CVPR2021论⽂合集下载论⽂分类汇总论⽂合集下载
CVPR2021 论⽂&&代码&&Post&&PPT (持续更新中，敬请关注)
分类⽬录：
1. 检测
图像⽬标检测(Image Object Detection)
视频⽬标检测(Video Object Detection)
三维⽬标检测(3D Object Detection)
动作检测(Activity Detection)
异常检测(Anomally Detetion)
2. 图像分割(Image Segmentation)
全景分割(Panoptic Segmentation)
语义分割(Semantic Segmentation)
实例分割(Instance Segmentation)
抠图(Matting)
3. 图像处理(Image Processing)
图像复原(Image Restoration)/超分辨率(Super Resolution)
图像阴影去除(Image Shadow Removal)
图像去噪/去模糊/去⾬去雾(Image Denoising)
图像编辑(Image Edit)
图像翻译(Image Translation))
4. ⼈脸(Face)
5. ⽬标跟踪(Object Tracking)
6. 重识别(Re-Identification)
7. 医学影像(Medical Imaging)
8. GAN/⽣成式/对抗式(GAN/Generative/Adversarial)
9. 估计(Estimation)
解析域名⼈体姿态估计(Human Po Estimation)
⼿势估计(Gesture Estimation)
光流/位姿/运动估计(Flow/Po/Motion Estimation)
深度估计(Depth Estimation)
10. 三维视觉(3D Vision)
三维点云(3D Point Cloud)
三维重建(3D Reconstruction)
11. 神经⽹络架构(Neural Network Structure)
Transformer
图神经⽹络(GNN)
12. 神经⽹络架构搜索(NAS)
13. 数据处理(Data Processing)
数据增⼴(Data Augmentation)
归⼀化/正则化(Batch Normalization)
图像聚类(Image Clustering)
14. 模型压缩(Model Compression)
知识蒸馏(Knowledge Distillation)
15. 模型评估(Model Evaluation)
16. 数据集(Databa)
17. 主动学习(Active Learning)
17. 主动学习(Active Learning)
18. ⼩样本学习/零样本(Few-shot Learning)
19. 持续学习(Continual Learning/Life-long Learning)
20. 视觉推理(Visual Reasoning)
21. 迁移学习/domain/⾃适应
22. 对⽐学习(Contrastive Learning)
23. 图像/视频检索(Image Retrieval)
暂⽆分类
检测
昆明市住房公积金
图像⽬标检测(Image Object Detection)
[7] Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detection(⼩样本⽬标检测的语义关系推理)
paper
[6] General Instance Distillation for Object Detection(通⽤实例蒸馏技术在⽬标检测中的应⽤)
paper
[5] Instance Localization for Self-supervid Detection Pretraining(⾃监督检测预训练的实例定位)
paper｜code
[4] Multiple Instance Active Learning for Object Detection（⽤于对象检测的多实例主动学习）
paper|code
[3] Towards Open World Object Detection(开放世界中的⽬标检测)
paper|code
[2] Positive-Unlabeled Data Purification in the Wild for Object Detection(野外检测对象的阳性⽆标签数据提纯)
[1] UP-DETR: Unsupervid Pre-training for Object Detection with Transformers
paper
解读：⽆监督预训练检测器
视频⽬标检测(Video Object Detection)
[3] Depth from Camera Motion and Object Detection(相机运动和物体检测的深度)
paper
[2] There is More than Meets the Eye: Self-Supervid Multi-Object Detection and Tracking with Sound by Distilling Multimodal Knowledge(多模态知识提取的⾃监督多⽬标检测与有声跟踪)
paper|video|project
[1] Dogfight: Detecting Drones from Drone Videos（从⽆⼈机视频中检测⽆⼈机）
三维⽬标检测(3D object detection)
[2] 3DIoUMatch: Leveraging IoU Prediction for Semi-Supervid 3D Object Detection(利⽤IoU预测进⾏半监督3D对象检测) paper|code|project|video
[1] Categorical Depth Distribution Network for Monocular 3D Object Detection(⽤于单⽬三维⽬标检测的分类深度分布⽹络) paper
动作检测(Activity Detection)
[1] Coar-Fine Networks for Temporal Activity Detection in Videos
paper
异常检测(Anomally Detetion)
[1] Multiresolution Knowledge Distillation for Anomaly Detection(⽤于异常检测的多分辨率知识蒸馏)
paper
图像分割(Image Segmentation)
[2] Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?
