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（持续更新极市平台 - 图1

置顶 极市平台 2020-03-11 09:37:00 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（持续更新极市平台 - 图2
16306 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（持续更新极市平台 - 图3
收藏 90

最后发布: 2020-03-11 09:37:00 首发: 2020-03-11 09:37:00

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。

CVPR2020 在 2 月 24 日公布了所有接受论文 ID，相关报道：1470 篇！CVPR2020 结果出炉，你中了吗？（附部分论文链接 / 开源代码 / 解读）。自论文 ID 公布以来，许多开发者都分享了自己的优秀工作。

从论文 ID 公布以来，极市一直在对 CVPR 进行实时跟进，本文是对 CVPR2020 论文整理和分类，均有论文链接，部分含开源代码，涵盖的方向有：目标检测、目标跟踪、图像分割、人脸识别、姿态估计、三维点云、视频分析、模型加速、GAN、OCR等方向。

为了方便大家阅读，小极已经将全部论文下载并打包。扫描下方二维码 关注 极市平台 公众号，回复 CVPR2020 即可获取下载链接。同时，可访问 极市社区，后续论文收录会在这里保持更新。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（持续更新极市平台 - 图4

声明：本文为极市平台原创整理，未经许可，不得擅自转载。

此外，我们也会在 Github 和极市社区上保持更新，欢迎大家关注：
https://github.com/extreme-assistant/cvpr2020/blob/master/CVPR2020.md

目录

目标检测

  1. Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection
    论文地址：https://arxiv.org/abs/1912.02424
    代码：https://github.com/sfzhang15/ATSS

  2. Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector
    论文地址：https://arxiv.org/abs/1908.01998

  3. AugFPN: Improving Multi-scale Feature Learning for Object Detection
    论文地址：https://arxiv.org/abs/1912.05384

  4. Hit-Detector: Hierarchical Trinity Architecture Search for Object Detection
    论文地址：https://arxiv.org/abs/2003.11818
    代码：https://github.com/ggjy/HitDet.pytorch

  5. Multi-task Collaborative Network for Joint Referring Expression Comprehension and Segmentation
    论文地址：https://arxiv.org/abs/2003.08813

  6. CentripetalNet: Pursuing High-quality Keypoint Pairs for Object Detection
    论文地址：https://arxiv.org/abs/2003.09119
    代码：https://github.com/KiveeDong/CentripetalNet

图像分割

  1. Semi-Supervised Semantic Image Segmentation with Self-correcting Networks
    论文地址：https://arxiv.org/abs/1811.07073

  2. Deep Snake for Real-Time Instance Segmentation
    论文地址：https://arxiv.org/abs/2001.01629

  3. CenterMask : Real-Time Anchor-Free Instance Segmentation
    论文地址：https://arxiv.org/abs/1911.06667
    代码：https://github.com/youngwanLEE/CenterMask

  4. SketchGCN: Semantic Sketch Segmentation with Graph Convolutional Networks
    论文地址：https://arxiv.org/abs/2003.00678

  5. PolarMask: Single Shot Instance Segmentation with Polar Representation
    论文地址：https://arxiv.org/abs/1909.13226
    代码：https://github.com/xieenze/PolarMask

  6. xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation
    论文地址：https://arxiv.org/abs/1911.12676

  7. BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation
    论文地址：https://arxiv.org/abs/2001.00309

  8. Enhancing Generic Segmentation with Learned Region Representations
    论文地址：https://arxiv.org/abs/1911.08564

人脸识别

  1. Towards Universal Representation Learning for Deep Face Recognition
    论文地址：https://arxiv.org/abs/2002.11841

  2. Suppressing Uncertainties for Large-Scale Facial Expression Recognition
    论文地址：https://arxiv.org/abs/2002.10392
    代码：https://github.com/kaiwang960112/Self-Cure-Network

  3. Face X-ray for More General Face Forgery Detection
    论文地址：https://arxiv.org/pdf/1912.13458.pdf

  4. Pose Agnostic Cross-spectral Hallucination via Disentangling Independent Factors
    论文地址：https://arxiv.org/abs/1909.04365

