/Awesome-CVPR-Paper

CVPR 论文收集,包含但不限于2020、2019、2018、2017文章

Awesome-CVPR-Paper

更新2020年最新CVPR下载链接!

CVPR论文收集,包含但不限于2017、2018、2019、2020文章,会持续更新

公众号【计算机视觉联盟】后台回复 CVPR2020 下载最新论文

往年的请回复 CVPR2019

CVPR 2020

1.GhostNet: More Features from Cheap Operations(超越Mobilenet v3的架构) 论文链接:https://arxiv.org/pdf/1911.11907arxiv.org 模型(在ARM CPU上的表现惊人):https://github.com/iamhankai/ghostnetgithub.com

We beat other SOTA lightweight CNNs such as MobileNetV3 and FBNet.

  1. AdderNet: Do We Really Need Multiplications in Deep Learning? (加法神经网络) 在大规模神经网络和数据集上取得了非常好的表现 论文链接:https://arxiv.org/pdf/1912.13200arxiv.org

  2. Frequency Domain Compact 3D Convolutional Neural Networks (3dCNN压缩) 论文链接:https://arxiv.org/pdf/1909.04977arxiv.org 开源代码:https://github.com/huawei-noah/CARSgithub.com

  3. A Semi-Supervised Assessor of Neural Architectures (神经网络精度预测器 NAS)

  4. Hit-Detector: Hierarchical Trinity Architecture Search for Object Detection (NAS 检测) backbone-neck-head一起搜索, 三位一体

  5. CARS: Contunuous Evolution for Efficient Neural Architecture Search (连续进化的NAS) 高效,具备可微和进化的多重优势,且能输出帕累托前研

  6. On Positive-Unlabeled Classification in GAN (PU+GAN)

  7. Learning multiview 3D point cloud registration(3D点云) 论文链接:arxiv.org/abs/2001.05119

  8. Multi-Modal Domain Adaptation for Fine-Grained Action Recognition(细粒度动作识别) 论文链接:arxiv.org/abs/2001.09691

  9. Action Modifiers:Learning from Adverbs in Instructional Video 论文链接:arxiv.org/abs/1912.06617

  10. PolarMask: Single Shot Instance Segmentation with Polar Representation(实例分割建模) 论文链接:arxiv.org/abs/1909.13226 论文解读:https://zhuanlan.zhihu.com/p/84890413 开源代码:https://github.com/xieenze/PolarMask

  11. Rethinking Performance Estimation in Neural Architecture Search(NAS) 由于block wise neural architecture search中真正消耗时间的是performance estimation部分,本文针对 block wise的NAS找到了最优参数,速度更快,且相关度更高。

  12. Distribution Aware Coordinate Representation for Human Pose Estimation(人体姿态估计) 论文链接:arxiv.org/abs/1910.06278 Github:https://github.com/ilovepose/DarkPose 作者团队主页:https://ilovepose.github.io/coco/