paper|code
[1] PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation(语义流经点以进⾏航空图像分割)
全景分割(Panoptic Segmentation)
[2] Cross-View Regularization for Domain Adaptive Panoptic Segmentation(⽤于域⾃适应全景分割的跨视图正则化)
paper
微营销课程[1] 4D Panoptic LiDAR Segmentation（4D全景LiDAR分割）
paper
语义分割(Semantic Segmentation)
[2] Towards Semantic Segmentation of Urban-Scale 3D Point Clouds: A Datat, Benchmarks and C
hallenges(⾛向城市规模3D点云的语义分割：数据集，基准和挑战)
预备党员需要交党费吗
paper|code
[1] PLOP: Learning without Forgetting for Continual Semantic Segmentation（PLOP：学习⽽不会忘记连续的语义分割）
paper
实例分割(Instance Segmentation)
[1] End-to-End Video Instance Segmentation with Transformers(使⽤Transformer的端到端视频实例分割)
paper
抠图(Matting)
[1] Real-Time High Resolution Background Matting
paper|code|project|video
9. 估计(Estimation)
⼈体姿态估计(Human Po Estimation)
[2] CanonPo: Self-supervid Monocular 3D Human Po Estimation in the Wild（野外⾃监督的单眼3D⼈类姿态估计）
[1] PCLs: Geometry-aware Neural Reconstruction of 3D Po with Perspective Crop Layers（具有透视作物层的3D姿势的⼏何感知神经重建）
paper
⼿势估计(Gesture Estimation)
[1] Camera-Space Hand Mesh Recovery via Semantic Aggregation and Adaptive 2D-1D Registration(基于语义聚合和⾃适应
2D-1D配准的相机空间⼿部⽹格恢复)
paper|code
光流/位姿/运动估计(Flow/Po/Motion Estimation)
[3] GDR-Net: Geometry-Guided Direct Regression Network for Monocular 6D Object Po Estimation(⽤于单眼6D对象姿态估计的⼏何引导直接回归⽹络)
paper|code
[2] Robust Neural Routing Through Space Partitions for Camera Relocalization in Dynamic Indoor Environments(在动态室内环境中，通过空间划分的鲁棒神经路由可实现摄像机的重新定位)
paper|project
[1] MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization(通过3D扫描同步进⾏多主体分割和运动估计)
金针菇瘦肉汤
paper|code
深度估计(Depth Estimation)
图像处理(Image Processing)
图像复原(Image Restoration)/超分辨率(Super Resolution)
[3] Multi-Stage Progressive Image Restoration(多阶段渐进式图像复原)
paper|code
[2] Data-Free Knowledge Distillation For Image Super-Resolution(DAFL算法的SR版本)
[1] AdderSR: Towards Energy Efficient Image Super-Resolution(将加法⽹路应⽤到图像超分辨率中)
今年清明是几号paper|code
解读：华为开源加法神经⽹络
图像阴影去除(Image Shadow Removal)
[1] Auto-Exposure Fusion for Single-Image Shadow Removal(⽤于单幅图像阴影去除的⾃动曝光融合)
paper|code
图像去噪/去模糊/去⾬去雾(Image Denoising)
[1] DeFMO: Deblurring and Shape Recovery of Fast Moving Objects(快速移动物体的去模糊和形状恢复)
paper|code|video
图像编辑(Image Edit)
[2] Anycost GANs for Interactive Image Synthesis and Editing(⽤于交互式图像合成和编辑的AnyCost Gans)
paper|code
[1] Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing（利⽤GAN中潜在的空间维度进⾏实时图像编辑）
图像翻译（Image Translation）
[2] Image-to-image Translation via Hierarchical Style Dintanglement
paper|code
[1] Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation(样式编码：⽤于图像到图像翻译的StyleGAN编码器) paper|code|project
⼈脸(Face)
[5] Cross Modal Focal Loss for RGBD Face Anti-Spoofing(Cross Modal Focal Loss for RGBD Face Anti-Spoofing) paper
[4] When Age-Invariant Face Recognition Meets Face Age Synthesis: A Multi-Task Learning Framework(当年龄不变的⼈脸识别遇到⼈脸年龄合成时：⼀个多任务学习框架)
