cvpr
文章平均质量分 73
_menglan_Zi
水水一枚
展开
-
SSD系列
1SSD: Single Shot MultiBox Detector. ECCV16 (arxiv)2R-SSD: enhancement of ssd by concatenating feature maps for object detection. BMVC17. (arxiv)3DSSD: Deconvolut原创 2017-12-28 10:05:43 · 2059 阅读 · 3 评论 -
StuffNet: Using ‘Stuff’ to Improve Object Detection - arxiv 16.10
StuffNet: Using ‘Stuff’ to Improve Object Detection, Arxiv 16.10论文地址:https://arxiv.org/pdf/1610.05861v1.pdf类似的论文:Contextual Priming and Feedback forFaster R-CNN, eccv16.=====好像现在都喜欢用multi-task原创 2016-10-27 20:10:40 · 1683 阅读 · 0 评论 -
plateau lr policy
好久没有冒泡了,哈哈。plateau lr policy来自于PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection这篇论文。这里从issue里面整理出来的,欢迎大家指点,以及如果你用了plateau lr policy来做实验,是否可以告知下效果如何?issues:Add "plate原创 2016-10-13 10:05:16 · 2832 阅读 · 2 评论 -
Multi-view Face Detection Using Deep Convolutional Neural Networks, ICMR 15.
Multi-view Face Detection Using Deep Convolutional Neural Networks, ICMR 15. 将Alexnet转成FCN的形式也就是227*227的输入会输出1*1的heat map),将detection问题转为classification问题。 很简单,对每个region/propos原创 2016-08-11 20:21:37 · 3114 阅读 · 8 评论 -
- UnitBox An Advanced Object Detection Network,arxiv 16.08
- UnitBox An Advanced Object Detection Network,arxiv 16.08 (download) 该论文提出了一种新的loss function:IoU loss。这点比较有意思,也容易复现。 ====== 论文分析了faster-rcnn和densebox的优缺点: 1 fast原创 2016-08-16 21:43:33 · 5727 阅读 · 1 评论 -
convolutional pose machines, CVPR 2016
convolutional pose machines, CVPR 2016.论文:http://arxiv.org/abs/1602.00134project:https://github.com/shihenw/convolutional-pose-machines-release=====看到这篇论文,心里还是有点难受的,当初做pose的毕设时,为什么就不参考下这篇掉渣天的论原创 2016-07-31 10:21:13 · 10695 阅读 · 7 评论 -
DeepFashion: Powering Robust Clothes Recognition and Retrieval with Rich Annotations – CVPR 2016
DeepFashion: Powering Robust ClothesRecognition and Retrieval with Rich Annotations – CVPR 2016论文&project:http://personal.ie.cuhk.edu.hk/~lz013/projects/DeepFashion.html1 clothes的chall原创 2016-07-03 21:49:17 · 6173 阅读 · 13 评论 -
Bootstrapping Face Detection with Hard Negative Examples,arxiv 16.08
- Bootstrapping Face Detection with Hard Negative Examples,arxiv 16.08(download) 昨天在微博上看到这个论文的时候,很是惊讶,为啥?因为出自小米的为发烧而生(跑分) ===== 论文比较短,主要提出了一个hard negative mining的方式,以及基于faste原创 2016-08-15 19:43:29 · 3418 阅读 · 4 评论 -
Instance-sensitive Fully Convolutional Networks - eccv 2016
Instance-sensitive Fully Convolutional Networks - eccv 2016=====论文地址:http://arxiv.org/abs/1603.08678=====一句话概括: 根据local coherence的特性,以sliding window的方式,利用FCN产生positive-sensitive的instance-le原创 2016-09-06 17:36:16 · 5324 阅读 · 3 评论 -
Deep Image Retrieval: Learning global representations for image search. In ECCV, 2016.
Deep Image Retrieval: Learning global representations for image search. In ECCV, 2016.论文地址:https://arxiv.org/abs/1604.01325extended version:end to end learning of deep visual representations for i原创 2016-11-03 17:15:47 · 5754 阅读 · 4 评论 -
A Discriminative Feature Learning Approach for Deep Face Recognition, ECCV16.