  5. Deep Spatial Gradient and Temporal Depth Learning for Face Anti-spoofing
    论文地址：https://arxiv.org/abs/2003.08061
    代码：https://github.com/clks-wzz/FAS-SGTD

  6. Learning Meta Face Recognition in Unseen Domains
    论文地址：https://arxiv.org/abs/2003.07733
    代码：https://github.com/cleardusk/MFR

目标跟踪

  1. ROAM: Recurrently Optimizing Tracking Model
    论文地址：https://arxiv.org/abs/1907.12006

三维点云 & 重建

  1. PF-Net: Point Fractal Network for 3D Point Cloud Completion
    论文地址：https://arxiv.org/abs/2003.00410

  2. PointAugment: an Auto-Augmentation Framework for Point Cloud Classification
    论文地址：https://arxiv.org/abs/2002.10876
    代码：https://github.com/liruihui/PointAugment/

  3. Learning multiview 3D point cloud registration
    论文地址：https://arxiv.org/abs/2001.05119

  4. C-Flow: Conditional Generative Flow Models for Images and 3D Point Clouds
    论文地址：https://arxiv.org/abs/1912.07009

  5. RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds
    论文地址：https://arxiv.org/abs/1911.11236

  6. Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image
    论文地址：https://arxiv.org/abs/2002.12212

  7. Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion
    论文地址：https://arxiv.org/abs/2003.01456

  8. In Perfect Shape: Certifiably Optimal 3D Shape Reconstruction from 2D Landmarks
    论文地址：https://arxiv.org/pdf/1911.11924.pdf

  9. Attentive Context Normalization for Robust Permutation-Equivariant Learning
    论文地址：https://arxiv.org/abs/1907.02545 Weiwei Sun, Wei Jiang, Eduard Trulls, Andrea Tagliasacchi, Kwang Moo Yi

  10. PQ-NET: A Generative Part Seq2Seq Network for 3D Shapes
    论文地址：https://arxiv.org/abs/1911.10949

  11. SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D Scans
    论文地址：https://arxiv.org/abs/1912.00036

  12. Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching
    论文地址：https://arxiv.org/abs/1912.06378
    代码：https://github.com/alibaba/cascade-stereo

  13. Unsupervised Learning of Intrinsic Structural Representation Points
    论文地址：https://arxiv.org/abs/2003.01661
    代码：https://github.com/NolenChen/3DStructurePoints

图像处理

  1. Learning to Shade Hand-drawn Sketches
    论文地址：https://arxiv.org/abs/2002.11812

  2. Single Image Reflection Removal through Cascaded Refinement
    论文地址：https://arxiv.org/abs/1911.06634

  3. Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Data
    论文地址：https://arxiv.org/abs/2002.11297

  4. Deep Image Harmonization via Domain Verification
    论文地址：https://arxiv.org/abs/1911.13239
    代码：https://github.com/bcmi/Image_Harmonization_Datasets

  5. RoutedFusion: Learning Real-time Depth Map Fusion
    论文地址：https://arxiv.org/pdf/2001.04388.pdf

  6. Neural Contours: Learning to Draw Lines from 3D Shapes
    论文地址：https://arxiv.org/abs/2003.10333

  7. Towards Photo-Realistic Virtual Try-On by Adaptively Generating 鈫 Preserving Image Content
    论文地址：https://arxiv.org/abs/2003.05863

  8. Reinforced Feature Points: Optimizing Feature Detection and Description for a High-Level Task（图像处理 - 图像特征匹配）
    论文地址：https://arxiv.org/abs/1912.00623

  9. Correspondence Networks with Adaptive Neighbourhood Consensus（图像处理 - 图像特征匹配）
    论文地址：https://arxiv.org/abs/2003.12059

  10. Normalized and Geometry-Aware Self-Attention Network for Image Captioning（图像处理 - 图像字幕）
    论文地址：https://arxiv.org/abs/2003.08897

