置顶 极市平台 2020-03-11 09:37:00
16306
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。
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
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/ATSSFew-Shot Object Detection with Attention-RPN and Multi-Relation Detector
论文地址:https://arxiv.org/abs/1908.01998AugFPN: Improving Multi-scale Feature Learning for Object Detection
论文地址:https://arxiv.org/abs/1912.05384Hit-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.pytorchMulti-task Collaborative Network for Joint Referring Expression Comprehension and Segmentation
论文地址:https://arxiv.org/abs/2003.08813CentripetalNet: 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
Semi-Supervised Semantic Image Segmentation with Self-correcting Networks
论文地址:https://arxiv.org/abs/1811.07073Deep Snake for Real-Time Instance Segmentation
论文地址:https://arxiv.org/abs/2001.01629CenterMask : Real-Time Anchor-Free Instance Segmentation
论文地址:https://arxiv.org/abs/1911.06667
代码:https://github.com/youngwanLEE/CenterMaskSketchGCN: Semantic Sketch Segmentation with Graph Convolutional Networks
论文地址:https://arxiv.org/abs/2003.00678PolarMask: Single Shot Instance Segmentation with Polar Representation
论文地址:https://arxiv.org/abs/1909.13226
代码:https://github.com/xieenze/PolarMaskxMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation
论文地址:https://arxiv.org/abs/1911.12676BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation
论文地址:https://arxiv.org/abs/2001.00309Enhancing Generic Segmentation with Learned Region Representations
论文地址:https://arxiv.org/abs/1911.08564
人脸识别
Towards Universal Representation Learning for Deep Face Recognition
论文地址:https://arxiv.org/abs/2002.11841Suppressing 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-NetworkFace X-ray for More General Face Forgery Detection
论文地址:https://arxiv.org/pdf/1912.13458.pdfPose Agnostic Cross-spectral Hallucination via Disentangling Independent Factors
论文地址:https://arxiv.org/abs/1909.04365Deep 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-SGTDLearning 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
- ROAM: Recurrently Optimizing Tracking Model
论文地址:https://arxiv.org/abs/1907.12006
三维点云 & 重建
PF-Net: Point Fractal Network for 3D Point Cloud Completion
论文地址:https://arxiv.org/abs/2003.00410PointAugment: 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/Learning multiview 3D point cloud registration
论文地址:https://arxiv.org/abs/2001.05119C-Flow: Conditional Generative Flow Models for Images and 3D Point Clouds
论文地址:https://arxiv.org/abs/1912.07009RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds
论文地址:https://arxiv.org/abs/1911.11236Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image
论文地址:https://arxiv.org/abs/2002.12212Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion
论文地址:https://arxiv.org/abs/2003.01456In Perfect Shape: Certifiably Optimal 3D Shape Reconstruction from 2D Landmarks
论文地址:https://arxiv.org/pdf/1911.11924.pdfAttentive 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 YiPQ-NET: A Generative Part Seq2Seq Network for 3D Shapes
论文地址:https://arxiv.org/abs/1911.10949SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D Scans
论文地址:https://arxiv.org/abs/1912.00036Cascade 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-stereoUnsupervised 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
Learning to Shade Hand-drawn Sketches
论文地址:https://arxiv.org/abs/2002.11812Single Image Reflection Removal through Cascaded Refinement
论文地址:https://arxiv.org/abs/1911.06634Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Data
论文地址:https://arxiv.org/abs/2002.11297Deep Image Harmonization via Domain Verification
论文地址:https://arxiv.org/abs/1911.13239
代码:https://github.com/bcmi/Image_Harmonization_DatasetsRoutedFusion: Learning Real-time Depth Map Fusion
论文地址:https://arxiv.org/pdf/2001.04388.pdfNeural Contours: Learning to Draw Lines from 3D Shapes
论文地址:https://arxiv.org/abs/2003.10333Towards Photo-Realistic Virtual Try-On by Adaptively Generating 鈫 Preserving Image Content