A Discriminative Feature Learning Approach for Deep Face Recognition, ECCV16.论文:http://ydwen.github.io/papers/WenECCV16.pdf代码(caffe):https://github.com/kpzhang93/caffe-face代码(mxnet):https://gith原创 2016-10-29 10:45:01 · 3265 阅读 · 0 评论 -
Let there be Color!: Automatic Image Colorization with Simultaneous Classification - sig - 2016
最近在arxiv上逛逛,看到一篇关于colorization的paper觉得挺有意思的:Let there be Color!: Joint End-to-end Learning of Global and Local Image Priors for Automatic Image Colorization with Simultaneous Classification - sig -原创 2016-05-05 10:55:24 · 3474 阅读 · 1 评论 -
human pose regression by combining indirect part detection and contextual information - arxiv - 1710
好久没写了,心血来潮好吧,怎么简单怎么来:human pose regression by combining indirect part detection and contextual information - arxiv - 1710.02322论文链接该论文的亮点在于重新用回了regression,而不是直接基于heat map的part detection方法。原创 2017-10-10 15:44:28 · 2462 阅读 · 1 评论 -
cv方面的博文收藏 -- 持续更新
(持续更新)- 深度学习变革视觉实例搜索 http://www.leiphone.com/news/201608/Iy4k4tU8zXThBYEQ.html原创 2016-11-15 15:37:14 · 2040 阅读 · 0 评论 -
R-FCN: Object Detection via Region-based Fully Convolutional Networks (NIPS 16), Arxiv 16.05
R-FCN: Object Detection via Region-based Fully Convolutional Networks, Arxiv 16.05=====blogs:论文阅读]R-FCN: Object Detection via Region-based Fully Convolutional Networks: http://blog原创 2016-08-31 13:59:47 · 5065 阅读 · 4 评论 -
Training Region-based Object Detectors with Online Hard Example Mining - cvpr 2016 oral
这是rgb大神的又一神作,cvpr 2016的oral paper,论文地址here。 先上图,如Figure2所示: 从图中可以看出,本文的亮点在于在每次迭代中,较少训练样本下,如何hard negative mining,来提升效果。 即针对Fast-RCNN框架,在每次minibatch(1张或者2张)训练时加入在线筛选hard region的策略,达到新的SoA。原创 2016-05-04 21:37:46 · 10365 阅读 · 38 评论 -
Improving Facial Attribute Prediction using Semantic Segmentation, in arxiv 2017.04
笔者最近在关注fine-grained方面的paper,发现有以下的方面去做:1 part-based2 weakly-supervised的,如second-orderless pooling(Compact Bilinear Pooling)等3 还是weakly-supervised的,但用上了proposals/grids/regions(如selective search)等原创 2017-05-08 22:34:18 · 1846 阅读 · 0 评论 -
Residual Attention Network for Image Classification, cvpr17
人至懒则无敌。cvpr17的论文,很有意思,值得一读和复现。(笔者懒,还是坐等开源吧)Residual Attention Network for Image Classification. In CVPR 2017.该模型的结构参考了: Stacked hourglass networks for human pose estimation. In arXiv 2016. (笔者原创 2017-05-08 22:00:04 · 7595 阅读 · 1 评论 -
Aggregated Residual Transformations for Deep Neural Networks - arxiv 16.11
Aggregated Residual Transformations for Deep Neural Networks, arXiv 16.11.论文链接: https://arxiv.org/abs/1611.05431=====这个是全明星阵容的paper,提出了深度模型另一个重要的需要考量的纬度:cardinality。(用简单的方式做不简单的事情)众所周知,提高模原创 2016-11-20 12:33:27 · 6610 阅读 · 1 评论 -
Pyramid Scene Parsing Network - arxiv - 1612.01105
Pyramid Scene Parsing Network - arxiv - 1612.011052016年imagenet的scene parsing的冠军github: https://github.com/hszhao/PSPNetproject: http://appsrv.cse.cuhk.edu.hk/~hszhao/projects/pspnet/index.h原创 2016-12-09 11:06:43 · 3115 阅读 · 1 评论 -
Fully Convolutional Instance-aware Semantic Segmentation - arXiv 16.11
Fully Convolutional Instance-aware Semantic Segmentation - arXiv 16.11论文链接:https://arxiv.org/pdf/1611.07709v1.pdfgithub:https://github.com/daijifeng001/TA-FCN=====参考博文:1Instance-sensitive Fu原创 2016-11-29 12:30:04 · 3716 阅读 · 0 评论 -
PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection - arxiv 2016.08
PVANET: Deep but Lightweight Neural Networks forReal-time Object Detection, arxiv 16.08论文地址:https://arxiv.org/pdf/1608.08021v1.pdf先看leaderboard再看下speed厉害的不要不要的。=====转正题,下面介绍下这篇原创 2016-09-08 15:07:33 · 6528 阅读 · 12 评论 -
深度学习论文笔记-Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
