行人属性“Attribute Recognition by Joint Recurrent Learning of Context and Correlation”
应该是比较新的属性学习文章了，ICCV2017。在监控场景中进行行人属性的识别，主要遇到的挑战是图像质量差，外形变化及属性可能在不同的空间位置，标记的训练样本少。论文提出JRL模型挖掘属性上下文信息及属性间相互关系提升识别准确率。JRL在一张行人图像内学习属性相关性，具体的说是属性预测顺序的相互关联性。 解决属性预测遇到挑战的方法，一是使用属性的相关性：如“女性”和“裙子”在一张行人图像中出现的可
相关文章
- 1. Grouping Attribute Recognition for Pedestrian with Joint Recurrent Learning
- 2. Mix and Match: Joint Model for Clothing and Attribute Recognition
- 3. Attribute-Recognition行人属性识别资料
- 4. 行人属性“Weakly-supervised Learning of Mid-level Features for Pedestrian Attribute Recognition and Loca”
- 5. 行人属性“Multi-attribute Learning for Pedestrian Attribute Recognition in Surveillance Scenarios”
- 6. 行人属性“Human Attribute Recognition by Deep Hierarchical Contexts”
- 7. 《Joint Learning of Named Entity Recognition and Entity Linking》论文笔记
- 8. Context Encoders: Feature Learning by Inpainting
- 9. 行人属性识别：Improving Pedestrian Attribute Recognition With Weakly-Supervised Multi-Scale Attribute……
- 10. 阅读笔记 CCL: Cross-modal Correlation Learning with Multi-grained Fusion by Hierarchical Network
- 更多相关文章...
- • C# 特性（Attribute） - C#教程
- • XSLT
- • JDK13 GA发布：5大特性解读
- • RxJava操作符（七）Conditional and Boolean
相关标签/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
欢迎关注本站公众号,获取更多信息
相关文章
- 1. Grouping Attribute Recognition for Pedestrian with Joint Recurrent Learning
- 2. Mix and Match: Joint Model for Clothing and Attribute Recognition
- 3. Attribute-Recognition行人属性识别资料
- 4. 行人属性“Weakly-supervised Learning of Mid-level Features for Pedestrian Attribute Recognition and Loca”
- 5. 行人属性“Multi-attribute Learning for Pedestrian Attribute Recognition in Surveillance Scenarios”
- 6. 行人属性“Human Attribute Recognition by Deep Hierarchical Contexts”
- 7. 《Joint Learning of Named Entity Recognition and Entity Linking》论文笔记
- 8. Context Encoders: Feature Learning by Inpainting
- 9. 行人属性识别：Improving Pedestrian Attribute Recognition With Weakly-Supervised Multi-Scale Attribute……
- 10. 阅读笔记 CCL: Cross-modal Correlation Learning with Multi-grained Fusion by Hierarchical Network