Interested Papers

最新推荐文章于 2022-12-22 13:19:30 发布
最新推荐文章于 2022-12-22 13:19:30 发布
阅读量793 收藏
点赞数
分类专栏： paper
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.csdn.net/ayst123/article/details/53464633
版权

Feb 28

Deep Image Harmonization
[https://arxiv.org/pdf/1702.08502.pdf](Unsupervised Image-to-Image Translation Networks), segmentation
Unsupervised Image-to-Image Translation Networks, Unsupervised image-to-image

Feb 23

Learning Chained Deep Features and Classifiers for Cascade in Object Detection, Xiaogang
ViP-CNN: A Visual Phrase Reasoning Convolutional Neural Network for Visual
Relationship Detection, Xiaogang

Feb 22

Learning Deep Features via Congenerous Cosine Loss for Person Recognition, Yu Liu, Xiaogang Wang
TRANSFERRING FACE VERIFICATION NETS TO PAIN AND EXPRESSION REGRESSION, Alan Yuille
Unsupervised Diverse Colorization via Generative Adversarial Networks, Colorization

Jan 11

Revisiting Deep Image Smoothing and Intrinsic Image Decomposition, Qingnan Fan, Baoquan Chen

Jan 10

Deep Feature Interpolation for Image Content Changes

manipulate

Dec 22

https://arxiv.org/pdf/1612.06890.pdf Justin
https://arxiv.org/pdf/1612.07182.pdf NLP
https://arxiv.org/pdf/1612.06933.pdf unsupervised place discovery for visual place classification
https://arxiv.org/pdf/1612.07086.pdf Recurrent Highway Networks with Language CNN for Image Captioning
https://arxiv.org/pdf/1612.07217.pdf Learning Motion Patterns in Videos
https://arxiv.org/pdf/1612.07310.pdf Beyond Holistic Object Recognition:
Enriching Image Understanding with Part States

Dec 21

https://arxiv.org/pdf/1612.06851.pdf beyond skip connections (5)
https://arxiv.org/pdf/1612.06573.pdf detecting unexpected obstacles
https://arxiv.org/pdf/1612.06558.pdf semantic segmentation
https://arxiv.org/pdf/1612.06530.pdf grounded visual questions
https://arxiv.org/pdf/1612.06524.pdf 3d human pose estimation

Dec 20

https://arxiv.org/pdf/1612.06371.pdf action recognition (5)
https://arxiv.org/pdf/1612.06321.pdf image retrieval (5)
https://arxiv.org/pdf/1612.06152.pdf few-shot object recognition (5)
https://arxiv.org/pdf/1612.06053.pdf visual tracking
https://arxiv.org/pdf/1612.05877.pdf action recognition
https://arxiv.org/pdf/1612.05872.pdf 3d shape
https://arxiv.org/pdf/1612.05836.pdf egoTransfer
https://arxiv.org/pdf/1612.05753.pdf qlearning

Dec 19

https://arxiv.org/pdf/1612.05363.pdf learning Residual Images for face attribute manipulation (5)
https://arxiv.org/pdf/1612.05322.pdf face detection
https://arxiv.org/pdf/1612.05478.pdf video propagation networks
https://arxiv.org/pdf/1612.05424.pdf unsupervised pixel-level domain adaptation with GAN (5)
https://arxiv.org/pdf/1612.05400.pdf deep residual hashing
https://arxiv.org/pdf/1612.05386.pdf vqa-machine

Dec 16

https://arxiv.org/pdf/1612.05086.pdf Coupling Adaptive Batch Sizes with Learning Rates
https://arxiv.org/pdf/1612.04844.pdf The more you know
https://arxiv.org/pdf/1612.04884.pdf action recognition
https://arxiv.org/pdf/1612.04901.pdf zero-shot learning, CMU
https://arxiv.org/pdf/1612.04904.pdf regressing robust model
https://arxiv.org/pdf/1612.04949.pdf Recurrent Image
https://arxiv.org/pdf/1612.05079.pdf SceneNet
https://arxiv.org/pdf/1612.05234.pdf Visual Compiler

Dec 14,15

https://arxiv.org/pdf/1612.04357.pdf stacked GAN
https://arxiv.org/pdf/1612.04337.pdf fast style transfer
https://arxiv.org/pdf/1612.04229.pdf recurrent generative model
https://arxiv.org/pdf/1612.03928.pdf more attention

Others

https://arxiv.org/pdf/1611.09969v1.pdf
https://arxiv.org/pdf/1612.00496v1.pdf
https://arxiv.org/pdf/1507.02379.pdf
https://arxiv.org/pdf/1611.08402.pdf
https://arxiv.org/pdf/1611.08303.pdf
https://arxiv.org/pdf/1611.08408.pdf
https://arxiv.org/pdf/1511.07125v1.pdf
https://arxiv.org/pdf/1611.08583.pdf
https://arxiv.org/pdf/1611.08986.pdf
https://arxiv.org/pdf/1611.09078.pdf
https://arxiv.org/pdf/1611.09325.pdf
https://arxiv.org/pdf/1611.09326.pdf
https://arxiv.org/pdf/1611.08588.pdf

Dec 13

https://arxiv.org/pdf/1612.03809.pdf
https://arxiv.org/pdf/1612.03236.pdf
https://arxiv.org/pdf/1612.03242.pdf
https://arxiv.org/pdf/1612.03268.pdf
https://arxiv.org/pdf/1612.03365.pdf
https://arxiv.org/pdf/1612.03550.pdf
https://arxiv.org/pdf/1612.03557.pdf
https://arxiv.org/pdf/1612.03628.pdf
https://arxiv.org/pdf/1612.03630.pdf
https://arxiv.org/pdf/1612.03663.pdf
https://arxiv.org/pdf/1612.03897.pdf

Dec 12

https://arxiv.org/pdf/1612.03144.pdf
https://arxiv.org/pdf/1612.03052.pdf
https://arxiv.org/pdf/1612.03129.pdf

Dec 7

https://arxiv.org/pdf/1612.02372.pdf
https://arxiv.org/pdf/1612.02297.pdf
https://arxiv.org/pdf/1612.02287.pdf
https://arxiv.org/pdf/1612.02177.pdf

Dec 6

https://arxiv.org/pdf/1612.01635.pdf
https://arxiv.org/pdf/1612.01895.pdf
https://arxiv.org/pdf/1612.01958.pdf
https://arxiv.org/pdf/1612.01981.pdf
https://arxiv.org/pdf/1612.01991.pdf
https://arxiv.org/pdf/1612.01887.pdf

Dec 5

https://arxiv.org/pdf/1612.01202.pdf
https://arxiv.org/pdf/1612.01465.pdf
https://arxiv.org/pdf/1612.01380.pdf
https://arxiv.org/pdf/1612.01079.pdf
https://arxiv.org/pdf/1612.01057.pdf
https://arxiv.org/pdf/1612.01051.pdf
https://arxiv.org/pdf/1612.00991.pdf
https://arxiv.org/pdf/1612.00901.pdf
https://arxiv.org/pdf/1612.01230.pdf
https://arxiv.org/pdf/1612.01294.pdf
https://arxiv.org/pdf/1612.01452.pdf
https://arxiv.org/pdf/1612.01479.pdf