转载于:http://blog.csdn.net/chenriwei2/article/details/38047119****************************************************************************文章:Spatial Pyramid Pooling in Deep Convolutional Network转载 2015-03-09 10:59:22 · 978 阅读 · 0 评论 -
CNN之Caffe配置
CNN之Caffe配置转载我老大的转载 2014-06-09 13:41:54 · 7774 阅读 · 2 评论 -
积分图像与积分直方图
转载:(本文所有权由原作者所有)http://blog.csdn.net/zhazhiqiang/article/details/18769195http://blog.sina.com.cn/s/blog_679e132901011cph.html*******************************************************************转载 2014-03-10 21:02:08 · 1503 阅读 · 0 评论 -
LBP特征
转载:http://blog.csdn.net/zouxy09/article/details/7929531安微博:http://weibo.com/u/2044913903************************************************************************* LBP(Local Binary Pat转载 2014-03-10 20:24:32 · 1214 阅读 · 0 评论 -
Modeling Video Evolution For Action Recognition - cvpr - 2015
Modeling Video Evolution For Action Recognition - cvpr - 2015论文题目Modeling Video Evolution For Action Recognition, 链接该篇论文是CVPR 2015的, 文章的核心是feature descriptors的获取. 直接看图说话:原创 2015-11-13 18:59:57 · 1946 阅读 · 4 评论 -
P-CNN: Pose-based CNN Features for Action Recognition (CNN篇)
论文题目P-CNN: Pose-based CNN Features for Action Recognition, 链接之前看过在静态图像上做action recognition的论文, 如Georgia Gkioxari这位大美女的论文, Contextual Action Recognition with R*CNN (可以看柱锦师兄的blog)和RGB视频里面的原创 2015-11-12 18:06:19 · 5855 阅读 · 11 评论 -
【转载】论文笔记 《Object detection via a multi-region & semantic segmentation-aware CNN model》
转载于:http://zhangliliang.com/2015/05/17/paper-note-ms-cnn/版权归原作者所有********************************************************************论文笔记 《Object detection via a multi-region & semanti转载 2016-05-04 18:51:44 · 5019 阅读 · 1 评论 -
Pose-Action-Caffe
等我弄完毕设,就来完善、整理自己基于fast-rcnn来弄的pose estimation 和 action recognition的方法。现在已经把代码放到github上了,欢迎各位看客前来指教。 pose-action-caffepose的参考论文: 1 Flowing ConvNets for Human Pose Estimation in Videos, ICCV原创 2016-04-07 11:54:29 · 2396 阅读 · 4 评论 -
research of action recognition and classfication in still images
一篇关于静态图像的活动/动作识别的调研文档, 具体看以下连接https://github.com/zimenglan-sysu-512/paper-note/blob/master/action-recognition/research.of.action.classfication.or.recognition.in.static.image.pdf请各位看官不要嫌弃。原创 2016-03-03 19:31:20 · 920 阅读 · 0 评论 -
求两帧图像或着视频的光流(optical flow)
最近在弄视频方面的pose estimation,由于不才,没有想到很高大上的idea来利用视频的信息(如LSTM等),只想到用optical flow的方式来利用视频信息,(路过的不要鄙视鄙人)至于怎么弄pose,欢迎各位看客前来赐教。至于怎么产生optical flow,请各位看官,移步至下面的连接https://github.com/zimenglan-sysu-51原创 2016-03-02 21:39:58 · 12199 阅读 · 3 评论 -
论文提要“You Only Look Once: Unified, Real-Time Object Detection”
转载于:http://blog.csdn.net/cv_family_z/article/details/46803421版权归原作者所有.项目主页:http://pjreddie.com/darknet/yolo/这篇文章着重在检测的速度提升,区别于之前的方法是用分类器来做检测,文章对bbox和对应的类概率进行回归,检测速度可以达到45f/s,mAP与原始的R-CNN差不多。转载 2016-01-10 15:44:47 · 1630 阅读 · 0 评论 -
Heterogeneous Multi-task Learning for Human Pose Estimation with Deep Convolutional Neural Network
Heterogeneous Multi-task Learning for Human Pose Estimation with Deep Convolutional Neural Network论文题目Heterogeneous Multi-task Learning for Human Pose Estimation with Deep Convolutional Neural原创 2015-12-14 14:28:09 · 2317 阅读 · 2 评论 -
Finding Action Tubes - cvpr - 2015
论文题目Finding Action Tubes, 论文链接该篇论文是CVPR 2015的, 主要讲述了action tube的localization.直接看图说话, 该论文的核心思想/步骤可以分为两个components: 1 Action detection at every frame of the video 2 Linked detection原创 2015-11-25 00:19:10 · 1863 阅读 · 0 评论 -
annotation code for human pose estimation
参考论文: http://www.cs.ucla.edu/~rothrock/pages/cvpr13/在标注part的时候 先标注part的状态,然后才标注part的bounding box (用两条直线来表示)其中 non-occluded 和 Default 是默认的*******************************鼠标左键:确认点和当原创 2014-02-17 10:04:01 · 1507 阅读 · 0 评论