人群场景的属性--Deeply Learned Attributes for Crowded Scene Understandin
2017-09-13 15:21
921 查看
Deeply Learned Attributes for Crowded Scene Understanding CVPR2015
http://www.ee.cuhk.edu.hk/~jshao/WWWCrowdDataset.html
https://github.com/amandajshao/www_deep_crowd
本文要解决的问题是什么了? 给你一段人群场景的视频,算法能否给出关于这段视频的一些信息?
能否回答下面三个问题?“ Who is in the crowd?”, “Where is the crowd?”, and “Why is crowd here?“
文章总体的流程如下:针对这个问题建立了一个大的数据库,WWW Crowd dataset with 10,000 videos from 8,257 crowded scenes,然后我们对这个数据库人工标记了94个属性,这94个属性是关于上面三个问题 Who Where Why 的 。 接着我们设计了一个 CNN网络 将上面的问题变成一个 CNN分类问题,CNN的输出是 94 类。这里CNN的输入包括两个部分: appearance and motion channels
下面首先来看看我们这个 WWW Crowd dataset 数据库
各个数据库的对比:
94个属性标签主要 分为 三类:
3 types of attributes: (1) Where (e.g. street, temple, and classroom), (2) Who (e.g. star, protester, and skater), and (3) Why (e.g. walk, board, and ceremony).
ticket counter, street, escalator, stadium, concert, stage, landmark, square, school, beach,
park, rink, church, conference center, classroom, temple, battlefield, runway, restaurant,
customer, passenger, pedestrian, audience, performer, conductor, choir, dancer, model,
photographer, star, speaker, protester, mob, parader, police, soldier, student, teacher,
runner, skater, swimmer, pilgrim, newly-wed couple, queue, stand, sit, kneel, walk, run,
wave, applaud, cheer, ride, swim, skate, dance, photograph, board, wait, buy ticket, check-
in/out, watch performance, performance, band performance, chorus, red-carpet show, fashion
show, war, fight, protest, disaster, parade, carnival, ceremony, speech, graduation,
conference, attend classes, wedding, marathon, picnic, pilgrimage, shopping, stock exchange,
dining, cut the ribbon
人工标记实例:
我们使用的CNN模型
两个网络分支具有相同的结构:Conv(96,7,2)-ReLU-Pool(3,2)-Norm(5)-Conv(256,5,2)-ReLU-Pool(3,2)-Norm(5)-Conv(384,3,1)-ReLU-Conv(384,3,1)-ReLU-
Conv(256,3,1)-ReLU-Pool(3,2)-FC(4096).
最后两个分支合并得到 FC(8192)-FC(94)-Sig producing 94 attribute probability predictions
4.2. Motion Channels
接着分别介绍了 Collectiveness Stability Conflict 的定义和计算
5 Experimental Results
deep learned static features (DLSF)
deeply learned motion features (DLMF)
AUC of each attribute obtained with DLSF+DLMF
Good and bad attribute prediction examples
Compare deeply learned features with baselines
Six attributes predicted by DLSF, DLMF, and DLSF + DLMF
http://www.ee.cuhk.edu.hk/~jshao/WWWCrowdDataset.html
https://github.com/amandajshao/www_deep_crowd
本文要解决的问题是什么了? 给你一段人群场景的视频,算法能否给出关于这段视频的一些信息?
能否回答下面三个问题?“ Who is in the crowd?”, “Where is the crowd?”, and “Why is crowd here?“
文章总体的流程如下:针对这个问题建立了一个大的数据库,WWW Crowd dataset with 10,000 videos from 8,257 crowded scenes,然后我们对这个数据库人工标记了94个属性,这94个属性是关于上面三个问题 Who Where Why 的 。 接着我们设计了一个 CNN网络 将上面的问题变成一个 CNN分类问题,CNN的输出是 94 类。这里CNN的输入包括两个部分: appearance and motion channels
下面首先来看看我们这个 WWW Crowd dataset 数据库
各个数据库的对比:
94个属性标签主要 分为 三类:
3 types of attributes: (1) Where (e.g. street, temple, and classroom), (2) Who (e.g. star, protester, and skater), and (3) Why (e.g. walk, board, and ceremony).