Dec 4,

  1. https://arxiv.org/pdf/1612.00835.pdf
  2. https://arxiv.org/pdf/1612.00500.pdf
  3. https://arxiv.org/pdf/1612.00522.pdf
  4. https://arxiv.org/pdf/1612.00593.pdf
  5. https://arxiv.org/pdf/1612.00606.pdf
  6. https://arxiv.org/pdf/1612.00686.pdf
  7. https://arxiv.org/pdf/1612.00500.pdf
  8. https://arxiv.org/pdf/1612.00523.pdf
ayst123
关注
  • 0
    点赞
  • 踩
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
专栏目录
概念解析 | 图像融合(Image Harmonization)
NLOS的博客
11-14 371
在图像处理中,我们经常需要将不同来源的图像进行组合,使它们看起来自然协调。例如,将一幅风景照与人像合成在一起。但是直接拼接两幅图像通常会出现颜色、照明不协调的问题。为了解决这一问题,图像融合(Image Harmonization)技术应运而生。它通过调整颜色、对比度等使图像的视觉风格达到协调,就像它们本来就是同一场景拍摄的。这为创作数字艺术提供了强有力的工具。
关于深度学习理论和架构的最新综述(参考文献)
qq_16197337的博客
04-02 3361
Schmidhuber, J. Deep Learning in Neural Networks: An Overview. Neural Netw. 2015, 61, 85–117. [CrossRef] [PubMed] Bengio, Y.; LeCun, Y.; Hinton, G. Deep Learning. Nature 2015, 521, 436–444. Bengio, Y...
AAAI 2023 | 双域风格图像和谐化
Paper weekly
12-22 558
©PaperWeekly 原创 ·作者 |曹俊燕单位 |上海交通大学BCMI实验室图像合成（Image Composition）是指将前景从一张图片上剪切下来，然后粘贴到另一张图片上，生成一张合成图片的技术。但通过这种方式获得的合成图片，其前景和背景会存在色彩、光照等统计信息不一致的问题，这导致整张图片看起来不真实、不和谐。图像和谐化（Image Harmonization）任务旨在调整合成...
论文阅读：Unsupervised Diverse Colorization via Generative Adversarial Networks
qq_39109729的博客
11-26 826
论文阅读：Unsupervised Diverse Colorization via Generative Adversarial Networks 这是一篇使用改进的Conditional GAN 来进行图像上色任务的论文，在多层中使用输入的灰度图像（GrayScale)作为条件信息对GAN的生成进行指导保证上色效果的真实性（reality)， 同时在生成器的所有层中加入随机的噪声信息保证上色结果的颜色多样性(diversity)。 1、动机 ​ 作者提到， 以往的自动上色方法，无论是非参数式
【图像上色小综述】生成对抗网络的GAN法
idol24的博客
10-08 4668
点击上方“机器学习与生成对抗网络”，关注"星标"获取有趣、好玩的前沿干货！超100篇！CVPR 2020最全GAN论文梳理汇总！0，图像上色及其分类图像上色一般分为两种：...
论文阅读：ViP-CNN:Visual Phrase Guided Convolutional Nerual Network(CVPR17)
qq_40349484的博客
02-11 1597
论文阅读：ViP-CNN:Visual Phrase Guided Convolutional Nerual Network(CVPR17)
Almost Random Graphs with Simple Hash Functions - Slides (2007)-计算机科学
04-22
Almost random graphs with simple hashfunctionsMartin DietzfelbingerTechnische Universität Ilmenau(Joint work ... ,m − 1} : the range, indices in tables T1, T2Interested in behaviour of h1, h2 on S ⊆
Windows Logon Forensics - 30th Jan 2013 (6928)-计算机科学
04-22
Reposting is not permited without express written permission.Interested in learning more? Check out the list of upcoming events offering "Advanced Incident Response, Threat Hunting, and Digital ...
Modern C v2 (2019)-计算机科学
04-22
Modern CJens GustedtINRIA, FRANCEICUBE, STRASBOURG, FRANCEThis ...feedback, includingcolleagues and other interested readers, Cédric Bastoul, Lucas Nussbaum, Vincent Loechner, Kliment Yanev, Szabolcs Na
Critique of Microkernel Architectures (Slides)-计算机科学
04-22
Microkernel ArchitecturesI’m not interested in making devices look like user-level. They aren’t, they shouldn’t, andmicrokernels are just stupid. Linus TorvaldsIs Linus right?2Microkernel ...
Python-DeepPainterlyHarmonization论文的实现代码和数据
08-11
"Deep Painterly Harmonization"论文的实现代码和数据
CVPR2017 all paper list
热门推荐
一亩半分地
07-26 2万+
本文给出了CVPR2017的最新的paperlist
2018 CVPR GAN 相关论文调研 （自己分了下类，附地址哦）
fly
09-20 6069
2018 CVPR GAN 相关论文调研 风格迁移 1. PairedCycleGAN: Asymmetric Style Transfer for Applying and Removing Makeup （给人脸化妆的风格转移） http://openaccess.thecvf.com/content_cvpr_2018/papers/Chang_PairedCycleGAN_Asym...
PKU2054 Color a Tree
Canopus
10-11 503
Description Bob is very interested in the data structure of a tree. A tree is a directed graph in which a special node is singled out, called the “root” of the tree, and there is a unique path from th
研究方向
luckyboy101的专栏
11-03 990
1、colorization(scribble:optimization,diffusion map, geodesic distance, gabor filter(texture). color transfer) 2、recoloring 3、color harmonization 4、specularity/highlights removal(dichromatic reflect
图像合成：Multi-scale Image Harmonization
qq_34901691的博客
08-22 1367
Multi-scale Image Harmonization 文章目录Multi-scale Image HarmonizationOverviewSmooth Histogram MatchingStructure and Noise MatchingPyramid compositing 在图像合成、拼接、纹理合成等图像处理应用场景中，不仅仅是需要实现背景图像内容间的无缝融合，还需要保证合成图像真实性，前面提到的泊松融合仅考虑到了图像在融合区域梯度场的约束，能很好的融合背景图像和前景图像的图像内容，但
CVPR 2018 paper
qq_34848537的博客
10-08 1万+
CVPR 2018 参考链接 CVPR 2018 论文解读集锦（9月27日更新） CVPR 2018 open access Paperlist Embodied Question Answering Learning by Asking Questions Finding Tiny Faces in the Wild With Generative Adversarial Network...
Object Detection(目标检测神文)---3
03-23 2万+
Object Detection on Mobile Devices Pelee: A Real-Time Object Detection System on Mobile Devices intro: ICLR 2018 workshop track intro: based on the SSD arxiv: https://arxiv.org/abs/1804.06882 ...
code for papers
最新发布
08-31
code for papers 可以理解为为论文编写代码的意思。在研究领域，科学家们经常需要编写代码来支持他们的研究工作。这些代码可以用于数据分析、模拟实验、算法实现等各种科学研究任务。 论文中的代码可以通过多种编程...

“相关推荐”对你有帮助么？

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值