论文笔记之：Pedestrian Detection aided by Deep Learning Semantic Tasks

Pedestrian Detection aided by Deep Learning Semantic Tasks

CVPR 2015

本文考虑将语义任务（即：行人属性和场景属性）和行人检测相结合，以语义信息协助进行行人检测。先来看一下大致的检测结果（TA-CNN为本文检测结果）：

可以看出，由于有了属性信息的协助，其行人检测的精确度有了较大的提升。具体网络架构如下图所示：

时间： 2024-10-11 17:40:37

论文笔记之：Pedestrian Detection aided by Deep Learning Semantic Tasks的相关文章

Deep Learning（深度学习）学习笔记整理系列（三）——Deep Learning的基本思想

[email protected] http://blog.csdn.net/zouxy09 作者:Zouxy version 1.0 2013-04-08 1)该Deep Learning的学习系列是整理自网上很大牛和机器学习专家所无私奉献的资料的.具体引用的资料请看参考文献.具体的版本声明也参考原文献. 2)本文仅供学术交流,非商用.所以每一部分具体的参考资料并没有详细对应.如果某部分不小心侵犯了大家的利益,还望海涵,并联系博主删除. 3)本人才疏学浅,整理总结的时候难免出错,还望各位前辈

【论文笔记】Reading Scene Text in Deep Convolutional Sequences

论文来源:http://www.eecs.qmul.ac.uk/~ccloy/files/aaai_2016_reading.pdf 接收会议:AAAI 2016(the Association for the Advance of Artificial Intelligence)人工智能领域非常不错的一个会议. 论文架构: Abstract 1.Introduction 2.Related Work 3.Deep-Text Recurrent Networks (DTRN) 3.1 Seque

论文笔记之：Large Scale Distributed Semi-Supervised Learning Using Streaming Approximation

Large Scale Distributed Semi-Supervised Learning Using Streaming Approximation Google 官方 Blog 链接:https://research.googleblog.com/2016/10/graph-powered-machine-learning-at-google.html 今天讲的是一个基于 streaming approximation 的大规模分布式半监督学习框架,出自 Google . 摘要:众所周

Deep Learning Face Representation by Joint Identification-Verification

Deep Learning Face Representation by Joint Identification-Verification 转载请注明:http://blog.csdn.net/stdcoutzyx/article/details/41497545 这篇文章是论文Deep Learning Face Representation by Joint Identification-Verification的笔记. 1. Main Contribution 这篇论文使用deep le

Joint Deep Learning for Pedestrian Detection笔记

1.结构图 Introduction Feature extraction, deformation handling, occlusion handling, and classification are four important components in pedestrian detection. Existing methods learn or design these components either individually or sequentially. The inte

论文笔记之：From Facial Parts Responses to Face Detection: A Deep Learning Approach

From Facial Parts Responses to Face Detection: A Deep Learning Approach ICCV 2015

论文笔记 Deep Patch Learning for Weakly Supervised Object Classication and Discovery

Background 1) "Patch-level image representation"的优势 "Patch-level image representation is very important for object classification and detection, since it is robust to spatial transformation, scale variation, and cluttered background" &

深度学习论文阅读笔记--Deep Learning Face Representation from Predicting 10,000 Classes

来自:CVPR 2014 作者:Yi Sun ,Xiaogang Wang,Xiaoao Tang 题目:Deep Learning Face Representation from Predicting 10,000 Classes 主要内容:通过深度学习来进行图像高级特征表示(DeepID),进而进行人脸的分类. 优点:在人脸验证上面做,可以很好的扩展到其他的应用,并且夸数据库有效性:在数据库中的类别越多时,其泛化能力越强,特征比较少,不像其他特征好几K甚至上M,好的泛化能力+不过拟合于

Deep Reinforcement Learning for Visual Object Tracking in Videos 论文笔记

Deep Reinforcement Learning for Visual Object Tracking in Videos 论文笔记 arXiv 摘要:本文提出了一种 DRL 算法进行单目标跟踪,算是单目标跟踪中比较早的应用强化学习算法的一个工作. 在基于深度学习的方法中,想学习一个较好的 robust spatial and temporal representation for continuous video data 是非常困难的. 尽管最近的 CNN based tracke