论文地址:https://arxiv.org/abs/2003.05863Reinforced 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/1912.00623Correspondence Networks with Adaptive Neighbourhood Consensus(图像处理 - 图像特征匹配)
论文地址:https://arxiv.org/abs/2003.12059Normalized 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
Self-training with Noisy Student improves ImageNet classification
论文地址:https://arxiv.org/abs/1911.04252Image Matching across Wide Baselines: From Paper to Practice
论文地址:https://arxiv.org/abs/2003.01587Towards Robust Image Classification Using Sequential Attention Models
论文地址:https://arxiv.org/abs/1912.02184Learning in the Frequency Domain
论文地址:https://arxiv.org/abs/2002.12416Learning from Web Data with Memory Module
论文地址:https://arxiv.org/abs/1906.12028Making 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
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/VIBEDistribution-Aware Coordinate Representation for Human Pose Estimation
论文地址:https://arxiv.org/abs/1910.06278
代码:https://github.com/ilovepose/DarkPose4D Association Graph for Realtime Multi-person Motion Capture Using Multiple Video Cameras
论文地址:https://arxiv.org/abs/2002.12625Optimal least-squares solution to the hand-eye calibration problem
论文地址:https://arxiv.org/abs/2002.10838D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry
论文地址:https://arxiv.org/abs/2003.01060Multi-Modal Domain Adaptation for Fine-Grained Action Recognition
论文地址:https://arxiv.org/abs/2001.09691Distribution Aware Coordinate Representation for Human Pose Estimation
论文地址:https://arxiv.org/abs/1910.06278The Devil is in the Details: Delving into Unbiased Data Processing for Human Pose Estimation
论文地址:https://arxiv.org/abs/1911.07524PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimation
论文地址:https://arxiv.org/abs/1911.04231Action Segmentation with Joint Self-Supervised Temporal Domain Adaptation
论文地址:https://arxiv.org/abs/2003.02824G2L-Net: Global to Local Network for Real-time 6D Pose Estimation with Embedding Vector Features
论文地址:https://arxiv.org/abs/2003.11089Deep 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
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/ZeroShotVideoClassificationSay As You Wish: Fine-grained Control of Image Caption Generation with Abstract Scene Graphs
论文地址:https://arxiv.org/abs/2003.00387Fine-grained Video-Text Retrieval with Hierarchical Graph Reasoning
论文地址:https://arxiv.org/abs/2003.00392Object Relational Graph with Teacher-Recommended Learning for Video Captioning
论文地址:https://arxiv.org/abs/2002.11566Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video Super-Resolution
论文地址:https://arxiv.org/abs/2002.11616Blurry Video Frame Interpolation
论文地址:https://arxiv.org/abs/2002.12259Hierarchical Conditional Relation Networks for Video Question Answering
论文地址:https://arxiv.org/abs/2002.10698Action Modifiers:Learning from Adverbs in Instructional Video
论文地址:https://arxiv.org/abs/1912.06617Visual Grounding in Video for Unsupervised Word Translation
论文地址:https://arxiv.org/abs/2003.05078
代码:https://github.com/gsig/visual-groundingMaskFlownet: 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/MaskFlownetUse 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
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/adetIterative Answer Prediction with Pointer-Augmented Multimodal Transformers for TextVQA
论文地址:https://arxiv.org/abs/1911.06258
GAN
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/ylgMSG-GAN: Multi-Scale Gradient GAN for Stable Image Synthesis
论文地址:https://arxiv.org/abs/1903.06048Robust Design of Deep Neural Networks against Adversarial Attacks based on Lyapunov Theory
论文地址:https://arxiv.org/abs/1911.04636PSGAN: 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
Improved Few-Shot Visual Classification
论文地址:https://arxiv.org/pdf/1912.03432.pdfMeta-Transfer Learning for Zero-Shot Super-Resolution
论文地址:https://arxiv.org/abs/2002.12213Instance 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
Rethinking the Route Towards Weakly Supervised Object Localization
