Describing People: A Poselet-Based Approach to Attribute Classification
来源:互联网 发布:预测算法有哪些 编辑:程序博客网 时间:2024/06/05 08:05
原文链接
1. Abstract
Use a part-based approach based on poselets.(Poselets is proposed by Lubomir Bourdev in 2009)
2. Introduce
Convert finegrained to attribute classification problem. For one attribute, we need to conbine many cues. For classification, detecting and aligning the parts is of much importance. But localizing body parts is a tough task.
The training input is a set of images in which the people of interset are specified via their visible bounds and the values of their attributes. Use a three layer feed-forward network. Three layers mean three steps of work. This layer is not the layer in deep learning.
In the first layer(first step), predict 9 attributes(is-male, has-hat, has-t-shirt,…) for each human part.
In the second layer(second step), combine information from all such predictions, as the gender given the face, the leges, and other parts, into one single attribute classification.
In the third layer(third layer), leverage dependencies between different attributes, such as the fact that gender is correlated with the presence of long hair.
In fact, this article regards poselets as a general tool for decomposing the viewpoint and pose.
3. Algorithm
Step 1
Detect the poselets on the test image and get
Step 2
For each poselet type i, extract a feature vector consisting of HOG cells at three, a color histogram and skin-mask features.
Step 3(first layer)
For each poselet type i and each attribute j, evalute a classifier
Step 4(second layer)
For the output of poselet-level attribute classifiers, we zero-center them(move the center to zero) and modulate them by the poselet detection probabilities
Step 5(third layer)
For each attribute j, evalute a third classifier called context-level attribute classifier. Input feature vector is the scores of all person-level classifiers for all attributes
- Describing People: A Poselet-Based Approach to Attribute Classification
- DefaultValue Attribute Based Approach to Property Initializaton
- 联合Tag-Label的推荐方法:A Joint Approach to Label Classification and Tag Tecommendation
- How to create LOV on a reference attribute (a different approach)
- A Model -Based Approach to Automated Testing of Access Control Policies
- A Three-Phase Approach to Document Clustering Based on Topic Significance Degree
- 《A Fragment-Based Approach to Object Representation and Classifiacation》阅读翻译
- English notes for Describing People
- A new approach to China
- An Efficient Shape-Based Approach to Image Retrieval
- Describing a Maven Plugin
- Ajax: A New Approach to Web Applications
- Ajax: A New Approach to Web Applications
- Ajax: A New Approach to Web Applications
- Ajax: A New Approach to Web Applications
- Ajax: A New Approach to Web Applications
- Ajax: A New Approach to Web Applications
- Ajax: A New Approach to Web Applications
- RecyclerView 之notifyDataSetChanged的暴躁
- SQLite文件格式初步分析之记录格式
- windows下安装redis
- Codeforces Round #374 (Div. 2) D. Maxim and Array
- 前端学习 按钮制作
- Describing People: A Poselet-Based Approach to Attribute Classification
- 27. 安全 HTTP (2)
- 异常笔试题
- hibernate映射文件??.hbm.xml配置映射元素详解--Hibernate映射类型
- oncreate方法中无法播放声音
- 关于keil4中:warning C316:unterminated conditionals
- Android笔试面试题二(常考问答)
- 能够提高开发效率的 Eclipse 实用操作
- android studio编译异常Error:Failed to resolve: