CV Code | 计算机视觉开源周报 20190601期

栏目: 编程工具 · 发布时间: 4年前

内容简介:刚刚过去的一周有很多有意思的工作开源了,比如接吻检测、从步态中进行疾病检测。

我爱计算机视觉 标星,更快获取CVML新技术

CV Code | 计算机视觉开源周报 20190601期

刚刚过去的一周有很多有意思的工作开源了,比如接吻检测、从步态中进行疾病检测。

我们一起来看看吧。

基于CNN的社交网络中室外图像的人类情感分类研究

OutdoorSent: Can Semantic Features Help Deep Learning in Sentiment Analysis of Outdoor Images?

Wyverson B. de Oliveira, Leyza B. Dorini, Rodrigo Minetto, Thiago H. Silva

https://arxiv.org/abs/1906.02331v1

http://dainf.ct.utfpr.edu.br/outdoorsent

直接从两幅图像通过CNN回归单应性矩阵,远远好于之前的SOTA方法

STN-Homography: estimate homography parameters directly

Qiang Zhou, Xin Li

https://arxiv.org/abs/1906.02539v1

好莱坞电影中接吻镜头检测,少儿不宜。。。

Detecting Kissing Scenes in a Database of Hollywood Films

Amir Ziai

https://arxiv.org/abs/1906.01843v1

http://github.com/amirziai/kissing-detector

使用深度学习提取拓扑关系

PI-Net: A Deep Learning Approach to Extract Topological Persistence Images

Anirudh Som, Hongjun Choi, Karthikeyan Natesan Ramamurthy, Matthew Buman, Pavan Turaga

https://arxiv.org/abs/1906.01769v1

https://github.com/anirudhsom/PI-Net

跨任务引导注意力模型的一通路多任务模型,用于脑肿瘤分割

One-pass Multi-task Networks with Cross-task Guided Attention for Brain Tumor Segmentation

Chenhong Zhou, Changxing Ding, Xinchao Wang, Zhentai Lu, Dacheng Tao

https://arxiv.org/abs/1906.01796v1

https://github.com/chenhong-zhou/OM-Net

非监督行人重识别

Towards better Validity: Dispersion based Clustering for Unsupervised Person Re-identification

Guodong Ding, Salman Khan, Zhenmin Tang, Jian Zhang, Fatih Porikli

https://arxiv.org/abs/1906.01308v1

https://github.com/gddingcs/Dispersion-based-Clustering.git

基于深度学习方法的步态视频中疾病检测

Automatic Health Problem Detection from Gait Videos Using Deep Neural Networks

Rahil Mehrizi, Xi Peng, Shaoting Zhang, Ruisong Liao, Kang Li

https://arxiv.org/abs/1906.01480v1

https://github.com/rmehrizi/multi-view-pose-estimation

BMVC 2017

多视3D目标识别

Dominant Set Clustering and Pooling for Multi-View 3D Object Recognition

Chu Wang, Marcello Pelillo, Kaleem Siddiqi

https://arxiv.org/abs/1906.01592v1

https://github.com/fate3439/dscnn

生成对抗网络综述和术语

Generative Adversarial Networks: A Survey and Taxonomy

Zhengwei Wang, Qi She, Tomas E. Ward

https://arxiv.org/abs/1906.01529v1

https://github.com/sheqi/GAN_Review

评估可缩放的贝叶斯深度学习方法,用于鲁棒计算机视觉

Evaluating Scalable Bayesian Deep Learning Methods for Robust Computer Vision

Fredrik K. Gustafsson, Martin Danelljan, Thomas B. Schön

https://arxiv.org/abs/1906.01620v1

https://github.com/fregu856/evaluating_bdl

跨域级联深度特征的图像变换方法

Cross-Domain Cascaded Deep Feature Translation

Oren Katzir, Dani Lischinski, Daniel Cohen-Or

https://arxiv.org/abs/1906.01526v1

(将开源,代码未公布)