论文地址:https://arxiv.org/abs/2002.11359NestedVAE: Isolating Common Factors via Weak Supervision
论文地址:https://arxiv.org/abs/2002.11576Unsupervised Reinforcement Learning of Transferable Meta-Skills for Embodied Navigation
论文地址:https://arxiv.org/abs/1911.07450Disentangling Physical Dynamics from Unknown Factors for Unsupervised Video Prediction
论文地址:https://arxiv.org/abs/2003.01460ClusterFit: Improving Generalization of Visual Representations
论文地址:https://arxiv.org/abs/1912.03330Auto-Encoding Twin-Bottleneck Hashing
论文地址:https://arxiv.org/abs/2002.11930Learning Representations by Predicting Bags of Visual Words
论文地址:https://arxiv.org/abs/2002.12247A Characteristic Function Approach to Deep Implicit Generative Modeling
论文地址:https://arxiv.org/abs/1909.07425Unsupervised 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
Cross-modality Person re-identification with Shared-Specific Feature Transfer
论文地址:https://arxiv.org/abs/2002.12489Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction
论文地址:https://arxiv.org/abs/2002.11927The 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
GhostNet: More Features from Cheap Operations
论文地址:https://arxiv.org/abs/1911.11907
代码:https://github.com/iamhankai/ghostnetWatch your Up-Convolution: CNN Based Generative Deep Neural Networks are Failing to Reproduce Spectral
论文地址:https://arxiv.org/abs/2003.01826GPU-Accelerated Mobile Multi-view Style Transfer
论文地址:https://arxiv.org/abs/2003.00706Bundle Adjustment on a Graph Processor
论文地址:https://arxiv.org/abs/2003.03134
代码:https://github.com/joeaortiz/gbpWatch your Up-Convolution: CNN Based Generative Deep Neural Networks are Failing to Reproduce Spectral
论文地址:https://arxiv.org/abs/2003.01826Holistically-Attracted Wireframe Parsing
论文地址:https://arxiv.org/abs/2003.01663AdderNet: Do We Really Need Multiplications in Deep Learning?
论文地址:https://arxiv.org/abs/1912.13200CARS: Contunuous Evolution for Efficient Neural Architecture Search
论文地址:https://arxiv.org/abs/1909.04977
代码:https://github.com/huawei-noah/CARSΠ-nets: Deep Polynomial Neural Networksv
论文地址:https://arxiv.org/abs/2003.03828Explaining Knowledge Distillation by Quantifying the Knowledge
论文地址:https://arxiv.org/abs/2003.03622
超分辨率
Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video Super-Resolution
论文地址:https://arxiv.org/abs/2002.11616Closed-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
Visual Commonsense R-CNN
论文地址:https://arxiv.org/abs/2002.12204
代码:https://github.com/Wangt-CN/VC-R-CNNScalable Uncertainty for Computer Vision with Functional Variational Inference
论文地址:https://arxiv.org/abs/2003.03396Deep Representation Learning on Long-tailed Data: A Learnable Embedding Augmentation Perspective
论文地址:https://arxiv.org/abs/2002.10826Representations, Metrics and Statistics For Shape Analysis of Elastic Graphs
论文地址:https://arxiv.org/abs/2003.00287Filter Grafting for Deep Neural Networks
论文地址:https://arxiv.org/abs/2001.05868
代码:https://github.com/fxmeng/filter-grafting.git12-in-1: Multi-Task Vision and Language Representation Learning
论文地址:https://arxiv.org/abs/1912.02315Towards 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/PREVALENTUnbiased Scene Graph Generation from Biased Training
论文地址:https://arxiv.org/abs/2002.11949Towards Visually Explaining Variational Autoencoders
论文地址:https://arxiv.org/abs/1911.07389BBN: 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/BBNHigh Frequency Component Helps Explain the Generalization of Convolutional Neural Networks
论文地址:https://arxiv.org/abs/1905.13545SAM: The Sensitivity of Attribution Methods to Hyperparameters
论文地址:http://s.anhnguyen.me/sam_cvpr2020.pdf
代码:https://github.com/anguyen8/samΠ− nets: Deep Polynomial Neural Networks
论文地址:https://arxiv.org/abs/2003.03828Towards Backward-Compatible Representation Learning
论文地址:https://arxiv.org/abs/2003.11942On Translation Invariance in CNNs: Convolutional Layers can Exploit Absolute Spatial Location
论文地址:https://arxiv.org/abs/2003.07064KeypointNet: 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