本贴是对 CVPR2021 已接受论文的粗略汇总，后期会有更详细的总结。期待ing......

官网链接：http://cvpr2021.thecvf.com
开会时间：2021年6月19日-6月25日
论文接收公布时间：2021年2月28日

接收论文IDs：

• CVPR 2021 接收论文列表！27%接受率！

• 姿态
  • SimPoE: Simulated Character Control for 3D Human Pose Estimation
    😮oral🏠project
  • Reconstructing 3D Human Pose by Watching Humans in the Mirror
    😮oral⭐code🏠project
• 三维
  • NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video
    😮oral⭐code🏠project
  • RGB-D Local Implicit Function for Depth Completion of Transparent Objects
    🏠project
  • LED2-Net: Monocular 360 Layout Estimation via Differentiable Depth Rendering
    😮oral⭐code🏠project
  • Deep Two-View Structure-from-Motion Revisited
  • Fostering Generalization in Single-view 3D Reconstruction by Learning a Hierarchy of Local and Global Shape Priors
• 跟踪
  • Online Multiple Object Tracking with Cross-Task Synergy
    ⭐code
• 分类
  • A Realistic Evaluation of Semi-Supervised Learning for Fine-Grained Classification
    😮oral
• 长尾识别
  • Improving Calibration for Long-Tailed Recognition
    ⭐code
• 深度学习
  • Towards Evaluating and Training Verifiably Robust Neural Networks
    😮oral⭐code
• SR
  • Unsupervised Degradation Representation Learning for Blind Super-Resolution
    ⭐code
• NAS
  • One-Shot Neural Ensemble Architecture Search by Diversity-Guided Search Space Shrinking
    ⭐code
• Transformer
  • LoFTR: Detector-Free Local Feature Matching with Transformers
    ⭐code🏠project
• 未分
  • PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relighting
    🏠project

🎆🎆🎆更新提示：4月1日新增39篇(1分割+2三维+2跟踪+1姿态+2点云+2分类+1视频+1剪枝+1检索+1成像+2域适应+1无人机+1图像压缩+2持续学习+5目标检测+2风格迁移+1视图合成+1相机定位+1类增量学习+2AR+2GAN+5未分)

• 分割
  • PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clustering
• 三维
  • Semi-supervised Synthesis of High-Resolution Editable Textures for 3D Humans
  • 3D Packing for Self-Supervised Monocular Depth Estimation
    😮oral⭐code
• 跟踪
  • Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark
    🏠project📺video
  • SiamGAT: Graph Attention Tracking
    ⭐code
• 姿态
  • Human POSEitioning System (HPS): 3D Human Pose Estimation and Self-localization in Large Scenes from Body-Mounted Sensors
    🏠project
• 点云
  • Denoise and Contrast for Category Agnostic Shape Completion
    ⭐code
  • Point2Skeleton: Learning Skeletal Representations from Point Clouds
    😮oral⭐code🏠project
• 分类
  • Fine-Grained Few-Shot Classification with Feature Map Reconstruction Networks
  • SimPLE: Similar Pseudo Label Exploitation for Semi-Supervised Classification
    ⭐code
• 视频
  • Learning by Aligning Videos in Time
• 剪枝
  • Neural Response Interpretation through the Lens of Critical Pathways
    ⭐code|code
• 检索
  • Convolutional Hough Matching
    😮oral🏠project
• 成像
  • Mask-ToF: Learning Microlens Masks for Flying Pixel Correction in Time-of-Flight Imaging
    🏠project
• 域适应
  • Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation
    🏠project
  • Domain Consensus Clustering for Universal Domain Adaptation
    ⭐code
• 无人机
  • Dogfight: Detecting Drones from Drones Videos
• 图像压缩
  • Learning Scalable ℓ∞-constrained Near-lossless Image Compression via Joint Lossy Image and Residual Compression
    ⭐code
• 持续学习
  • Rainbow Memory: Continual Learning with a Memory of Diverse Samples
  • Rectification-based Knowledge Retention for Continual Learning
• 目标检测
  • Scale-aware Automatic Augmentation for Object Detection
    ⭐code
  • GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection
    ⭐code📺video
    论文公开
  • A Closer Look at Fourier Spectrum Discrepancies for CNN-generated Images Detection
    😮oral🏠project
  • Dense Relation Distillation with Context-aware Aggregation for Few-Shot Object Detection
    ⭐code
  • DAP: Detection-Aware Pre-training with Weak Supervision
• 风格迁移
  • Rethinking Style Transfer: From Pixels to Parameterized Brushstrokes
    ⭐code
  • ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows
    ⭐code
• 视图合成
  • Layout-Guided Novel View Synthesis from a Single Indoor Panorama
    ⭐code
• 相机定位
  • Learning Camera Localization via Dense Scene Matching
    ⭐code
• 类增量学习
  • DER: Dynamically Expandable Representation for Class Incremental Learning
    ⭐code
• AR
  • Stay Positive: Non-Negative Image Synthesis for Augmented Reality
    😮oral
  • VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalization
• GAN
  • ReMix: Towards Image-to-Image Translation with Limited Data
  • Unsupervised Disentanglement of Linear-Encoded Facial Semantics
• 未分
  • Extreme Rotation Estimation using Dense Correlation Volumes
  • Can We Characterize Tasks Without Labels or Features?
  • Embracing Uncertainty: Decoupling and De-bias for Robust Temporal Grounding
  • Online Learning of a Probabilistic and Adaptive Scene Representation
  • Generative Modelling of BRDF Textures from Flash Images
    ⭐code🏠project

• Rethinking Style Transfer: From Pixels to Parameterized Brushstrokes
  ⭐code
• ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows
  ⭐code

• Distribution Alignment: A Unified Framework for Long-tail Visual Recognition
  ⭐code

• Kaleido-BERT: Vision-Language Pre-training on Fashion Domain
  

• 图像信号处理
  • Invertible Image Signal Processing
    ⭐code🏠project
• 光谱重建
  • Tuning IR-cut Filter for Illumination-aware Spectral Reconstruction from RGB
    😮oral

• Cloud2Curve: Generation and Vectorization of Parametric Sketches

• 因果推理算法
  • ACRE: Abstract Causal REasoning Beyond Covariation
    ⭐code🏠project
• 抽象时空推理算法
  • Abstract Spatial-Temporal Reasoning via Probabilistic Abduction and Execution
    ⭐code🏠project

• Tangent Space Backpropagation for 3D Transformation Groups
  ⭐code
• 视觉里程计
  • Generalizing to the Open World: Deep Visual Odometry with Online Adaptation
• 机器人
  • Visual Room Rearrangement
    😮oral🏠project📺video
• AR
  • Stay Positive: Non-Negative Image Synthesis for Augmented Reality
    😮oral
  • 虚拟试穿
    • VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalization

• Dynamic Slimmable Network
  😮oral⭐code

• Dynamic Metric Learning: Towards a Scalable Metric Space to Accommodate Multiple Semantic Scales
  ⭐code
• Embedding Transfer with Label Relaxation for Improved Metric Learning
• Noise-resistant Deep Metric Learning with Ranking-based Instance Selection
  ⭐code

• Skeleton Based Sign Language Recognition Using Whole-body Keypoints
  ⭐code
• Read and Attend: Temporal Localisation in Sign Language Videos
  🏠project

• Deep Gaussian Scale Mixture Prior for Spectral Compressive Imaging
  ⭐code🏠project
• Mask-ToF: Learning Microlens Masks for Flying Pixel Correction in Time-of-Flight Imaging
  🏠project

• Deep Graph Matching under Quadratic Constraint

• Affect2MM: Affective Analysis of Multimedia Content Using Emotion Causality
  🏠project

• Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts
  🌻dataset
• Sewer-ML: A Multi-Label Sewer Defect Classification Dataset and Benchmark
  🏠project
• Benchmarking Representation Learning for Natural World Image Collections
  🌻dataset

• Spatially-Adaptive Pixelwise Networks for Fast Image Translation
  🏠project
  采用超网络和隐式函数，极快的图像到图像翻译速度（比基线快18倍）
• Image Generators with Conditionally-Independent Pixel Synthesis
  😮oral⭐code

• Im2Vec: Synthesizing Vector Graphics without Vector Supervision
  😮oral⭐code🏠project
• 图像生成
  • Context-Aware Layout to Image Generation with Enhanced Object Appearance
    ⭐code
• 视频生成
  • Playable Video Generation
    😮oral⭐code🏠project📺video
  • One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing
    😮oral⭐code🏠project📺video
    解读：颠覆视频压缩的不一定是新压缩算法，而可能是GAN！英伟达新算法最高压缩90%流量
    Nvidia的新研究，使用人脸关键点+GAN重建视频通话，相比传统的H.264节省90%流量。代码未开源，但英伟达的GAN框架开源了。

• AdCo: Adversarial Contrast for Efficient Learning of Unsupervised Representations from Self-Trained Negative Adversaries
  ⭐code
  解读:CVPR 2021接收论文：AdCo基于对抗的对比学习

• 场景文本检测
  • What If We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labels
  • Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition
    😮oral⭐code

• Simulating Unknown Target Models for Query-Efficient Black-box Attacks
  ⭐code
  黑盒对抗攻击
• Delving into Data: Effectively Substitute Training for Black-box Attack
  基于高效训练替代模型的黑盒攻击方法
  解读：8
• LiBRe: A Practical Bayesian Approach to Adversarial Detection
  ⭐code

• Learning Continuous Image Representation with Local Implicit Image Function
  😮oral⭐code🏠project📺video

• Structured Scene Memory for Vision-Language Navigation

• Learning Asynchronous and Sparse Human-Object Interaction in Videos
• QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information
  ⭐code
• Reformulating HOI Detection as Adaptive Set Prediction
  ⭐code

• Detecting Human-Object Interaction via Fabricated Compositional Learning
  ⭐code

• Robust Neural Routing Through Space Partitions for Camera Relocalization in Dynamic Indoor Environments
  😮oral
• Back to the Feature: Learning Robust Camera Localization from Pixels to Pose
  ⭐code
• Learning Camera Localization via Dense Scene Matching
  ⭐code

• Scan2Cap: Context-aware Dense Captioning in RGB-D Scans
  ⭐code🏠project📺video
• VX2TEXT: End-to-End Learning of Video-Based Text Generation From Multimodal Inputs
  视频字幕、视频问答和视频对话任务的多模式框架
• Open-book Video Captioning with Retrieve-Copy-Generate Network

• 图像字幕
  • Human-like Controllable Image Captioning with Verb-specific Semantic Roles
    ⭐code

• Vab-AL: Incorporating Class Imbalance and Difficulty with Variational Bayes for Active Learning

• Learning the Predictability of the Future
  预测未来
  ⭐code🏠project📺video
  

• VirTex: Learning Visual Representations from Textual Annotations
  ⭐code

• Learning the Superpixel in a Non-iterative and Lifelong Manner
  论文公开

• Fair Attribute Classification through Latent Space De-biasing
  ⭐code🏠project
  

• IIRC: Incremental Implicitly-Refined Classification
  🏠project
  
• Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learning
• DER: Dynamically Expandable Representation for Class Incremental Learning
  ⭐code

• Rainbow Memory: Continual Learning with a Memory of Diverse Samples
  
• Training Networks in Null Space for Continual Learning
  😮oral⭐code

• Efficient Feature Transformations for Discriminative and Generative Continual Learning
• Rainbow Memory: Continual Learning with a Memory of Diverse Samples
• Rectification-based Knowledge Retention for Continual Learning

• Coarse-Fine Networks for Temporal Activity Detection in Videos
  
• 3D CNNs with Adaptive Temporal Feature Resolutions
  
• Understanding the Robustness of Skeleton-based Action Recognition under Adversarial Attack
• BASAR:Black-box Attack on Skeletal Action Recognition
  📺video
• TDN: Temporal Difference Networks for Efficient Action Recognition
  ⭐code
• ACTION-Net: Multipath Excitation for Action Recognition
  ⭐code
  解读：CVPR 2021 | 用于动作识别，即插即用、混合注意力机制的 ACTION 模块
• No frame left behind: Full Video Action Recognition

• Recognizing Actions in Videos from Unseen Viewpoints
• 时序动作定位
  • Modeling Multi-Label Action Dependencies for Temporal Action Localization
    😮oral
    提出基于注意力的网络架构来学习视频中的动作依赖性，用于解决多标签时间动作定位任务。
  • Learning Salient Boundary Feature for Anchor-free Temporal Action Localization
    基于显著边界特征学习的无锚框时序动作定位
    解读：10
  • The Blessings of Unlabeled Background in Untrimmed Videos
  • Temporal Context Aggregation Network for Temporal Action Proposal Refinement
  • Learning Salient Boundary Feature for Anchor-free Temporal Action Localization
  • CoLA: Weakly-Supervised Temporal Action Localization with Snippet Contrastive Learning

• Improving Unsupervised Image Clustering With Robust Learning
  ⭐code
  利用鲁棒学习改进无监督图像聚类技术
  

• Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized Labels
  ⭐code
  

• 细粒度分类
  • Fine-grained Angular Contrastive Learning with Coarse Labels
    😮oral
    使用自监督进行 Coarse Labels（粗标签）的细粒度分类方面的工作。粗标签与细粒度标签相比，更容易和更便宜，因为细粒度标签通常需要域专家。
  • Graph-based High-Order Relation Discovery for Fine-grained Recognition
    基于特征间高阶关系挖掘的细粒度识别方法
    解读：20
  • Fine-Grained Few-Shot Classification with Feature Map Reconstruction Networks
• 图像分类
  • MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition
  • PML: Progressive Margin Loss for Long-tailed Age Classification
    
  • Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification
    🏠project(https://www.kaihan.org/HybridLT/)
  • Capsule Network is Not More Robust than Convolutional Network
  • Model-Contrastive Federated Learning
• 半监督图像分类
  • SimPLE: Similar Pseudo Label Exploitation for Semi-Supervised Classification
    ⭐code

• FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation
  ⭐code
  
• GDR-Net: Geometry-Guided Direct Regression Network for Monocular 6D Object Pose Estimation
  ⭐code
• FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanism
  😮oral⭐code

• ID-Unet: Iterative Soft and Hard Deformation for View Synthesis
• NeX: Real-time View Synthesis with Neural Basis Expansion
  😮oral🏠project📺video
  利用神经基础扩展的实时视图合成技术
• Layout-Guided Novel View Synthesis from a Single Indoor Panorama
  ⭐code

• Counterfactual Zero-Shot and Open-Set Visual Recognition
  ⭐code
  
• Few-shot Open-set Recognition by Transformation Consistency
  
• Learning Placeholders for Open-Set Recognition
  😮oral

• DeRF: Decomposed Radiance Fields
  🏠project
  
• D-NeRF: Neural Radiance Fields for Dynamic Scenes
  🏠project
  

• Neural Lumigraph Rendering
  🌻dataset🏠project📺video
  斯坦福大学
• AutoInt: Automatic Integration for Fast Neural Volume Rendering
  😮oral🏠project📺video
  斯坦福大学
• pixelNeRF: Neural Radiance Fields from One or Few Images
  ⭐code🏠project📺video
• IBRNet: Learning Multi-View Image-Based Rendering
  🏠project
  备注：有学者评论pixelNeRF和IBRNet的工作**相近，但IBRNet似乎更加成熟。
• Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans
  ⭐code:project📺video
  浙大等学者发明的Neural Body算法，输入多角度视频可输出3D人体和新角度视图。
• NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesis
  🏠project📺video
  在任意照明条件下，根据一组输入图像生成完整的3D场景
• Self-Supervised Visibility Learning for Novel View Synthesis
  ⭐code