paper|code
[3] Multi-attentional Deepfake Detection(多注意的深伪检测)
paper
[2] Image-to-image Translation via Hierarchical Style Dintanglement
paper|code
[1] A 3D GAN for Improved Large-po Facial Recognition(⽤于改善⼤姿势⾯部识别的3D GAN)
paper
⽬标跟踪(Object Tracking)
[4] HPS: localizing and tracking people in large 3D scenes from wearable nsors(通过可穿戴式传感器对⼤型3D场景中的⼈进⾏定位和跟踪)
[3] Track to Detect and Segment: An Online Multi-Object Tracker(跟踪检测和分段：在线多对象跟踪器)
project|video
[2] Probabilistic Tracklet Scoring and Inpainting for Multiple Object Tracking(多⽬标跟踪的概率⼩波计分和修复)
paper
束手就擒[1] Rotation Equivariant Siame Networks for Tracking（旋转等距连体⽹络进⾏跟踪）全国导游证
paper
重识别
[1] Meta Batch-Instance Normalization for Generalizable Person Re-Identification(通⽤批处理⼈员重新标识的元批实例规范化) paper
医学影像(Medical Imaging)
[5] DeepTag: An Unsupervid Deep Learning Method for Motion Tracking on Cardiac Tagging Magnetic Resonance
Images(⼀种⼼脏标记磁共振图像运动跟踪的⽆监督深度学习⽅法)
paper
[4] Multi-institutional Collaborations for Improving Deep Learning-bad Magnetic Resonance Image Reconstruction Using Federated Learning(多机构协作改进基于深度学习的联合学习磁共振图像重建)
paper|code
[3] 3D Graph Anatomy Geometry-Integrated Network for Pancreatic Mass Segmentation, Diagnosis, and Quantitative Patient Management(⽤于胰腺肿块分割，诊断和定量患者管理的3D图形解剖学⼏何集成⽹络)
[2] Deep Lesion Tracker: Monitoring Lesions in 4D Longitudinal Imaging Studies(深部病变追踪器：在4D纵向成像研究中监控病变)
paper
[1] Automatic Vertebra Localization and Identification in CT by Spine Rectification and Anatomically-constrained Optimization(通过脊柱矫正和解剖学约束优化在CT中⾃动进⾏椎⾻定位和识别)
paper
神经⽹络架构搜索(NAS)
[3] AttentiveNAS: Improving Neural Architecture Search via Attentive(通过注意⼒改善神经架构搜索)
paper
[2] ReNAS: Relativistic Evaluation of Neural Architecture Search(NAS predictor当中ranking loss的重要性)
paper
[1] HourNAS: Extremely Fast Neural Architecture Search Through an Hourglass Lens（降低NAS的成本）
paper
GAN/⽣成式/对抗式(GAN/Generative/Adversarial)
[6] Anycost GANs for Interactive Image Synthesis and Editing(⽤于交互式图像合成和编辑的AnyCost Gans)
paper|code
[5] Efficient Conditional GAN Transfer with Knowledge Propagation across Class(⾼效的有条件GAN转移以及跨课程的知识传播)
paper|code
[4] Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing（利⽤GAN中潜在的空间维度进⾏实时图像编辑）
[3] Hijack-GAN: Unintended-U of Pretrained, Black-Box GANs(Hijack-GAN：意外使⽤经过预训练的⿊匣⼦GAN)
paper
[2] Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation(样式编码：⽤于图像到图像翻译的StyleGAN编码器) paper|code|project
[1] A 3D GAN for Improved Large-po Facial Recognition(⽤于改善⼤姿势⾯部识别的3D GAN)
paper
三维视觉(3D Vision)
[2] A Deep Emulator for Secondary Motion of 3D Characters(三维⾓⾊⼆次运动的深度仿真器) paper
[1] 3D CNNs with Adaptive Temporal Feature Resolutions(具有⾃适应时间特征分辨率的3D CNN)
paper
三维点云(3D Point Cloud)
[8] TPCN: Temporal Point Cloud Networks for Motion Forecasting(⾯向运动预测的时态点云⽹络) paper|code