更新

  1. 视觉常识R-CNN,Visual Commonsense R-CNN

https://arxiv.org/abs/2002.12204

  1. Out-of-distribution图像检测

https://arxiv.org/abs/2002.11297

  1. 模糊视频帧插值,Blurry Video Frame Interpolation

https://arxiv.org/abs/2002.12259

  1. 元迁移学习零样本超分

https://arxiv.org/abs/2002.12213

  1. 3D室内场景理解

https://arxiv.org/abs/2002.12212

6.从有偏训练生成无偏场景图

https://arxiv.org/abs/2002.11949

  1. 自动编码双瓶颈哈希

https://arxiv.org/abs/2002.11930

  1. 一种用于人类轨迹预测的社会时空图卷积神经网络

https://arxiv.org/abs/2002.11927

  1. 面向面向深度人脸识别的通用表示学习

https://arxiv.org/abs/2002.11841

  1. 视觉表示泛化性

https://arxiv.org/abs/1912.03330

  1. 减弱上下文偏差

https://arxiv.org/abs/2002.11812

  1. 可迁移元技能的无监督强化学习

https://arxiv.org/abs/1911.07450

  1. 快速准确时空视频超分

https://arxiv.org/abs/2002.11616

  1. 对象关系图Teacher推荐学习的视频captioning

https://arxiv.org/abs/2002.11566

  1. 弱监督物体定位路由再思考

https://arxiv.org/abs/2002.11359

  1. 通过预培训学习视觉和语言导航的通用代理

https://arxiv.org/pdf/2002.10638.pdf

  1. GhostNet轻量级神经网络

https://arxiv.org/pdf/1911.11907.pdf

  1. AdderNet:在深度学习中,我们真的需要乘法吗?

https://arxiv.org/pdf/1912.13200.pdf

  1. CARS:高效神经结构搜索的持续进化

https://arxiv.org/abs/1909.04977

  1. 通过协作式的迭代级联微调来移除单图像中的反射

https://arxiv.org/abs/1911.06634

  1. 深度神经网络的滤波嫁接

https://arxiv.org/pdf/2001.05868.pdf

  1. PolarMask:将实例分割统一到FCN

https://arxiv.org/pdf/1909.13226.pdf

  1. 半监督语义图像分割

https://arxiv.org/pdf/1811.07073.pdf

  1. 通过选择性的特征再生来抵御通用攻击

https://arxiv.org/pdf/1906.03444.pdf

  1. 实时的基于细粒度草图的图像检索

https://arxiv.org/abs/2002.10310

  1. 用子问题询问VQA模型

https://arxiv.org/abs/1906.03444

  1. 从2D范例中学习神经三维纹理空间

https://geometry.cs.ucl.ac.uk/projects/2020/neuraltexture/

  1. NestedVAE:通过薄弱的监督来隔离共同因素

https://arxiv.org/abs/2002.11576

  1. 实现多未来轨迹预测

https://arxiv.org/pdf/1912.06445.pdf

  1. 使用序列注意力模型进行稳健的图像分类

https://arxiv.org/pdf/1912.02184

CVPR 2017

CVPR 2018

CVPR 2019

CVPR近年来最佳论文

2018Taskonomy: Disentangling Task Transfer LearningAmir R. Zamir, Stanford University; et al.
Alexander Sax, Stanford University
William Shen, Stanford University
Leonidas Guibas, Stanford University
Jitendra Malik, University of California Berkeley
Silvio Savarese, Stanford University
2017Densely Connected Convolutional NetworksZhuang Liu, Tsinghua University; et al.
Gao Huang, Cornell University
Laurens van der Maaten, Facebook AI Research
Kilian Q. Weinberger, Cornell University
Learning from Simulated and Unsupervised Images through Adversarial TrainingAshish Shrivastava, Apple Inc.; et al.
Tomas Pfister, Apple Inc.
Oncel Tuzel, Apple Inc.
Josh Susskind, Apple Inc.
Wenda Wang, Apple Inc.
Russ Webb, Apple Inc.
2016Deep Residual Learning for Image RecognitionKaiming He, Microsoft Research; et al.
Xiangyu Zhang, Microsoft Research
Shaoqing Ren, Microsoft Research
Jian Sun, Microsoft Research
2015DynamicFusion: Reconstruction and Tracking of Non-rigid Scenes in Real-TimeRichard A. Newcombe, University of Washington; et al.
Dieter Fox, University of Washington
Steven M. Seitz, University of Washington
2014What Camera Motion Reveals About Shape with Unknown BRDFManmohan Chandraker, NEC Labs America2013Fast, Accurate Detection of 100,000 Object Classes on a Single MachineThomas Dean, Google; et al.
Mark A. Ruzon, Google
Mark Segal, Google
Jonathon Shlens, Google
Sudheendra Vijayanarasimhan, Google
Jay Yagnik, Google
2012A Simple Prior-free Method for Non-Rigid Structure-from-Motion FactorizationYuchao Dai, Northwestern Polytechnical University; et al.
Hongdong Li, Australian National University
Mingyi He, Northwestern Polytechnical University
2011Real-time Human Pose Recognition in Parts from Single Depth ImagesJamie Shotton, Microsoft Research; et al.
Andrew Fitzgibbon, Microsoft Research
Mat Cook, Microsoft Research
Toby Sharp, Microsoft Research
Mark Finocchio, Microsoft Research
Richard Moore, Microsoft Research
Alex Kipman, Microsoft Research
Andrew Blake, Microsoft Research
2010Efficient Computation of Robust Low-Rank Matrix Approximations in the Presence of Missing Data usi...Anders Eriksson & Anton va den Hendel, University of Adelaide2009Single Image Haze Removal Using Dark Channel PriorKaiming He, The Chinese University of Hong Kong; et al.
Jian Sun, Microsoft Research
Xiaoou Tang, The Chinese University of Hong Kong
2008Global Stereo Reconstruction under Second Order Smoothness PriorsOliver Woodford, University of Oxford; et al.
Ian Reid, Oxford Brookes University
Philip Torr, University of Oxford
Andrew Fitzgibbon, Microsoft Research
Beyond Sliding Windows: Object Localization by Efficient Subwindow SearchChistoph H. Lampert, Max Planck Institut; et al.
Matthew B. Blaschko, Max Planck Institut
Thomas Hodmann, Google
2007Dynamic 3D Scene Analysis from a Moving VehicleBastian Leibe, ETH Zurich; et al.
Nico Cornelis, Katholieke Universiteit Leuven
Kurt COrnelis, Katholieke Universiteit Leuven
Luc Van Gool, ETH Zurich
2006Putting Objects in PerspectiveDerek Hoiem, Carnegie Mellon University; et al.
Alexei Efros, Carnegie Mellon University
Martial Hebert, Carnegie Mellon University
2005Real-Time Non-Rigid Surface DetectionJulien Pilet, École Polytechnique Fédérale de Lausanne; et al.
Vincent Lepetit, École Polytechnique Fédérale de Lausanne
Pascal Fua, École Polytechnique Fédérale de Lausanne
2004Programmable Imaging using a Digital Micromirror ArrayShree K. Nayar, Columbia University; et al.
Vlad Branzoi, Columbia University
Terry E. Boult, University of Colorado
2003Object Class Recognition by Unsupervised Scale-Invariant LearningRob Fergus, University of Oxford; et al.
Pietro Perona, California Institute of Technology
Andrew Zisserman, University of Oxford
2001Morphable 3D models from videoMatthew Brand, Mitsubishi Electric Research Laboratories2000Real-Time Tracking of Non-Rigid Objects using Mean ShiftDorin Comaniciu, Siemens Corporate Research; et al.
Visvanathan Ramesh, Siemens Corporate Research
Peter Meer, Rutgers University