Multi-Task Learning via Co-Attentive Sharing for Pedestrian Attribute Recognition

时间 2021-01-06

标签行人属性繁體版

原文原文链接

动机：为了在两个单独的任务网络之间共享特征表示，传统的方法，如Cross-Stitch和Sluice网络学习特征或特征子空间的线性组合。然而，线性组合排除了通道之间复杂的相互依赖关系。此外，空间信息交换的考虑较少。贡献：提出了一种新的共注意共享(co - Sharing, CAS)模块，该模块提取识别通道和空间区域，从而在行人属性识别中实现两个任务网络之间更有效的特征共享。它包括三个分支:协

>>阅读原文<<

1. Grouping Attribute Recognition for Pedestrian with Joint Recurrent Learning
2. 行人属性“Multi-attribute Learning for Pedestrian Attribute Recognition in Surveillance Scenarios”
3. Pedestrian Attribute Recognition via Hierarchical Multi-task Learning and Relationship Attention
4. A Temporal Attentive Approach for Video-Based Pedestrian Attribute Recognition
5. [笔记] Pedestrian Attribute Recognition Dataset Summary
6. 行人属性“Weakly-supervised Learning of Mid-level Features for Pedestrian Attribute Recognition and Loca”
7. A multi-branch separable convolution neural network for pedestrian attribute recognition
8. 行人属性识别：A Temporal Attentive Approach for Video-Based Pedestrian Attribute Recognition
9. Pose Guided Deep Model for Pedestrian Attribute Recognition in Surveillance Scenarios
10. [论文复现]A Richly Annotated Dataset for Pedestrian Attribute Recognition
更多相关文章...
• C# 特性（Attribute） - C#教程
• Swift for 循环 - Swift 教程
• Java Agent入门实战（三）-JVM Attach原理与使用
• Java Agent入门实战（一）-Instrumentation介绍与使用

最新文章

1. [最佳实践]了解 Eolinker 如何助力远程办公
2. katalon studio 安装教程
3. 精通hibernate（harness hibernate oreilly）中的一个”错误“
4. ECharts立体圆柱型
5. 零拷贝总结
6. 6 传输层
7. Github协作图想
8. Cannot load 32-bit SWT libraries on 64-bit JVM
9. IntelliJ IDEA 找其历史版本
10. Unity3D(二)游戏对象及组件

本站公众号

欢迎关注本站公众号,获取更多信息

1. Grouping Attribute Recognition for Pedestrian with Joint Recurrent Learning
2. 行人属性“Multi-attribute Learning for Pedestrian Attribute Recognition in Surveillance Scenarios”
3. Pedestrian Attribute Recognition via Hierarchical Multi-task Learning and Relationship Attention
4. A Temporal Attentive Approach for Video-Based Pedestrian Attribute Recognition
5. [笔记] Pedestrian Attribute Recognition Dataset Summary
6. 行人属性“Weakly-supervised Learning of Mid-level Features for Pedestrian Attribute Recognition and Loca”
7. A multi-branch separable convolution neural network for pedestrian attribute recognition
8. 行人属性识别：A Temporal Attentive Approach for Video-Based Pedestrian Attribute Recognition
9. Pose Guided Deep Model for Pedestrian Attribute Recognition in Surveillance Scenarios
10. [论文复现]A Richly Annotated Dataset for Pedestrian Attribute Recognition

>>更多相关文章<<