CVPR 2020論文收藏（轉知乎：https://zhuanlan.zhihu.com/p/112337176）

CVPR 2020 共收錄 1470篇文章，根據當前的公布情況，人工智能學社整理了以下約100篇，分享給讀者。

代碼開源情況：詳見每篇注釋，當前共15篇開源。(持續更新中，可關注了解)。

算法主要領域：圖像與視頻處理，圖像分類&檢測&分割、視覺目標跟蹤、視頻內容分析、人體姿態估計、模型加速、網絡架構搜索(NAS)、生成對抗(GAN)、光學字符識別(OCR)、人臉識別、三維重建等方向。 目錄如下：

 

# 總目錄

# 圖像處理

1. Deep Image Harmonization via Domain Verification

論文：Deep Image Harmonization via Domain Verification

代碼：bcmi/Image_Harmonization_Datasets

2. Learning to Shade Hand-drawn Sketches

論文：Learning to Shade Hand-drawn Sketches

3. Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Data

論文：Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Data

4. Single Image Reflection Removal through Cascaded Refinement

論文：https://arxiv.org/abs/1911.06634

5. RoutedFusion: Learning Real-time Depth Map Fusion

論文：https://arxiv.org/pdf/2001.04388.pdf

# 圖像分類

1. Towards Robust Image Classification Using Sequential Attention Models

論文：Towards Robust Image Classification Using Sequential Attention Models

2. Self-training with Noisy Student improves ImageNet classification

論文：Self-training with Noisy Student improves ImageNet classification

3. Image Matching across Wide Baselines: From Paper to Practice

論文：Image Matching across Wide Baselines: From Paper to Practice

4. Improved Few-Shot Visual Classification

論文：https://arxiv.org/pdf/1912.03432.pdf

5. A General and Adaptive Robust Loss Function

論文：A General and Adaptive Robust Loss Function

6. Making Better Mistakes: Leveraging Class Hierarchies with Deep Networks

論文：Making Better Mistakes: Leveraging Class Hierarchies with Deep Networks

# 目標檢測和分割


1. Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector

論文：Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector

2. Bridng the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection

論文：https://arxiv.org/abs/1912.02424

代碼：sfzhang15/ATSS

3. Semi-Supervised Semantic Image Segmentation with Self-correcting Networks

論文：Semi-Supervised Semantic Image Segmentation with Self-correcting Networks

4. Deep Snake for Real-Time Instance Segmentation

論文：Deep Snake for Real-Time Instance Segmentation

5. SketchGCN: Semantic Sketch Segmentation with Graph Convolutional Networks

論文：SketchGCN: Semantic Sketch Segmentation with Graph Convolutional Networks

6. xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation

論文：xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation

7. CenterMask : Real-Time Anchor-Free Instance Segmentation

論文：CenterMask : Real-Time Anchor-Free Instance Segmentation

代碼：youngwanLEE/CenterMask

8. PolarMask: Single Shot Instance Segmentation with Polar Representation

論文：PolarMask: Single Shot Instance Segmentation with Polar Representation

代碼：xieenze/PolarMask

9. BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation

論文：BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation

# 視覺目標跟蹤


1. ROAM: Recurrently Optimizing Tracking Model

論文：ROAM: Recurrently Optimizing Tracking Model

# 視頻內容分析(理解)


1. Hierarchical Conditional Relation Networks for Video Question Answering

論文：Hierarchical Conditional Relation Networks for Video Question Answering

2. Rethinking Zero-shot Video Classification: End-to-end Training for Realistic Applications

論文：Rethinking Zero-shot Video Classification: End-to-end Training for Realistic Applications

代碼：bbrattoli/ZeroShotVideoClassification

3. Action Modifiers:Learning from Adverbs in Instructional Video

論文：Action Modifiers: Learning from Adverbs in Instructional Videos

4. Fine-grained Video-Text Retrieval with Hierarchical Graph Reasoning

論文：Fine-grained Video-Text Retrieval with Hierarchical Graph Reasoning

5. Blurry Video Frame Interpolation

論文：Blurry Video Frame Interpolation

6. Object Relational Graph with Teacher-Recommended Learning for Video Captioning

論文：Object Relational Graph with Teacher-Recommended Learning for Video Captioning