图像分类

  1. Self-training with Noisy Student improves ImageNet classification
    论文地址：https://arxiv.org/abs/1911.04252

  2. Image Matching across Wide Baselines: From Paper to Practice
    论文地址：https://arxiv.org/abs/2003.01587

  3. Towards Robust Image Classification Using Sequential Attention Models
    论文地址：https://arxiv.org/abs/1912.02184

  4. Learning in the Frequency Domain
    论文地址：https://arxiv.org/abs/2002.12416

  5. Learning from Web Data with Memory Module
    论文地址：https://arxiv.org/abs/1906.12028

  6. Making Better Mistakes: Leveraging Class Hierarchies with Deep Networks
    论文地址：https://arxiv.org/abs/1912.09393

姿态估计 / 动作识别

  1. VIBE: Video Inference for Human Body Pose and Shape Estimation
    论文地址：https://arxiv.org/abs/1912.05656
    代码：https://github.com/mkocabas/VIBE

  2. Distribution-Aware Coordinate Representation for Human Pose Estimation
    论文地址：https://arxiv.org/abs/1910.06278
    代码：https://github.com/ilovepose/DarkPose

  3. 4D Association Graph for Realtime Multi-person Motion Capture Using Multiple Video Cameras
    论文地址：https://arxiv.org/abs/2002.12625

  4. Optimal least-squares solution to the hand-eye calibration problem
    论文地址：https://arxiv.org/abs/2002.10838

  5. D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry
    论文地址：https://arxiv.org/abs/2003.01060

  6. Multi-Modal Domain Adaptation for Fine-Grained Action Recognition
    论文地址：https://arxiv.org/abs/2001.09691

  7. Distribution Aware Coordinate Representation for Human Pose Estimation
    论文地址：https://arxiv.org/abs/1910.06278

  8. The Devil is in the Details: Delving into Unbiased Data Processing for Human Pose Estimation
    论文地址：https://arxiv.org/abs/1911.07524

  9. PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimation
    论文地址：https://arxiv.org/abs/1911.04231

  10. Action Segmentation with Joint Self-Supervised Temporal Domain Adaptation
    论文地址：https://arxiv.org/abs/2003.02824

  11. G2L-Net: Global to Local Network for Real-time 6D Pose Estimation with Embedding Vector Features
    论文地址：https://arxiv.org/abs/2003.11089

  12. Deep Image Spatial Transformation for Person Image Generation
    论文地址：https://arxiv.org/abs/2003.00696
    代码：https://github.com/RenYurui/ Global-Flow-Local-Attention

视频分析

  1. Rethinking Zero-shot Video Classification: End-to-end Training for Realistic Applications
    论文地址：https://arxiv.org/abs/2003.01455
    代码：https://github.com/bbrattoli/ZeroShotVideoClassification

  2. Say As You Wish: Fine-grained Control of Image Caption Generation with Abstract Scene Graphs
    论文地址：https://arxiv.org/abs/2003.00387

  3. Fine-grained Video-Text Retrieval with Hierarchical Graph Reasoning
    论文地址：https://arxiv.org/abs/2003.00392

  4. Object Relational Graph with Teacher-Recommended Learning for Video Captioning
    论文地址：https://arxiv.org/abs/2002.11566

  5. Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video Super-Resolution
    论文地址：https://arxiv.org/abs/2002.11616

  6. Blurry Video Frame Interpolation
    论文地址：https://arxiv.org/abs/2002.12259

  7. Hierarchical Conditional Relation Networks for Video Question Answering
    论文地址：https://arxiv.org/abs/2002.10698

  8. Action Modifiers:Learning from Adverbs in Instructional Video
    论文地址：https://arxiv.org/abs/1912.06617

  9. Visual Grounding in Video for Unsupervised Word Translation
    论文地址：https://arxiv.org/abs/2003.05078
    代码：https://github.com/gsig/visual-grounding

