人群场景的属性--Deeply Learned Attributes for Crowded Scene Understandin

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).

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

本文参与腾讯云自媒体分享计划,欢迎正在阅读的你也加入,一起分享。

发表于

我来说两句

0 条评论
登录 后参与评论

相关文章

来自专栏AI研习社

Github 项目推荐 | GAN 的 Keras 实现案例集合 —— Keras-GAN

该库收集了大量用 Keras 实现的 GAN 案例代码以及论文,地址: https://github.com/eriklindernoren/Keras-GAN...

3458
来自专栏专知

【论文推荐】最新八篇生成对抗网络相关论文—离散数据生成、设计灵感、语音波形合成、去模糊、视觉描述、语音转换、对齐方法、注意力

【导读】专知内容组整理了最近八篇生成对抗网络(Generative Adversarial Networks )相关文章,为大家进行介绍,欢迎查看! 1.Cor...

3287
来自专栏机器学习人工学weekly

机器学习人工学weekly-2018/3/17

1. PyTorch构架分析 PyTorch – Internal Architecture Tour 链接:http://blog.christianper...

2957
来自专栏CreateAMind

Integration of Deep Learning and Neuroscience整合神经科学和深度学习

Neuroscience has focused on the detailed implementation of computation, studying...

1122
来自专栏人工智能LeadAI

长短时记忆网络LSTM(基本理论)

参考: Understanding LSTM Networks The Unreasonable Effectiveness of Recurrent Neu...

2764
来自专栏CreateAMind

互信息论文笔记

https://github.com/topics/mutual-information

1465
来自专栏大数据挖掘DT机器学习

深度学习、机器学习图像/人脸/字幕/自动驾驶数据集(Dataset)汇总

1. CIFAR-10 & CIFAR-100 CIFAR-10包含10个类别,50,000个训练图像,彩色图像大小:32x32,10,000个测试图像...

4915
来自专栏机器之心

资源 | 生成对抗网络新进展与论文全集

选自GitHub 参与:蒋思源、吴攀 生成对抗网络(GAN)是近段时间以来最受研究者关注的机器学习方法之一,深度学习泰斗 Yann LeCun 就曾多次谈到 这...

36911
来自专栏专知

【干货】GAN调研:多极扩展(跨域和条件的GAN扩展模型调研)

本文授权转载于知乎专栏作者:陈乐天 https://zhuanlan.zhihu.com/p/32103958 【摘要】 本文关注跨域(cross-domain...

2887
来自专栏专知

【20180511】专知AI干货资料推荐,论文、代码、教程等

2082

扫码关注云+社区