7. Say As You Wish: Fine-grained Control of Image Caption Generation with Abstract Scene Graphs

論文：Say As You Wish: Fine-grained Control of Image Caption Generation with Abstract Scene Graphs

8. Learning Representations by Predicting Bags of Visual Words

論文：Learning Representations by Predicting Bags of Visual Words

9. Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video Super-Resolution

論文：Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video Super-Resolution

# 人體關鍵點檢測和姿態估計


1. Distribution-Aware Coordinate Representation for Human Pose Estimation

論文：Distribution-Aware Coordinate Representation for Human Pose Estimation

代碼：ilovepose/DarkPose

2. VIBE: Video Inference for Human Body Pose and Shape Estimation

論文：VIBE: Video Inference for Human Body Pose and Shape Estimation

代碼：mkocabas/VIBE

3. The Devil is in the Details: Delving into Unbiased Data Processing for Human Pose Estimation

論文：The Devil is in the Details: Delving into Unbiased Data Processing for Human Pose Estimation

4. Optimal least-squares solution to the hand-eye calibration problem

論文：Optimal least-squares solution to the hand-eye calibration problem

5. Distribution Aware Coordinate Representation for Human Pose Estimation

論文：Distribution-Aware Coordinate Representation for Human Pose Estimation

6. D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry

論文：D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry

7. Multi-Modal Domain Adaptation for Fine-Grained Action Recognition

論文：Multi-Modal Domain Adaptation for Fine-Grained Action Recognition

8. PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimation

論文：https://arxiv.org/abs/1911.04231

9. 4D Association Graph for Realtime Multi-person Motion Capture Using Multiple Video Cameras

論文：4D Association Graph for Realtime Multi-person Motion Capture Using Multiple Video Cameras

# 模型輕量化和加速

1. GPU-Accelerated Mobile Multi-view Style Transfer

論文：GPU-Accelerated Mobile Multi-view Style Transfer

# 神經網絡架構設計和搜索NAS


1. GhostNet: More Features from Cheap Operations

論文：GhostNet: More Features from Cheap Operations

代碼：huawei-noah/ghostnet

2. CARS: Contunuous Evolution for Efficient Neural Architecture Search

論文：https://arxiv.org/pdf/1909.04977.pdf

代碼：huawei-noah/CARS

3. Visual Commonsense R-CNN

論文：https://arxiv.org/abs/2002.12204

4. Watch your Up-Convolution: CNN Based Generative Deep Neural Networks are Failing to Reproduce Spectral

論文：Watch your Up-Convolution: CNN Based Generative Deep Neural Networks are Failing to Reproduce Spectral Distributions

5. AdderNet: Do We Really Need Multiplications in Deep Learning?

論文：https://arxiv.org/pdf/1912.13200

6. Filter Grafting for Deep Neural Networks

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

# 生成對抗GAN


1. Your Local GAN: Designing Two Dimensional Local Attention Mechanisms for Generative Models

論文：Your Local GAN: Designing Two Dimensional Local Attention Mechanisms for Generative Models

代碼：giannisdaras/ylg

2. MSG-GAN: Multi-Scale Gradient GAN for Stable Image Synthesis

論文：MSG-GAN: Multi-Scale Gradient GAN for Stable Image Synthesis

3. Robust Design of Deep Neural Networks against Adversarial Attacks based on Lyapunov Theory

論文：Robust Design of Deep Neural Networks against Adversarial Attacks based on Lyapunov Theory