  10. MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask（视频分析 - 光流估计）
    论文地址：https://arxiv.org/abs/2003.10955
    代码：https://github.com/microsoft/MaskFlownet

  11. Use the Force, Luke! Learning to Predict Physical Forces by Simulating Effects（视频预测）
    论文地址：https://arxiv.org/abs/2003.12045
    代码：https://ehsanik.github.io/forcecvpr2020

OCR

  1. ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network
    论文地址：https://arxiv.org/abs/2002.10200
    代码：https://github.com/Yuliang-Liu/bezier_curve_text_spotting,https://github.com/aim-uofa/adet

  2. Iterative Answer Prediction with Pointer-Augmented Multimodal Transformers for TextVQA
    论文地址：https://arxiv.org/abs/1911.06258

GAN

  1. Your Local GAN: Designing Two Dimensional Local Attention Mechanisms for Generative Models
    论文地址：https://arxiv.org/abs/1911.12287
    代码：https://github.com/giannisdaras/ylg

  2. MSG-GAN: Multi-Scale Gradient GAN for Stable Image Synthesis
    论文地址：https://arxiv.org/abs/1903.06048

  3. Robust Design of Deep Neural Networks against Adversarial Attacks based on Lyapunov Theory
    论文地址：https://arxiv.org/abs/1911.04636

  4. PSGAN: Pose and Expression Robust Spatial-Aware GAN for Customizable Makeup Transfer
    论文地址：https://arxiv.org/abs/1909.06956

小样本 / 零样本

  1. Improved Few-Shot Visual Classification
    论文地址：https://arxiv.org/pdf/1912.03432.pdf

  2. Meta-Transfer Learning for Zero-Shot Super-Resolution
    论文地址：https://arxiv.org/abs/2002.12213

  3. Instance Credibility Inference for Few-Shot Learning
    论文地址：https://arxiv.org/abs/2003.11853
    代码：https://github.com/Yikai-Wang/ICI-FSL

弱监督 / 无监督 / 自监督

  1. Rethinking the Route Towards Weakly Supervised Object Localization
    论文地址：https://arxiv.org/abs/2002.11359

  2. NestedVAE: Isolating Common Factors via Weak Supervision
    论文地址：https://arxiv.org/abs/2002.11576

  3. Unsupervised Reinforcement Learning of Transferable Meta-Skills for Embodied Navigation
    论文地址：https://arxiv.org/abs/1911.07450

  4. Disentangling Physical Dynamics from Unknown Factors for Unsupervised Video Prediction
    论文地址：https://arxiv.org/abs/2003.01460

  5. ClusterFit: Improving Generalization of Visual Representations
    论文地址：https://arxiv.org/abs/1912.03330

  6. Auto-Encoding Twin-Bottleneck Hashing
    论文地址：https://arxiv.org/abs/2002.11930

  7. Learning Representations by Predicting Bags of Visual Words
    论文地址：https://arxiv.org/abs/2002.12247

  8. A Characteristic Function Approach to Deep Implicit Generative Modeling
    论文地址：https://arxiv.org/abs/1909.07425

  9. Unsupervised Learning of Intrinsic Structural Representation Points
    论文地址：https://arxiv.org/abs/2003.01661
    代码：https://github.com/NolenChen/3DStructurePoints

行人跟踪 / 行人检测 / ReID

  1. Cross-modality Person re-identification with Shared-Specific Feature Transfer
    论文地址：https://arxiv.org/abs/2002.12489

  2. Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction
    论文地址：https://arxiv.org/abs/2002.11927

  3. The Garden of Forking Paths: Towards Multi-Future Trajectory Prediction
    论文地址：https://arxiv.org/abs/1912.06445

神经网络 / 模型压缩 / 模型加速

  1. GhostNet: More Features from Cheap Operations
    论文地址：https://arxiv.org/abs/1911.11907
    代码：https://github.com/iamhankai/ghostnet

  2. Watch your Up-Convolution: CNN Based Generative Deep Neural Networks are Failing to Reproduce Spectral
    论文地址：https://arxiv.org/abs/2003.01826