Crowd Attribute List (94)
indoor, outdoor, bazaar, shopping mall, stock market, airport, platform, (subway)passageway,ticket counter, street, escalator, stadium, concert, stage, landmark, square, school, beach,
park, rink, church, conference center, classroom, temple, battlefield, runway, restaurant,
customer, passenger, pedestrian, audience, performer, conductor, choir, dancer, model,
photographer, star, speaker, protester, mob, parader, police, soldier, student, teacher,
runner, skater, swimmer, pilgrim, newly-wed couple, queue, stand, sit, kneel, walk, run,
wave, applaud, cheer, ride, swim, skate, dance, photograph, board, wait, buy ticket, check-
in/out, watch performance, performance, band performance, chorus, red-carpet show, fashion
show, war, fight, protest, disaster, parade, carnival, ceremony, speech, graduation,
conference, attend classes, wedding, marathon, picnic, pilgrimage, shopping, stock exchange,
dining, cut the ribbon
人工标记实例:
我们使用的CNN模型
两个网络分支具有相同的结构:Conv(96,7,2)-ReLU-Pool(3,2)-Norm(5)-Conv(256,5,2)-ReLU-Pool(3,2)-Norm(5)-Conv(384,3,1)-ReLU-Conv(384,3,1)-ReLU-
Conv(256,3,1)-ReLU-Pool(3,2)-FC(4096).
最后两个分支合并得到 FC(8192)-FC(94)-Sig producing 94 attribute probability predictions
4.2. Motion Channels
接着分别介绍了 Collectiveness Stability Conflict 的定义和计算
5 Experimental Results
deep learned static features (DLSF)
deeply learned motion features (DLMF)
AUC of each attribute obtained with DLSF+DLMF
Good and bad attribute prediction examples
Compare deeply learned features with baselines
Six attributes predicted by DLSF, DLMF, and DLSF + DLMF
相关文章推荐
- Deeply Learned Attributes for Crowded Scene Understanding(WWW dataset)
- Deeply Learned Attributes for Crowded Scene Understanding
- DeepID2+:Deeply Learned Attributes for Crowded Scene Understanding
- 论文笔记:Chaotic Invariants of Lagrangian Particle Trajectories for Anomaly Detection in Crowded Scenes
- 论文笔记:Chaotic Invariants of Lagrangian Particle Trajectories for Anomaly Detection in Crowded Scenes
- 列出对像属性,for(var i in obj)[转]
- In Gradle projects, always use http://schemas.android.com/apk/res-auto for custom attributes more..
- 使用for..in时会遍历对象原型中的自定义属性
- for in枚举属性
- 列出对像属性,for(var i in obj)
- 列出对像属性,for(var i in obj)
- 使用自定义属性报错 No resource identifier found for attribute 'widthFactor' in package
- 如何使用th:each属性迭代模板-原标题:How To Use th:each For Iteration In Thymeleaf Template?
- DL-SFA: Deeply-Learned Slow Feature Analysis for Action Recognition(泛读)
- [Javascript]xmlhttp的对象方法属性,用for x in obj的方法得到
- linux报错jar包时出现“Exception in thread "main" java.lang.SecurityException: Invalid signature file digest for Manifest main attributes”
- 如何用th:attr标签在thymeleaf模板中设置属性-原标题:How To Set Attributes in Thymeleaf Template using th:attr?
- Use Matadata file to add attributes for properties in Ria service
- 年龄及性别预测(2)AgeNet: Deeply Learned Regressor and Classifier for Robust Apparent Age Estimation
- Javascript中的for in语句获取对象属性的顺序问题