• Camera-Space Hand Mesh Recovery via Semantic Aggregation and Adaptive 2D-1D Registration
  ⭐code
  
• Monocular Real-time Full Body Capture with Inter-part Correlations
  📺video
  在电影动作特效中，人体运动捕捉是关键技术，高质量的捕捉往往需要特殊设备，而如果能使用普通RGB相机进行运动捕捉，将会使人人都是特效师。该视频来自清华、马普所等单位的学者发表于CVPR2021的论文结果，使用单目RGB相机的动作捕捉。
• Behavior-Driven Synthesis of Human Dynamics
  ⭐code🏠project
• Learning Compositional Representation for 4D Captures with Neural ODE

• 3D手部重建
  • Model-based 3D Hand Reconstruction via Self-Supervised Learning
• 人体运动迁移
  • Few-Shot Human Motion Transfer by Personalized Geometry and Texture Modeling
    ⭐code📺video
• Human Volumetric Capture
  • POSEFusion: Pose-guided Selective Fusion for Single-view Human Volumetric Capture
    😮oral🏠project
• 3D人体姿态估计
  • CanonPose: Self-supervised Monocular 3D Human Pose Estimation in the Wild
  • Context Modeling in 3D Human Pose Estimation: A Unified Perspective
  • PCLs: Geometry-aware Neural Reconstruction of 3D Pose with Perspective Crop Layers
    📺video
    通过消除 location-dependent 透视效果来改进3D人体姿势估计技术工作。
    
  • Graph Stacked Hourglass Networks for 3D Human Pose Estimation
  • Human POSEitioning System (HPS): 3D Human Pose Estimation and Self-localization in Large Scenes from Body-Mounted Sensors
    🏠project
• 动物姿态估计
  • From Synthetic to Real: Unsupervised Domain Adaptation for Animal Pose Estimation
    ⭐code

• Densely connected multidilated convolutional networks for dense prediction tasks
  提出的D3Net在语义分割&音乐源分离任务上的表现优于SOTA网络
  
• Dense Contrastive Learning for Self-Supervised Visual Pre-Training
  ⭐code

• Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning
  ⭐code

• Cross Modal Focal Loss for RGBD Face Anti-Spoofing
  

• VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples
  ⭐code
• Learning by Aligning Videos in Time
• 视频摘要
  • Learning Discriminative Prototypes with Dynamic Time Warping
    ⭐code
• 视频编解码
  • MetaSCI: Scalable and Adaptive Reconstruction for Video Compressive Sensing
    ⭐code
• 视频插帧
  • FLAVR: Flow-Agnostic Video Representations for Fast Frame Interpolation
    ⭐code🏠project
    
• 视频语言学习（video-and-language learning）
  • Less is More: CLIPBERT for Video-and-Language Learning via Sparse Sampling
    😮oral⭐code
    
• 视频预测
  • Greedy Hierarchical Variational Autoencoders for Large-Scale Video Prediction
    🏠project📺video
• 视频理解
  • Context-aware Biaffine Localizing Network for Temporal Sentence Grounding
    ⭐code
  • Co-Grounding Networks with Semantic Attention for Referring Expression Comprehension in Videos
    🏠project
• 视频缩放
  • Video Rescaling Networks with Joint Optimization Strategies for Downscaling and Upscaling
    ⭐code🏠project

• A Deep Emulator for Secondary Motion of 3D Characters
  
• Neural Deformation Graphs for Globally-consistent Non-rigid Reconstruction
  😮oral🏠project📺video
  
• Deep Implicit Templates for 3D Shape Representation
  😮oral⭐code🏠project📺video
  CVPR 2021 Oral，清华学者提出Deep Implicit Templates，极大扩展DIF能力
  
• SMPLicit: Topology-aware Generative Model for Clothed People
  🏠project
• Picasso: A CUDA-based Library for Deep Learning over 3D Meshes
  ⭐code
• Semi-supervised Synthesis of High-Resolution Editable Textures for 3D Humans

• 深度估计
  • PLADE-Net: Towards Pixel-Level Accuracy for Self-Supervised Single-View Depth Estimation with Neural Positional Encoding and Distilled Matting Loss
  • Beyond Image to Depth: Improving Depth Prediction using Echoes
    ⭐code🏠project
  • Learning High Fidelity Depths of Dressed Humans by Watching Social Media Dance Videos
    😮oral⭐code🏠project📺video
  • 3D Packing for Self-Supervised Monocular Depth Estimation
    😮oral⭐code
• 三维重建
  • Deep Implicit Moving Least-Squares Functions for 3D Reconstruction
    ⭐code
  • Bilevel Online Adaptation for Out-of-Domain Human Mesh Reconstruction
    🏠project
  • Learning Parallel Dense Correspondence from Spatio-Temporal Descriptors for Efficient and Robust 4D Reconstruction
    ⭐code

• Hierarchical and Partially Observable Goal-driven Policy Learning with Goals Relational Graph
  ⭐code🏠project
• Unsupervised Learning for Robust Fitting:A Reinforcement Learning Approach

• Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition
  ⭐code
  ECCV 2020 Facebook Mapillary Visual Place Recognition Challenge 冠军方案

• Convex Online Video Frame Subset Selection using Multiple Criteria for Data Efficient Autonomous Driving

• 3D Graph Anatomy Geometry-Integrated Network for Pancreatic Mass Segmentation, Diagnosis, and Quantitative Patient Management
  用纯多模态 CT 影像可替代目前 JHMI 的需要做肿瘤化学检测和 DNA 测序+医学影像的综合多模态诊断流程，从诊断准确度上有可比较性，定量诊断精度更优
  
• Deep Lesion Tracker: Monitoring Lesions in 4D Longitudinal Imaging Studies
  肿瘤影像里面智能 PACS 辅助医生读片的重要功能
  
• Automatic Vertebra Localization and Identification in CT by Spine Rectification and Anatomically-constrained Optimization
  基于CT 影像的骨折/骨质疏松系统
  
• Multi-institutional Collaborations for Improving Deep Learning-based Magnetic Resonance Image Reconstruction Using Federated Learning
  ⭐code
  多机构合作，利用联合学习改进基于深度学习的磁共振图像重建技术
  
• DeepTag: An Unsupervised Deep Learning Method for Motion Tracking on Cardiac Tagging Magnetic Resonance Images
  😮oral⭐code
  DeepTag: 一种无监督的深度学习方法，用于心脏标记磁共振图像的运动跟踪
  
• Multiple Instance Captioning: Learning Representations from Histopathology Textbooks and Articles

• XProtoNet: Diagnosis in Chest Radiography with Global and Local Explanations
• 医学图像分割
  • FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Space
    ⭐code
  • DoDNet: Learning to segment multi-organ and tumors from multiple partially labeled datasets
    ⭐code
  • DiNTS: Differentiable Neural Network Topology Search for 3D Medical Image Segmentation
• 医学图像合成
  • Brain Image Synthesis with Unsupervised Multivariate Canonical CSCℓ4Net
    😮oral

