CVPR 2020 共收录 1470篇文章，根据当前的公布情况，人工智能学社整理了以下约100篇，分享给读者。

代码开源情况：详见每篇注释，当前共15篇开源。(持续更新中，可关注了解)。

算法主要领域：图像与视频处理，图像分类&检测&分割、视觉目标跟踪、视频内容分析、人体姿态估计、模型加速、网络架构搜索(NAS)、生成对抗(GAN)、光学字符识别(OCR)、人脸识别、三维重建等方向。 目录如下：

持续更新，获取最新，可关注 ~~

总目录

图像处理

1. Deep Image Harmonization via Domain Verification 论文：arxiv.org/abs/1911.13… 代码：github.com/bcmi/Image_…

2. Learning to Shade Hand-drawn Sketches 论文：arxiv.org/abs/2002.11…

3. Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Data 论文：arxiv.org/abs/2002.11…

4. Single Image Reflection Removal through Cascaded Refinement 论文：arxiv.org/abs/1911.06…

5. RoutedFusion: Learning Real-time Depth Map Fusion 论文：arxiv.org/pdf/2001.04…

图像分类

1. Towards Robust Image Classification Using Sequential Attention Models 论文：arxiv.org/abs/1912.02…

2. Self-training with Noisy Student improves ImageNet classification 论文：arxiv.org/abs/1911.04…

3. Image Matching across Wide Baselines: From Paper to Practice 论文：arxiv.org/abs/2003.01…

4. Improved Few-Shot Visual Classification 论文：arxiv.org/pdf/1912.03…

5. A General and Adaptive Robust Loss Function 论文：arxiv.org/abs/1701.03…

6. Making Better Mistakes: Leveraging Class Hierarchies with Deep Networks 论文：arxiv.org/abs/1912.09…

目标检测和分割

1. Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector 论文：arxiv.org/abs/1908.01…

2. Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection 论文：arxiv.org/abs/1912.02…
   代码：github.com/sfzhang15/A…

3. Semi-Supervised Semantic Image Segmentation with Self-correcting Networks 论文：arxiv.org/abs/1811.07…

4. Deep Snake for Real-Time Instance Segmentation 论文：arxiv.org/abs/2001.01…

5. SketchGCN: Semantic Sketch Segmentation with Graph Convolutional Networks 论文：arxiv.org/abs/2003.00…

6. xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation 论文：arxiv.org/abs/1911.12…

7. CenterMask : Real-Time Anchor-Free Instance Segmentation 论文：arxiv.org/abs/1911.06… 代码：github.com/youngwanLEE…

8. PolarMask: Single Shot Instance Segmentation with Polar Representation 论文：arxiv.org/abs/1909.13… 代码：github.com/xieenze/Pol…

9. BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation 论文：arxiv.org/abs/2001.00…

视觉目标跟踪

1. ROAM: Recurrently Optimizing Tracking Model 论文：arxiv.org/abs/1907.12…

视频内容分析(理解)

1. Hierarchical Conditional Relation Networks for Video Question Answering 论文：arxiv.org/abs/2002.10…

2. Rethinking Zero-shot Video Classification: End-to-end Training for Realistic Applications 论文：arxiv.org/abs/2003.01…
   代码：github.com/bbrattoli/Z…

3. Action Modifiers:Learning from Adverbs in Instructional Video 论文：arxiv.org/abs/1912.06…

4. Fine-grained Video-Text Retrieval with Hierarchical Graph Reasoning 论文：arxiv.org/abs/2003.00…

5. Blurry Video Frame Interpolation 论文：arxiv.org/abs/2002.12…

6. Object Relational Graph with Teacher-Recommended Learning for Video Captioning 论文：arxiv.org/abs/2002.11…

7. Say As You Wish: Fine-grained Control of Image Caption Generation with Abstract Scene Graphs 论文：arxiv.org/abs/2003.00…

8. Learning Representations by Predicting Bags of Visual Words 论文：arxiv.org/abs/2002.12…

9. Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video Super-Resolution 论文：arxiv.org/abs/2002.11…

人体关键点检测和姿态估计

1. Distribution-Aware Coordinate Representation for Human Pose Estimation 论文：arxiv.org/abs/1910.06…
   代码：github.com/ilovepose/D…

2. VIBE: Video Inference for Human Body Pose and Shape Estimation 论文：arxiv.org/abs/1912.05…
   代码：github.com/mkocabas/VI…

3. The Devil is in the Details: Delving into Unbiased Data Processing for Human Pose Estimation 论文：arxiv.org/abs/1911.07…

4. Optimal least-squares solution to the hand-eye calibration problem 论文：arxiv.org/abs/2002.10…

5. Distribution Aware Coordinate Representation for Human Pose Estimation 论文：arxiv.org/abs/1910.06…

6. D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry 论文：arxiv.org/abs/2003.01…

7. Multi-Modal Domain Adaptation for Fine-Grained Action Recognition 论文：arxiv.org/abs/2001.09…

8. PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimation 论文：arxiv.org/abs/1911.04…

9. 4D Association Graph for Realtime Multi-person Motion Capture Using Multiple Video Cameras 论文：arxiv.org/abs/2002.12…

