is a combination of multiple binary attribute classification cost functions. Experiments show that the proposed method significantly outperforms the SVM based method on the PETA database. (C) 2016 Elsevier B.V. All rights reserved. |
| 英文摘要: |
|
| 外单位作者单位: |
|
| 备注: |
|
关闭窗口 |
|