• Transformer Interpretability Beyond Attention Visualization
  ⭐code
  
• MIST: Multiple Instance Spatial Transformer Network
  试图从热图中进行可微的top-K选择(MIST)（目前在自然图像上也有了一些结果；) 用它可以在没有任何定位监督的情况下进行检测和分类（并不是它唯一能做的事情!）

• 动作识别检测
  • 3D Vision Transformers for Action Recognition
    用于动作识别的3D视觉Transformer
• 目标检测
  • UP-DETR: Unsupervised Pre-training for Object Detection with Transformers
    😮oral⭐code
• 图像处理
  • Pre-Trained Image Processing Transformer
    
• 人机交互
  • End-to-End Human Object Interaction Detection with HOI Transformer
    ⭐code
• 图像分割
  • Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
    ⭐code🏠project
    基于Transformers从序列到序列的角度重新思考语义分割
    解读：16
    解读：Transformer 在语义分割中的应用，曾位ADE20K 榜首（44.42% mIoU）
  • VisTR: End-to-End Video Instance Segmentation with Transformers
    😮oral⭐code
• 跟踪
  • Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking
    😮oral⭐code
    more:Transformer再蓄力，跟踪任务中创新高，桥接独立帧，跨帧传递时域信息，CVPR 2021 Oral
  • Transformer Tracking
    ⭐code
• 动作预测
  • Multimodal Motion Prediction with Stacked Transformers
    ⭐code🏠project📺video
• Self-attention自注意力机制
  • Scaling Local Self-Attention For Parameter Efficient Visual Backbones
    😮oral
• 检索
  • Revamping Cross-Modal Recipe Retrieval with Hierarchical Transformers and Self-supervised Learning
    ⭐code

• Meta Batch-Instance Normalization for Generalizable Person Re-Identification
  
• Watching You: Global-guided Reciprocal Learning for Video-based Person Re-identification
• Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-Identification
  ⭐code
• [Self-supervised 3D Reconstruction and Re-Projection for Texture Insensitive Person Re-identification]
  基于自监督三维重建和重投影的纹理不敏感行人重识别
  解读：12
• Intra-Inter Camera Similarity for Unsupervised Person Re-Identification
  ⭐code
  论文公开
• Anchor-Free Person Search
  ⭐code

• Lifelong Person Re-Identification via Adaptive Knowledge Accumulation
  ⭐code
• Group-aware Label Transfer for Domain Adaptive Person Re-identification
  ⭐code|code
• 拥挤人群计数
  • Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting

• Learning Student Networks in the Wild
  
• ReXNet: Diminishing Representational Bottleneck on Convolutional Neural Network
  ⭐code
  
• RepVGG: Making VGG-style ConvNets Great Again
  ⭐code
  
• Coordinate Attention for Efficient Mobile Network Design
  ⭐code

• 剪枝
  • Manifold Regularized Dynamic Network Pruning
  • Neural Response Interpretation through the Lens of Critical Pathways
    ⭐code|code
• 模型扩展
  • Fast and Accurate Model Scaling
    ⭐code
• 量化
  • Learnable Companding Quantization for Accurate Low-bit Neural Networks
  • Diversifying Sample Generation for Accurate Data-Free Quantization
  • Zero-shot Adversarial Quantization
    😮oral⭐code
• 知识蒸馏
  • Refine Myself by Teaching Myself: Feature Refinement via Self-Knowledge Distillation
    ⭐code
  • Complementary Relation Contrastive Distillation
• 可逆神经网络
  • Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks
    🏠project
• 模型压缩
  • CDFI: Compression-Driven Network Design for Frame Interpolation
    ⭐code

• Dogfight: Detecting Drones from Drone Videos
  

• 航空影像分割
  • PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation
    ⭐code
• 航空影像检测
  • ReDet: A Rotation-equivariant Detector for Aerial Object Detection
    ⭐code
• 无人机检测
  • Dogfight: Detecting Drones from Drones Videos

• Data-Free Knowledge Distillation For Image Super-Resolution
  
• AdderSR: Towards Energy Efficient Image Super-Resolution
  ⭐code
  
• Cross-MPI: Cross-scale Stereo for Image Super-Resolution using Multiplane Images
  🏠project📺video
  CVPR 2021，Cross-MPI以底层场景结构为线索的端到端网络，在大分辨率（x8）差距下也可完成高保真的超分辨率
• ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic
  ⭐code

• Robust Reference-based Super-Resolution via C²-Matching
• GLEAN: Generative Latent Bank for Large-Factor Image Super-Resolution
  😮oral🏠project
• BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond
  ⭐code🏠project
• [Temporal Modulation Network for Controllable Space-Time Video Super-Resolution]
  作者主页
  基于时空特征可控插值的视频超分辨率网络
  解读：18
• Flow-based Kernel Prior with Application to Blind Super-Resolution

• Weakly-supervised Grounded Visual Question Answering using Capsules
  

• Counterfactual VQA: A Cause-Effect Look at Language Bias
  ⭐code
• AGQA: A Benchmark for Compositional Spatio-Temporal Reasoning
• Domain-robust VQA with diverse datasets and methods but no target labels
• 视频问答
  • TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Events
    ⭐code

• Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing
  
• Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation
  ⭐code🏠project
  
• Hijack-GAN: Unintended-Use of Pretrained, Black-Box GANs
  
• Image-to-image Translation via Hierarchical Style Disentanglement
  ⭐code
• Efficient Conditional GAN Transfer with Knowledge Propagation across Classes
  ⭐code
• Anycost GANs for Interactive Image Synthesis and Editing
  ⭐code🏠project📺video
  Anycost GAN，可适应广泛的硬件和延迟要求，以及实现交互式图像编辑
• TediGAN: Text-Guided Diverse Image Generation and Manipulation
  ⭐code🏠project📺video
• Generative Hierarchical Features from Synthesizing Images
  😮oral⭐code🏠project
  作者称预训练 GAN 生成器可以当作是一种学习的多尺度损失。用它进行训练可以带来高度竞争的层次化和分离的视觉特征，称之为生成层次化特征（GH-Feat）。并进一步表明，GH-Feat不仅有利于生成性任务，更重要的是有利于分辨性任务，包括人脸验证、关键点检测、layout prediction、迁移学习、style mixing、图像编辑等。
• Teachers Do More Than Teach: Compressing Image-to-Image Models
• PISE: Person Image Synthesis and Editing with Decoupled GAN
  ⭐code
• LOHO: Latent Optimization of Hairstyles via Orthogonalization
• Image-to-image Translation via Hierarchical Style Disentanglement
  😮oral⭐code
  在图像到图像翻译上实现层次风格解耦
• CoMoGAN: continuous model-guided image-to-image translation
  😮oral⭐code
• HumanGAN: A Generative Model of Humans Images
• HistoGAN: Controlling Colors of GAN-Generated and Real Images via Color Histograms
  ⭐code
• DivCo: Diverse Conditional Image Synthesis via Contrastive Generative Adversarial Network
  ⭐code

• pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis
  😮oral🏠project📺video
  更多：斯坦福学者提出周期性隐式生成对抗网络（π-GAN或pi-GAN），用于高质量的3D感知图像合成
  斯坦福大学
• ReMix: Towards Image-to-Image Translation with Limited Data
• Unsupervised Disentanglement of Linear-Encoded Facial Semantics

• 小样本学习
  • Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning
    
  • Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning
    
  • Learning Dynamic Alignment via Meta-filter for Few-shot Learning
    作者主页
    通过元卷积核实现基于动态对齐的小样本学习
    解读：17
• 域泛化
  • FSDR: Frequency Space Domain Randomization for Domain Generalization
    受 JPEG 将空间图像转换为多个频率分量(FCs)的启发，提出频率空间域随机化(FSDR)，通过保留域变量FCs(DIFs)和只随机化域变量FCs(DVFs)来随机化频率空间的图像。
  • Domain Generalization via Inference-time Label-Preserving Target Projections
    😮 Oral
  • Adaptive Methods for Real-World Domain Generalization
  • Progressive Domain Expansion Network for Single Domain Generalization
    ⭐code
• 零样本学习
  • Goal-Oriented Gaze Estimation for Zero-Shot Learning⭐code
  • Contrastive Embedding for Generalized Zero-Shot Learning
    ⭐code
• 域适应
  • Dynamic Transfer for Multi-Source Domain Adaptation
    ⭐code
  • Transferable Semantic Augmentation for Domain Adaptation
  • MetaAlign: Coordinating Domain Alignment and Classification for Unsupervised Domain Adaptation
  • DRANet: Disentangling Representation and Adaptation Networks for Unsupervised Cross-Domain Adaptation
  • Dynamic Domain Adaptation for Efficient Inference
    ⭐code
  • Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation
    🏠project
  • Domain Consensus Clustering for Universal Domain Adaptation
    ⭐code

• Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers
• Convolutional Hough Matching
  😮oral🏠project
• 图像检索
  • Probabilistic Embeddings for Cross-Modal Retrieval
    
  • QAIR: Practical Query-efficient Black-Box Attacks for Image Retrieval
  • More Photos are All You Need: Semi-Supervised Learning for Fine-Grained Sketch Based Image Retrieval
    ⭐code
  • StyleMeUp: Towards Style-Agnostic Sketch-Based Image Retrieval
• 视频检索
  • On Semantic Similarity in Video Retrieval
    ⭐code🏠project📺video

• 图像恢复Image Restoration
  • Multi-Stage Progressive Image Restoration
    ⭐code
    
• 去阴影Shadow Removal
  • Auto-Exposure Fusion for Single-Image Shadow Removal
    ⭐code
    
  • From Shadow Generation to Shadow Removal
    ⭐code
• 去模糊Deblurring
  • DeFMO: Deblurring and Shape Recovery of Fast Moving Objects
    ⭐code📺video
    
  • ARVo: Learning All-Range Volumetric Correspondence for Video Deblurring
• 去反射Reflection Removal
  • Robust Reflection Removal with Reflection-free Flash-only Cues
    ⭐ccode
• 去雾
  • Learning to Restore Hazy Video: A New Real-World Dataset and A New Method
    学习复原有雾视频：一种新的真实数据集及算法
    解读：9
  • Contrastive Learning for Compact Single Image Dehazing
    基于对比学习的紧凑图像去雾方法
    解读：5
• 去噪Denoising
  • Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Images
    解读：CVPR 2021 | Neighbor2Neighbor：仅需噪声图像即可训练任意降噪网络的方法
• 去雨Deraining
  • Semi-Supervised Video Deraining with Dynamic Rain Generator
  • Closing the Loop: Joint Rain Generation and Removal via Disentangled Image Translation
• 曝光校正
  • Learning Multi-Scale Photo Exposure Correction
    ⭐code
• 图像修复Image Inpainting
  • Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAE
    ⭐code
  • TransFill: Reference-guided Image Inpainting by Merging Multiple Color and Spatial Transformations
    🏠project
• 图像编辑
  • DeFLOCNet: Deep Image Editing via Flexible Low-level Controls
    ⭐code
• 图像压缩
  • Attention-guided Image Compression by Deep Reconstruction of Compressive Sensed Saliency Skeleton
  • Slimmable Compressive Autoencoders for Practical Neural Image Compression
    ⭐code
  • Checkerboard Context Model for Efficient Learned Image Compression
  • Learning Scalable ℓ∞-constrained Near-lossless Image Compression via Joint Lossy Image and Residual Compression
    ⭐code

• 人脸识别
  • A 3D GAN for Improved Large-pose Facial Recognition
    
  • When Age-Invariant Face Recognition Meets Face Age Synthesis: A Multi-Task Learning Framework
    ⭐github
    
  • MagFace: A Universal Representation for Face Recognition and Quality Assessment
    😮oral⭐code
    人脸识别+质量，今年的Oral presentation。 代码待整理
  • WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition
    🏠project
  • ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis
    😮oral🏠project📺video
  • Spherical Confidence Learning for Face Recognition
    😮oral
    基于超球流形置信度学习的人脸识别
  • Consistent Instance False Positive Improves Fairness in Face Recognition
    基于实例误报一致性的人脸识别公平性提升方法
    解读：7
  • CRFace: Confidence Ranker for Model-Agnostic Face Detection Refinement
  • Cross-Domain Similarity Learning for Face Recognition in Unseen Domains
• 合成人脸（Deepfake/Face Forgery）检测
  • Multi-attentional Deepfake Detection
    
  • Frequency-aware Discriminative Feature Learning Supervised by Single-Center Loss for Face Forgery Detection
  • MagDR: Mask-guided Detection and Reconstruction for Defending Deepfakes
  • Face Forensics in the Wild
    😮oral⭐code
• 人脸质量评估
  • SDD-FIQA: Unsupervised Face Image Quality Assessment with Similarity Distribution Distance
    基于相似度分布距离的无监督人脸质量评估
    解读：6
• 3D人脸重建
  • Learning to Aggregate and Personalize 3D Face from In-the-Wild Photo Collection
    😮oral
    在开放的人像集合中学习3D人脸的聚合与特异化重建
  • 3DCaricShop: A Dataset and A Baseline Method for Single-view 3D Caricature Face Reconstruction
    ⭐code🏠project
• 人脸表情识别
  • Affective Processes: stochastic modelling of temporal context for emotion and facial expression recognition
    
• 人脸聚类
  • Structure-Aware Face Clustering on a Large-Scale Graph with 10^7 Nodes
    ⭐code🏠project
• 人脸编辑
  • High-Fidelity and Arbitrary Face Editing
• 人脸跟踪
  • High-fidelity Face Tracking for AR/VR via Deep Lighting Adaptation
    🏠project📺video

• AttentiveNAS: Improving Neural Architecture Search via Attentive
  
• HourNAS: Extremely Fast Neural Architecture Search Through an Hourglass Lens
  
• ReNAS: Relativistic Evaluation of Neural Architecture Search
  
• OPANAS: One-Shot Path Aggregation Network Architecture Search for Object
• Towards Improving the Consistency, Efficiency, and Flexibility of Differentiable Neural Architecture Search
  北京大学人工智能研究院机器学习研究中心
• Contrastive Neural Architecture Search with Neural Architecture Comparators
  ⭐code
• Searching by Generating: Flexible and Efficient One-Shot NAS with Architecture Generator
  ⭐code
• Prioritized Architecture Sampling with Monto-Carlo Tree Search
  ⭐code

• Rotation Equivariant Siamese Networks for Tracking
  
• Graph Attention Tracking
  ⭐code

• 多目标跟踪
  • Probabilistic Tracklet Scoring and Inpainting for Multiple Object Tracking
    
  • Track to Detect and Segment: An Online Multi-Object Tracker
    ⭐code🏠project📺video
    TraDeS ：CVPR 2021多目标跟踪算法，改进了目前联合检测与跟踪的在线方法，使用跟踪线索辅助检测，在多个数据集实现了大幅精度提升，作者来自纽约州立大学。代码已开源。
  • Multiple Object Tracking with Correlation Learning
  • Learning a Proposal Classifier for Multiple Object Tracking
    ⭐code
  • Learnable Graph Matching: Incorporating Graph Partitioning with Deep Feature Learning for Multiple Object Tracking
    ⭐code
• 视觉目标跟踪
  • IoU Attack: Towards Temporally Coherent Black-Box Adversarial Attack for Visual Object Tracking
    ⭐code
• 单目标跟踪
  • Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark
    🏠project📺video
  • SiamGAT: Graph Attention Tracking
    ⭐code

• Information-Theoretic Segmentation by Inpainting Error Maximization
  
• Simultaneously Localize, Segment and Rank the Camouflaged Objects
  ⭐code
• Capturing Omni-Range Context for Omnidirectional Segmentation
  ⭐code
• Boundary IoU: Improving Object-Centric Image Segmentation Evaluation
  ⭐code🏠project

• Locate then Segment: A Strong Pipeline for Referring Image Segmentation
• 实例分割
  • [Zero-Shot Instance Segmentation]
    创新奇智首次提出零样本实例分割，助力解决工业场景数据瓶颈难题
  • Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers
    ⭐code
  • Weakly Supervised Instance Segmentation for Videos with Temporal Mask Consistency
• 全景分割
  • 4D Panoptic LiDAR Segmentation
    
  • Cross-View Regularization for Domain Adaptive Panoptic Segmentation
    😮oral
    用于域自适应全景分割的跨视图正则化方法
    
  • Part-aware Panoptic Segmentation
    
  • Toward Joint Thing-and-Stuff Mining for Weakly Supervised Panoptic Segmentation
    联合物体和物质挖掘的弱监督全景分割
    解读：15
  • Panoptic-PolarNet: Proposal-free LiDAR Point Cloud Panoptic Segmentation
    ⭐code
• 语义分割
  • PLOP: Learning without Forgetting for Continual Semantic Segmentation
    ⭐code
  • Towards Semantic Segmentation of Urban-Scale 3D Point Clouds: A Dataset, Benchmarks and Challenges
    🌻dataset📺video
    
  • Multi-Source Domain Adaptation with Collaborative Learning for Semantic Segmentation
  • Semi-supervised Domain Adaptation based on Dual-level Domain Mixing for Semantic Segmentation
  • Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsing
    😮oral⭐code
  • Learning Statistical Texture for Semantic Segmentation
  • MetaCorrection: Domain-aware Meta Loss Correction for Unsupervised Domain Adaptation in Semantic Segmentation
    ⭐code
    语义分割中的无监督域适应的域感知元损失校正
  • Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representations
  • Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusion
    ⭐code
  • [Rethinking BiSeNet For Real-time Semantic Segmentation]
    ⭐code
  • BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentation
    ⭐code
  • Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentation
    ⭐code
  • Cross-Dataset Collaborative Learning for Semantic Segmentation
  • Coarse-to-Fine Domain Adaptive Semantic Segmentation with Photometric Alignment and Category-Center Regularization
  • Non-Salient Region Object Mining for Weakly Supervised Semantic Segmentation
    ⭐code
  • Source-Free Domain Adaptation for Semantic Segmentation
  • PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clustering
• 场景理解/场景解析
  • Exploring Data Efficient 3D Scene Understanding with Contrastive Scene Contexts
    😮oral🏠project📺video
  • Monte Carlo Scene Search for 3D Scene Understanding
  • Bidirectional Projection Network for Cross Dimension Scene Understanding
    😮oral⭐code
  • RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whitening
    😮oral⭐code
  • 场景图合成/分析
    • SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequences
      🏠project
    • Probabilistic Modeling of Semantic Ambiguity for Scene Graph Generation
      场景图生成---场景解析
    • Exploiting Edge-Oriented Reasoning for 3D Point-based Scene Graph Analysis
      🏠project
      利用面向边缘的推理进行基于3D点的场景图分析---场景理解
    • Fully Convolutional Scene Graph Generation
      😮oral
• 抠图
  • Real-Time High Resolution Background Matting
    😮oral⭐code🏠project📺video
    最新开源抠图技术，实时快速高分辨率，4k(30fps)、现代GPU（60fps）
    解读：单块GPU实现4K分辨率每秒30帧，华盛顿大学实时视频抠图再升级，毛发细节到位
    最新开源抠图技术，实时快速高分辨率，4k(30fps)、现代GPU（60fps）
• 视频动作分割
  • Global2Local: Efficient Structure Search for Video Action Segmentation
    从全局到局部：面向视频动作分割的高效网络结构搜索
    解读：19
• 时序动作分割
  • Temporal Action Segmentation from Timestamp Supervision
    ⭐code
  • Temporally-Weighted Hierarchical Clustering for Unsupervised Action Segmentation
    ⭐code
• 雷达分割
  • Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation
    😮oral⭐code
    在 SemanticKITTI 榜单排名第一（until CVPR DDL），在 nuScenes 中获得 SOTA，并对其他基于激光雷达的任务保持了良好的泛化能力，包括激光雷达全景分割和激光雷达三维检测，其中就基于此工作，在 SemanticKITTI 全景分割榜单也排名第一。
• 视频目标分割
  • Modular Interactive Video Object Segmentation:Interaction-to-Mask, Propagation and Difference-Aware Fusion
    😮oral⭐code🏠project📺video
  • Learning to Recommend Frame for Interactive Video Object Segmentation in the Wild
    ⭐code
  • Efficient Regional Memory Network for Video Object Segmentation
    ⭐code🏠project
• 视频实例分割
  • SG-Net: Spatial Granularity Network for One-Stage Video Instance Segmentation
    ⭐code📺video
    文章介绍一个简单有效的单阶段框架：SG-Net，与传统的两阶段框架相比，可以有效提高掩码质量和推理速度。
• 小样本分割
  • Self-Guided and Cross-Guided Learning for Few-Shot Segmentation
    ⭐code

• Multiple Instance Active Learning for Object Detection
  ⭐code
  
• Positive-Unlabeled Data Purification in the Wild for Object Detection
  
• Depth from Camera Motion and Object Detection
  ⭐github📺video
  通过使用“普通手机摄像头运动+目标检测的包围框”数据，设计RNN网络实现了达到最先进精度的目标深度估计。
  
• Towards Open World Object Detection
  😮oral⭐code
  
• General Instance Distillation for Object Detection
  近年来，知识蒸馏已被证明是模型压缩的有效解决方案。可以使轻量级的学生模型获得从繁琐的教师模型中提取的知识，但以往的检测蒸馏方法对于不同的检测框架的泛化能力较弱，而且严重依赖ground truth（GT），忽略了实例之间有价值的关系信息。为此，作者在本文中提出新的基于判别性实例的检测任务蒸馏方法，不考虑 GT 区分的正负，命名为通用实例蒸馏（GID）。该方法包含一个通用实例选择模块(GISM)，可以充分利用基于特征、基于关系和基于响应的知识进行蒸馏。实验验证，学生模型在各种检测框架中可以实现显著的 AP 改进，甚至优于教师模型。具体来说，RetinaNet 与 ResNet-50 在 COCO 数据集上用 GID 实现了39.1% 的 mAP，比基线 36.2% 超出了 2.9%，甚至优于基于 ResNet-101 的教师模型 38.1% 的 AP。
  
• Distilling Object Detectors via Decoupled Features
  
• MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detection
  
• Informative and Consistent Correspondence Mining for Cross-Domain Weakly Supervised Object Detection
  😮oral

• You Only Look One-level Feature
  ⭐code
  论文公开
  开源 YOLOF，无需 FPN，速度比 YOLOv4 快13%
  解读：目标检测算法YOLOF：You Only Look One-level Feature

• Sparse R-CNN: End-to-End Object Detection with Learnable Proposals
  ⭐code
• End-to-End Object Detection with Fully Convolutional Network
  ⭐code
  解读：丢弃Transformer，FCN也可以实现E2E检测
• Robust and Accurate Object Detection via Adversarial Learning