基于语义的医学图像融合方法

A Semantic-based Medical Image Fusion Approach

Fanda Fan, Yunyou Huang, Lei Wang, Xingwang Xiong, Zihan Jiang, Zhifei Zhang, Jianfeng Zhan

https://arxiv.org/abs/1906.00225v1

https://github.com/fanfanda/Medical-Image-Fusion

区域特定的微分形式的度量映射用于图像配准

Region-specific Diffeomorphic Metric Mapping

Zhengyang Shen, François-Xavier Vialard, Marc Niethammer

https://arxiv.org/abs/1906.00139v1

https://github.com/uncbiag/registration

通过渐进和选择性实例切换进行目标检测的数据增广

Data Augmentation for Object Detection via Progressive and Selective Instance-Switching

Hao Wang, Qilong Wang, Fan Yang, Weiqi Zhang, Wangmeng Zuo

https://arxiv.org/abs/1906.00358v1

https://github.com/Hwang64/PSIS

深度学习边缘检测的对抗样例

Adversarial Examples for Edge Detection: They Exist, and They Transfer

Christian Cosgrove, Alan L. Yuille

https://arxiv.org/abs/1906.00335v1

通过对抗鲁棒学习感知校正表示

Learning Perceptually-Aligned Representations via Adversarial Robustness

Logan Engstrom, Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras, Brandon Tran, Aleksander Madry

https://arxiv.org/abs/1906.00945v1

https://git.io/robust-reps

凝视校正,自监督GAN

GazeCorrection:Self-Guided Eye Manipulation in the wild using Self-Supervised Generative Adversarial Networks

Jichao Zhang, Meng Sun, Jingjing Chen, Hao Tang, Yan Yan, Xueying Qin, Nicu Sebe

https://arxiv.org/abs/1906.00805v1

https://github.com/zhangqianhui/GazeCorrection

深度学习数钢筋的CNN-DC方法

Automated Steel Bar Counting and Center Localization with Convolutional Neural Networks

Zhun Fan, Jiewei Lu, Benzhang Qiu, Tao Jiang, Kang An, Alex Noel Josephraj, Chuliang Wei

https://arxiv.org/abs/1906.00891v1

https://github.com/BenzhangQiu/Steel-bar-Detection

从视频中学习人-物交互的热点方法

Grounded Human-Object Interaction Hotspots from Video (Extended Abstract)

Tushar Nagarajan, Christoph Feichtenhofer, Kristen Grauman

https://arxiv.org/abs/1906.01963v1

http://vision.cs.utexas.edu/projects/interaction-hotspots/

深度学习GAN辅助电子显微镜成像

Partial Scan Electron Microscopy with Deep Learning

Jeffrey M. Ede, Richard Beanland

https://arxiv.org/abs/1905.13667v1

https://github.com/Jeffrey-Ede/partial-STEM

加群交流

关注计算机视觉与机器学习技术,欢迎加入52CV群,扫码添加CV君拉你入群,

请务必注明:52CV

CV Code | 计算机视觉开源周报 20190601期

喜欢在QQ交流的童鞋,可以加52CV官方 QQ群702781905

(不会时时在线,如果没能及时通过验证还请见谅)

CV Code | 计算机视觉开源周报 20190601期

长按关注 我爱计算机视觉


以上就是本文的全部内容,希望本文的内容对大家的学习或者工作能带来一定的帮助,也希望大家多多支持 码农网

查看所有标签

猜你喜欢:

本站部分资源来源于网络,本站转载出于传递更多信息之目的,版权归原作者或者来源机构所有,如转载稿涉及版权问题,请联系我们

梦断代码

梦断代码

Scott Rosenberg / 韩磊 / 电子工业出版社 / 2008.06 / 49.00元

软件乃是人类自以为最有把握,实则最难掌控的技术。本书作者罗森伯格对OSAF主持的Chandler项目进行田野调查,跟踪经年,试图借由Chandler的开发过程揭示软件开发中的一些根本性大问题。. 本书是讲一事,也是讲百千事;是写一软件,也是写百千软件;是写一群人,也是写百千万人。任何一个在软件领域稍有经验的技术人员看完本书,必掩卷长叹:做软件难。...一起来看看 《梦断代码》 这本书的介绍吧!

HTML 压缩/解压工具
HTML 压缩/解压工具

在线压缩/解压 HTML 代码

CSS 压缩/解压工具
CSS 压缩/解压工具

在线压缩/解压 CSS 代码

Base64 编码/解码
Base64 编码/解码

Base64 编码/解码