# 三維點雲&3D重建


1. PointAugment: an Auto-Augmentation Framework for Point Cloud Classification

論文：PointAugment: an Auto-Augmentation Framework for Point Cloud Classification

代碼：liruihui/PointAugment

2. PF-Net: Point Fractal Network for 3D Point Cloud Completion

論文：PF-Net: Point Fractal Network for 3D Point Cloud Completion

3. Learning multiview 3D point cloud registration

論文：Learning multiview 3D point cloud registration

4. Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image

論文：Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image

5. In Perfect Shape: Certifiably Optimal 3D Shape Reconstruction from 2D Landmarks

論文：https://arxiv.org/pdf/1911.11924.pdf

6. RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds

論文：RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds

7. C-Flow: Conditional Generative Flow Models for Images and 3D Point Clouds

論文：C-Flow: Conditional Generative Flow Models for Images and 3D Point Clouds

8. Representations, Metrics and Statistics For Shape Analysis of Elastic Graphs

論文：Representations, Metrics and Statistics For Shape Analysis of Elastic Graphs

9. Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion

論文：Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion

# 光學字符識別OCR

1. ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network

論文：ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network

代碼：https://github.com/Yuliang-Liu/bezier_curve_text_spotting,https://github.com/aim-uofa/adet

# 遷移學習


1. Meta-Transfer Learning for Zero-Shot Super-Resolution

論文：Meta-Transfer Learning for Zero-Shot Super-Resolution

2. Transferring Dense Pose to Proximal Animal Classes

論文：Transferring Dense Pose to Proximal Animal Classes

# 弱監督 & 無監督學習

1. Unsupervised Reinforcement Learning of Transferable Meta-Skills for Embodied Navigation

論文：Unsupervised Reinforcement Learning of Transferable Meta-Skills for Embodied Navigation

2. Disentangling Physical Dynamics from Unknown Factors for Unsupervised Video Prediction

論文：Disentangling Physical Dynamics from Unknown Factors for Unsupervised Video Prediction

3. Rethinking the Route Towards Weakly Supervised Object Localization

論文：Rethinking the Route Towards Weakly Supervised Object Localization

4. NestedVAE: Isolating Common Factors via Weak Supervision

論文：NestedVAE: Isolating Common Factors via Weak Supervision

# 人臉識別

1. Towards Universal Representation Learning for Deep Face Recognition

論文：Towards Universal Representation Learning for Deep Face Recognition

2. Suppressing Uncertainties for Large-Scale Facial Expression Recognition

論文：Suppressing Uncertainties for Large-Scale Facial Expression Recognition

代碼：kaiwang960112/Self-Cure-Network

3. Face X-ray for More General Face Forgery Detection

論文：https://arxiv.org/pdf/1912.13458.pdf

# 圖神經網絡GNN

1. Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction

論文：Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction

2. Bundle Adjustment on a Graph Processor

論文：Bundle Adjustment on a Graph Processor

代碼：joeaortiz/gbp

# 視覺 & 語言 混合任務研究

1. Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training

論文：Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training

代碼：weituo12321/PREVALENT

2. 12-in-1: Multi-Task Vision and Language Representation Learning

論文：12-in-1: Multi-Task Vision and Language Representation Learning

3. Hierarchical Conditional Relation Networks for Video Question Answering

論文：Hierarchical Conditional Relation Networks for Video Question Answering

# 其他問題研究

1. What it Thinks is Important is Important: Robustness Transfers through Input Gradients

論文：https://arxiv.org/abs/1912.05699

2. Holistically-Attracted Wireframe Parsing

論文：Holistically-Attracted Wireframe Parsing

3. Attntive Context Normalization for Robust Permutation-Equivariant Learning

論文：Attentive Context Normalization for Robust Permutation-Equivariant Learning

5. ClusterFit: Improving Generalization of Visual Representations

論文：ClusterFit: Improving Generalization of Visual Representations

6. Learning in the Frequency Domain

論文：Learning in the Frequency Domain

7. A Characteristic Function Approach to Deep Implicit Generative Modeling

論文：A Characteristic Function Approach to Deep Implicit Generative Modeling

8. Auto-Encoding Twin-Bottleneck Hashing

論文：Auto-Encoding Twin-Bottleneck Hashing

 

# 論文打包下載地址

 

鏈接：https://pan.baidu.com/s/1lo3smbFWiBSNnut9JssYaQ

提取碼：可在公眾號內發送消息： cvpr2020