• I^3Net: Implicit Instance-Invariant Network for Adapting One-Stage Object Detectors
• Distilling Object Detectors via Decoupled Features
  ⭐code
• OTA: Optimal Transport Assignment for Object Detection
  ⭐code
• Scale-aware Automatic Augmentation for Object Detection
  ⭐code
• A Closer Look at Fourier Spectrum Discrepancies for CNN-generated Images Detection
  😮oral🏠project
• 小样本目标检测
  • Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detection
    首个研究少样本检测任务的语义关系推理，并证明它可提升强基线的潜。
    
  • Dense Relation Distillation with Context-aware Aggregation for Few-Shot Object Detection
    ⭐code
    北京大学人工智能研究院机器学习研究中心
    
  • FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding
    ⭐code
• 多目标检测
  • There is More than Meets the Eye: Self-Supervised Multi-Object Detection and Tracking with Sound by Distilling Multimodal Knowledge
    🏠project
    
• 3D目标检测
  • Categorical Depth Distribution Network for Monocular 3D Object Detection
    😮oral
    
  • 3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detection
    ⭐code🏠project📺video
    更多：CVPR 2021|利用IoU预测进行半监督式3D目标检测
  • ST3D: Self-training for Unsupervised Domain Adaptation on 3D ObjectDetection
    ⭐code
  • Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection
    ⭐code
  • MonoRUn: Monocular 3D Object Detection by Self-Supervised Reconstruction and Uncertainty Propagation
    ⭐code
  • M3DSSD: Monocular 3D Single Stage Object Detector
    ⭐code
  • GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection
    ⭐code📺video
    论文公开
  • LiDAR R-CNN: An Efficient and Universal 3D Object Detector
    ⭐code
  • Exploring intermediate representation for monocular vehicle pose estimation
    ⭐code
  • Delving into Localization Errors for Monocular 3D Object Detection
    ⭐code
• 旋转目标检测
  • Dense Label Encoding for Boundary Discontinuity Free Rotation Detection
    ⭐code
• 目标定位
  • Unveiling the Potential of Structure-Preserving for Weakly Supervised Object Localization
    基于结构信息保持的弱监督目标定位
    解读：13
• 密集目标检测
  • Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection
    ⭐code
    解读：目标检测无痛涨点之 Generalized Focal Loss V2
• RGB-D 显著目标检测
  • Deep RGB-D Saliency Detection with Depth-Sensitive Attention and Automatic Multi-Modal Fusion
    😮oral
• 半监督目标检测
• Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detection
• 弱监督目标检测
  • DAP: Detection-Aware Pre-training with Weak Supervision

• KeepAugment: A Simple Information-Preserving Data Augmentation
  

• Multiresolution Knowledge Distillation for Anomaly Detection
  

• 弱监督
  • Weakly Supervised Learning of Rigid 3D Scene Flow
    ⭐code🏠project
    
  • Relation-aware Instance Refinement for Weakly Supervised Visual Grounding
    ⭐code
• 半监督
  • Adaptive Consistency Regularization for Semi-Supervised Transfer Learning
    ⭐code
    
  • SSLayout360: Semi-Supervised Indoor Layout Estimation from 360∘ Panorama
• 自监督
  • Self-supervised Geometric Perception
    😮oral⭐code
    作者称 SGP 是第一个在几何感知中进行特征学习的通用框架，不需要任何来自 ground-truth 几何标签的监督。SGP以EM方式运行，它迭代执行几何模型的鲁棒估计以生成伪标签，并在噪声伪标签的监督下进行特征学习。将 SGP 应用于相机姿势估计和点云配准，并证明在大规模真实数据集中，SGP 的性能等同于甚至优于监督的权威。
  • Vectorization and Rasterization: Self-Supervised Learning for Sketch and Handwriting
    ⭐code

• Style-based Point Generator with Adversarial Rendering for Point Cloud Completion
  
• MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization
  😮oral⭐code
• TPCN: Temporal Point Cloud Networks for Motion Forecasting
  用于运动预测的时空点云网络
  
• How Privacy-Preserving are Line Clouds? Recovering Scene Details from 3D Lines
  ⭐code
• PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds
• Point2Skeleton: Learning Skeletal Representations from Point Clouds
  😮oral⭐code🏠project

• 点云配准
  • PREDATOR: Registration of 3D Point Clouds with Low Overlap
    😮oral⭐code🏠project
    
  • SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration
    ⭐code
  • Robust Point Cloud Registration Framework Based on Deep Graph Matching
    ⭐code
  • PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency
    ⭐code
  • ReAgent: Point Cloud Registration using Imitation and Reinforcement Learning
    ⭐code
• 点云补全
  • Cycle4Completion: Unpaired Point Cloud Completion using Cycle Transformation with Missing Region Coding
  • Denoise and Contrast for Category Agnostic Shape Completion
    ⭐code
• 点云关键点检测
  • Skeleton Merger: an Unsupervised Aligned Keypoint Detector
    ⭐code
• 3D点云
  • Diffusion Probabilistic Models for 3D Point Cloud Generation
    😮oral⭐code
    
  • PointGuard: Provably Robust 3D Point Cloud Classification
  • Equivariant Point Network for 3D Point Cloud Analysis
    ⭐code

• Sequential Graph Convolutional Network for Active Learning
  
• Quantifying Explainers of Graph Neural Networks in Computational Pathology
  
• Binary Graph Neural Networks

• Inverting the Inherence of Convolution for Visual Recognition
  
• Representative Batch Normalization with Feature Calibration
  
• UC2: Universal Cross-lingual Cross-modal Vision-and-Language Pretraining
  
• Reconsidering Representation Alignment for Multi-view Clustering
  
• Self-supervised Simultaneous Multi-Step Prediction of Road Dynamics and Cost Map
  
• Instance Localization for Self-supervised Detection Pretraining
  ⭐code
  
• Model-Contrastive Federated Learning
  提出模型对比学习来解决联合学习中的非IID数据问题
  
• Neural Geometric Level of Detail:Real-time Rendering with Implicit 3D Surfaces
  😮Oral⭐code🏠project
  
• Data-Free Model Extraction
  ⭐code
  
• Single-Stage Instance Shadow Detection with Bidirectional Relation Learning
  😮oral
  ⭐code
• Continual Adaptation of Visual Representations via Domain Randomization and Meta-learning
  😮oral
• PatchmatchNet: Learned Multi-View Patchmatch Stereo
  😮oral⭐code
• [Online Bag-of-Visual-Words Generation for Unsupervised Representation Learning]
• [Semantic Palette: Guiding Scene Generation with Class Proportions]
• Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensors
  😮oral
• POSEFusion:Pose-guided Selective Fusion for Single-view Human Volumetric Capture
  😮oral
• Multi-Objective Interpolation Training for Robustness to Label Noise
  ⭐code
• Right for the Right Concept: Revising Neuro-Symbolic Concepts by Interacting with their Explanations
  ⭐code
• Simpler Certified Radius Maximization by Propagating Covariances
  😮oral📺video
• Nutrition5k: Towards Automatic Nutritional Understanding of Generic Food
• Discovering Hidden Physics Behind Transport Dynamics
  😮oral
• Soft-IntroVAE: Analyzing and Improving the Introspective Variational Autoencoder
  😮oral⭐code🏠project
• Deep Gradient Projection Networks for Pan-sharpening
  ⭐code
• Consensus Maximisation Using Influences of Monotone Boolean Functions
  😮oral

• Forecasting Irreversible Disease via Progression Learning
• Causal Hidden Markov Model for Time Series Disease Forecasting
• Towards Unified Surgical Skill Assessment