  3. GPU-Accelerated Mobile Multi-view Style Transfer
    论文地址：https://arxiv.org/abs/2003.00706

  4. Bundle Adjustment on a Graph Processor
    论文地址：https://arxiv.org/abs/2003.03134
    代码：https://github.com/joeaortiz/gbp

  5. Watch your Up-Convolution: CNN Based Generative Deep Neural Networks are Failing to Reproduce Spectral
    论文地址：https://arxiv.org/abs/2003.01826

  6. Holistically-Attracted Wireframe Parsing
    论文地址：https://arxiv.org/abs/2003.01663

  7. AdderNet: Do We Really Need Multiplications in Deep Learning?
    论文地址：https://arxiv.org/abs/1912.13200

  8. CARS: Contunuous Evolution for Efficient Neural Architecture Search
    论文地址：https://arxiv.org/abs/1909.04977
    代码：https://github.com/huawei-noah/CARS

  9. Π-nets: Deep Polynomial Neural Networksv
    论文地址：https://arxiv.org/abs/2003.03828

  10. Explaining Knowledge Distillation by Quantifying the Knowledge
    论文地址：https://arxiv.org/abs/2003.03622

超分辨率

  1. Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video Super-Resolution
    论文地址：https://arxiv.org/abs/2002.11616

  2. Closed-loop Matters: Dual Regression Networks for Single Image Super-Resolution
    论文地址：https://arxiv.org/abs/2003.07018
    代码：https://github.com/guoyongcs/DRN

视觉常识 / 其他

  1. Visual Commonsense R-CNN
    论文地址：https://arxiv.org/abs/2002.12204
    代码：https://github.com/Wangt-CN/VC-R-CNN

  2. Scalable Uncertainty for Computer Vision with Functional Variational Inference
    论文地址：https://arxiv.org/abs/2003.03396

  3. Deep Representation Learning on Long-tailed Data: A Learnable Embedding Augmentation Perspective
    论文地址：https://arxiv.org/abs/2002.10826

  4. Representations, Metrics and Statistics For Shape Analysis of Elastic Graphs
    论文地址：https://arxiv.org/abs/2003.00287

  5. Filter Grafting for Deep Neural Networks
    论文地址：https://arxiv.org/abs/2001.05868
    代码：https://github.com/fxmeng/filter-grafting.git

  6. 12-in-1: Multi-Task Vision and Language Representation Learning
    论文地址：https://arxiv.org/abs/1912.02315

  7. Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training
    论文地址：https://arxiv.org/abs/2002.10638
    代码：https://github.com/weituo12321/PREVALENT

  8. Unbiased Scene Graph Generation from Biased Training
    论文地址：https://arxiv.org/abs/2002.11949

  9. Towards Visually Explaining Variational Autoencoders
    论文地址：https://arxiv.org/abs/1911.07389

  10. BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition
    论文地址：http://www.weixiushen.com/publication/cvpr20_BBN.pdf
    代码：https://github.com/Megvii-Nanjing/BBN

  11. High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks
    论文地址：https://arxiv.org/abs/1905.13545

  12. SAM: The Sensitivity of Attribution Methods to Hyperparameters
    论文地址：http://s.anhnguyen.me/sam_cvpr2020.pdf
    代码：https://github.com/anguyen8/sam

  13. Π− nets: Deep Polynomial Neural Networks
    论文地址：https://arxiv.org/abs/2003.03828

  14. Towards Backward-Compatible Representation Learning
    论文地址：https://arxiv.org/abs/2003.11942

  15. On Translation Invariance in CNNs: Convolutional Layers can Exploit Absolute Spatial Location
    论文地址：https://arxiv.org/abs/2003.07064

  16. KeypointNet: A Large-scale 3D Keypoint Dataset Aggregated from Numerous Human Annotations（数据集）
    论文地址：https://arxiv.org/abs/2002.12687
    https://blog.csdn.net/Extremevision/article/details/104789697