模型轻量化和加速

1. GPU-Accelerated Mobile Multi-view Style Transfer 论文：arxiv.org/abs/2003.00…

神经网络架构设计和搜索NAS

1. GhostNet: More Features from Cheap Operations 论文：arxiv.org/abs/1911.11… 代码：github.com/iamhankai/g…

2. CARS: Contunuous Evolution for Efficient Neural Architecture Search 论文：arxiv.org/pdf/1909.04… 代码：github.com/huawei-noah…

3. Visual Commonsense R-CNN 论文：arxiv.org/abs/2002.12…

4. Watch your Up-Convolution: CNN Based Generative Deep Neural Networks are Failing to Reproduce Spectral 论文：arxiv.org/abs/2003.01…

5. AdderNet: Do We Really Need Multiplications in Deep Learning? 论文：arxiv.org/pdf/1912.13…

6. Filter Grafting for Deep Neural Networks 论文：arxiv.org/pdf/2001.05…

生成对抗GAN

1. Your Local GAN: Designing Two Dimensional Local Attention Mechanisms for Generative Models 论文：arxiv.org/abs/1911.12… 代码：github.com/giannisdara…

2. MSG-GAN: Multi-Scale Gradient GAN for Stable Image Synthesis 论文：arxiv.org/abs/1903.06…

3. Robust Design of Deep Neural Networks against Adversarial Attacks based on Lyapunov Theory 论文：arxiv.org/abs/1911.04…

三维点云&3D重建

1. PointAugment: an Auto-Augmentation Framework for Point Cloud Classification 论文：arxiv.org/abs/2002.10… 代码：github.com/liruihui/Po…

2. PF-Net: Point Fractal Network for 3D Point Cloud Completion 论文：arxiv.org/abs/2003.00…

3. Learning multiview 3D point cloud registration 论文：arxiv.org/abs/2001.05…

4. Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image 论文：arxiv.org/abs/2002.12…

5. In Perfect Shape: Certifiably Optimal 3D Shape Reconstruction from 2D Landmarks 论文：arxiv.org/pdf/1911.11…

6. RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds 论文：arxiv.org/abs/1911.11…

7. C-Flow: Conditional Generative Flow Models for Images and 3D Point Clouds 论文：arxiv.org/abs/1912.07…

8. Representations, Metrics and Statistics For Shape Analysis of Elastic Graphs 论文：arxiv.org/abs/2003.00…

9. Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion 论文：arxiv.org/abs/2003.01…

光学字符识别OCR

1. ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network 论文：arxiv.org/abs/2002.10… 代码：github.com/Yuliang-Liu…

迁移学习

1. Meta-Transfer Learning for Zero-Shot Super-Resolution 论文：arxiv.org/abs/2002.12…

2. Transferring Dense Pose to Proximal Animal Classes 论文：arxiv.org/abs/2003.00…

弱监督 & 无监督学习

1. Unsupervised Reinforcement Learning of Transferable Meta-Skills for Embodied Navigation 论文：arxiv.org/abs/1911.07…

2. Disentangling Physical Dynamics from Unknown Factors for Unsupervised Video Prediction 论文：arxiv.org/abs/2003.01…

3. Rethinking the Route Towards Weakly Supervised Object Localization 论文：arxiv.org/abs/2002.11…

4. NestedVAE: Isolating Common Factors via Weak Supervision 论文：arxiv.org/abs/2002.11…

人脸识别

1. Towards Universal Representation Learning for Deep Face Recognition 论文：arxiv.org/abs/2002.11…

2. Suppressing Uncertainties for Large-Scale Facial Expression Recognition
   论文：arxiv.org/abs/2002.10… 代码：github.com/kaiwang9601…

3. Face X-ray for More General Face Forgery Detection 论文：arxiv.org/pdf/1912.13…

图神经网络GNN

1. Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction 论文：arxiv.org/abs/2002.11…

2. Bundle Adjustment on a Graph Processor 论文：arxiv.org/abs/2003.03… 代码：github.com/joeaortiz/g…

视觉 & 语言 混合任务研究

1. Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training 论文：arxiv.org/abs/2002.10… 代码：github.com/weituo12321…

2. 12-in-1: Multi-Task Vision and Language Representation Learning 论文：arxiv.org/abs/1912.02…

3. Hierarchical Conditional Relation Networks for Video Question Answering 论文：arxiv.org/abs/2002.10…

其他问题研究

1. What it Thinks is Important is Important: Robustness Transfers through Input Gradients 论文：arxiv.org/abs/1912.05…

2. Holistically-Attracted Wireframe Parsing 论文：arxiv.org/abs/2003.01…

3. Attentive Context Normalization for Robust Permutation-Equivariant Learning 论文：arxiv.org/abs/1907.02…

4. ClusterFit: Improving Generalization of Visual Representations 论文：arxiv.org/abs/1912.03…

5. Learning in the Frequency Domain 论文：arxiv.org/abs/2002.12…

6. A Characteristic Function Approach to Deep Implicit Generative Modeling 论文：arxiv.org/abs/1909.07…

7. Auto-Encoding Twin-Bottleneck Hashing 论文：arxiv.org/abs/2002.11…

论文打包下载地址

链接：pan.baidu.com/s/1lo3smbFW…

提取码：公众号内回复 cvpr2020

论文包中有彩蛋一枚~~~~