• Knowledge Evolution in Neural Networks
  😮oral⭐code

• RSTNet: Captioning with Adaptive Attention on Visual and Non-Visual Words
  RSTNet: 基于可区分视觉词和非视觉词的自适应注意力机制的图像描述生成模型
  解读：14
• Removing the Background by Adding the Background: Towards a Background Robust Self-supervised Video Representation Learning
  通过添加背景来去除背景影响：背景鲁棒的自监督视频表征学习
  解读：11
• Representative Batch Normalization with Feature Calibration
  😮oral
  作者主页
  基于特征校准的表征批规范化方法解读：4
• Learning Compositional Representation for 4D Captures with Neural ODE
• Involution: Inverting the Inherence of Convolution for Visual Recognition
  ⭐code
  解读：CVPR'21 | involution：超越convolution和self-attention的神经网络新算子
• Spatially Consistent Representation Learning
• Limitations of Post-Hoc Feature Alignment for Robustness
• AutoDO: Robust AutoAugment for Biased Data with Label Noise via Scalable Probabilistic Implicit Differentiation
  ⭐code
• Abstract Spatial-Temporal Reasoning via Probabilistic Abduction and Execution
  ⭐code
• CFNet: Cascade and Fused Cost Volume for Robust Stereo Matching
  ⭐code
• Augmentation Strategies for Learning with Noisy Labels
  ⭐code
• Abstract Spatial-Temporal Reasoning via Probabilistic Abduction and Execution
  ⭐code
• CFNet: Cascade and Fused Cost Volume for Robust Stereo Matching
  ⭐code
• Augmentation Strategies for Learning with Noisy Labels
  ⭐code
• PGT: A Progressive Method for Training Models on Long Videos
  😮oral⭐code
• Generic Perceptual Loss for Modeling Structured Output Dependencies
• Masksembles for Uncertainty Estimation
  ⭐code🏠project
• Student-Teacher Learning from Clean Inputs to Noisy Inputs
• Scene-Intuitive Agent for Remote Embodied Visual Grounding
• Meta-Mining Discriminative Samples for Kinship Verification
  
• Learning Probabilistic Ordinal Embeddings for Uncertainty-Aware Regression
  ⭐code📺video
  论文公开
• Diverse Branch Block: Building a Convolution as an Inception-like Unit
  ⭐code
• OTCE: A Transferability Metric for Cross-Domain Cross-Task Representations
• Disentangled Cycle Consistency for Highly-realistic Virtual Try-On
  ⭐code
• Stylized Neural Painting
  ⭐code🏠project📺video
  风格化的神经绘画,Stylized Neural Painting,提出 image-to-painting 翻译方法，生成生动逼真、风格可控的绘画艺术作品
• Confluent Vessel Trees with Accurate Bifurcations
  ⭐code
• Repopulating Street Scenes
• Extreme Rotation Estimation using Dense Correlation Volumes
• Can We Characterize Tasks Without Labels or Features?
• Embracing Uncertainty: Decoupling and De-bias for Robust Temporal Grounding
• Online Learning of a Probabilistic and Adaptive Scene Representation
• Generative Modelling of BRDF Textures from Flash Images
  ⭐code🏠project

• Transport Challenge with ThreeDWorld
  📺video⚠️6月1截止
  • 论文：The ThreeDWorld Transport Challenge: A Visually Guided Task-and-Motion Planning Benchmark for Physically Realistic Embodied AI

• Visual Perception for Navigation in Human Environments
  第二届人类环境导航视觉感知征稿 ⚠️4月15截止

• UG 2 + Challenge
  旨在通过应用图像恢复和增强算法提高分析性能，推动对 "difficult"图像的分析。参与者任务是开发新的算法，以改进对在问题条件下拍摄的图像分析。
  👑10K美元奖金
  

  • 低能见度环境下的目标检测
    • 雾霾条件下的(半)监督目标检测
    • (半)低光条件下的人脸检测
  • 黑暗视频中的动作识别
    • 黑暗中进行完全监督动作识别
    • 黑暗中进行半监督动作识别

• Continual Learning in Computer Vision 征稿中
  旨在聚集学术界和工业界的研究人员和工程师，讨论持续学习的最新进展。
  

  • Best paper award: 500 USD + 500 USD worth of Huawei cloud credits (HUAWEI)
  • Overall Challenge winner: 1,000 USD + 500 USD worth of Huawei cloud credits (HUAWEI)
  • Supervised-Learning track winner: 500 USD (HUAWEI)
  • Reinforcement-Learning track winner: 500 USD (ServiceNow)

• 第四届UG2研讨会和竞赛：弥合计算成像与视觉识别之间的鸿沟

• 10万美元奖金！CVPR 2021 重磅赛事，安全AI挑战者计划

  • CVPR 2021大赛， 安全AI 之防御模型的「白盒对抗攻击」解析
  • 还在刷榜ImageNet？找出模型的脆弱之处更有价值！

• Responsible Computer Vision
  ⚠️3月25日截止
  本次研讨会将广泛讨论计算机视觉背景下负责任的人工智能的三个主要方面：公平性；可解释性和透明度；以及隐私。

• Holistic Video Understanding
  目的是建立一个整合所有语义概念联合识别的视频基准，因为每个任务的单一类标签往往不足以描述视频的整体内容。

• ThreeDWorld Transport Challenge
  ⚠️6月1截止
  📺video

• FGVC 8
  第八届细粒度视觉分类研讨会（FGVC8）将通过细粒度视觉理解的视角，探讨细粒度学习、自监督学习、半监督学习、matching(匹配)、localization(定位)、域适应、迁移学习、小样本学习、机器教学、多模态学习（如音频和视频）、众包和分类学预测等相关话题。
  ⚠️论文截稿日期为4月2日
  征稿主题包含以下几个方面

  • Fine-grained categorization细粒度分类
    • Novel datasets and data collection strategies for fine-grained categorization用于细粒度分类的新型数据集和数据收集策略
    • Appropriate error metrics for fine-grained categorization细粒度分类的适当误差指标
    • Low/few shot learning少/小样本学习
    • Self-supervised learning自监督学习
    • Semi-supervised learning半监督学习
    • Transfer-learning from known to novel subcategories
    • Attribute and part based approaches
    • Taxonomic predictions
    • Addressing long-tailed distributions
  • Human-in-the-loop
    • Fine-grained categorization with humans in the loop
    • Embedding human experts’ knowledge into computational models
    • Machine teaching
    • Interpretable fine-grained models
  • Multi-modal learning
    • Using audio and video data
    • Using geographical priors
    • Learning shape
  • Fine-grained applications
    • Product recognition
    • Animal biometrics and camera traps
    • Museum collections
    • Agricultural
    • Medical
    • Fashion
  • 相关挑战赛如下（部分已在Kaggle网站开始）
    • GeoLifeCLEF2021
      利用观测结果与航空图像和环境特征配对，预测物种的存在
    • Semi-iNat2021
      由iNaturalist的数据组成的半监督细粒度图像分类
    • iNatChallenge2021
      对1万类动植物进行图像分类挑战赛
    • iMet2021
      对艺术品进行细粒度属性分类
    • iMat-Fashion2021未开始
      服装实例分割和细粒度属性分类
    • Hotel-ID 2021
      从图像中识别酒店房间
    • HerbariumChallenge2021
      从数据集中识别标本，该数据集包含来自美洲、大洋洲和太平洋地区的近66,000种 vascular plant species（维管束植物）的 2.5M 图像
    • iWildCam2021
      对图像序列中每个物种的动物数量计数
    • PlantPathologyChallenge2021未开始
      对病害植物的图像进行分类