【CVPR2020】：CVPR2020论文分方向整理: 目标检测/图像分割/姿态估计等，附打包下载

21.Deep Image Harmonization via Domain Verification(图像和谐化)
论文链接： https://arxiv.org/abs/1911.13239
代码：https://github.com/bcmi/Image_Harmonization_Datasets

20.GhostNet: More Features from Cheap Operations（超越Mobilenet v3的架构）
论文链接：https://arxiv.org/pdf/1911.11907
开源代码：https://github.com/iamhankai/ghostnet

19.AdderNet: Do We Really Need Multiplications in Deep Learning? （加法神经网络）
论文链接：https://arxiv.org/pdf/1912.13200

18.CARS: Contunuous Evolution for Efficient Neural Architecture Search（连续进化的NAS）
论文链接：https://arxiv.org/pdf/1909.04977.pdf
开源代码：https://github.com/huawei-noah/CARS

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

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

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

14.PolarMask: Single Shot Instance Segmentation with Polar Representation（实例分割）
论文链接：https://arxiv.org/abs/1909.13226
开源代码：https://github.com/xieenze/PolarMask

13.Distribution Aware Coordinate Representation for Human Pose Estimation（姿态估计）
论文链接：https://arxiv.org/abs/1910.06278
开源代码：https://github.com/ilovepose/DarkPose

12.Suppressing Uncertainties for Large-Scale Facial Expression Recognition（面部表情识别）
论文链接：https://arxiv.org/abs/2002.10392
开源代码：https://github.com/kaiwang960112/Self-Cure-Network

11.xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic
论文链接：https://arxiv.org/abs/1911.12676

10.RoutedFusion: Learning Real-time Depth Map Fusion
论文链接：https://arxiv.org/pdf/2001.04388.pdf

9.What it Thinks is Important is Important: Robustness Transfers through Input Gradients
论文链接：https://arxiv.org/abs/1912.05699

8.Your Local GAN: Designing Two Dimensional Local Attention Mechanisms（GAN）
论文链接：https://arxiv.org/abs/1911.12287
开源代码：https://github.com/giannisdaras/ylg

7.12-in-1: Multi-Task Vision and Language Representation Learning（多任务视觉和语言表示学习）
论文链接：https://arxiv.org/abs/1912.02315

6.MSG-GAN: Multi-Scale Gradient GAN for Stable Image Synthesis（GAN）
论文链接：https://arxiv.org/abs/1903.06048

5.Making Better Mistakes: Leveraging Class Hierarchies with Deep Networks
论文链接：https://arxiv.org/abs/1912.09393

4.The Devil is in the Details: Delving into Unbiased Data Processing for
论文链接：https://arxiv.org/abs/1911.07524

3.In Perfect Shape: Certifiably Optimal 3D Shape Reconstruction from 2D（三维重建）
论文链接：https://arxiv.org/pdf/1911.11924

2.Improved Few-Shot Visual Classification（改进小样本学习视觉分类）
论文链接：https://arxiv.org/pdf/1912.03432.pdf

1.ROAM: Recurrently Optimizing Tracking Model（递归优化跟踪模型）
论文链接：https://arxiv.org/abs/1907.12006