CVPR 2020 共收录 1470篇文章,根据当前的公布情况,人工智能学社整理了以下约100篇,分享给读者。
代码开源情况:详见每篇注释,当前共15篇开源。(持续更新中,可关注了解)。
算法主要领域:图像与视频处理,图像分类&检测&分割、视觉目标跟踪、视频内容分析、人体姿态估计、模型加速、网络架构搜索(NAS)、生成对抗(GAN)、光学字符识别(OCR)、人脸识别、三维重建等方向。 目录如下:
总目录
图像处理
-
Deep Image Harmonization via Domain Verification
论文:https://arxiv.org/abs/1911.13239
代码:https://github.com/bcmi/Image_Harmonization_Datasets -
Learning to Shade Hand-drawn Sketches
论文:https://arxiv.org/abs/2002.11812 -
Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Data
论文:https://arxiv.org/abs/2002.11297 -
Single Image Reflection Removal through Cascaded Refinement
论文:https://arxiv.org/abs/1911.06634 -
RoutedFusion: Learning Real-time Depth Map Fusion
论文:https://arxiv.org/pdf/2001.04388.pdf
图像分类
-
Towards Robust Image Classification Using Sequential Attention Models
论文:https://arxiv.org/abs/1912.02184 -
Self-training with Noisy Student improves ImageNet classification
论文:https://arxiv.org/abs/1911.04252 -
Image Matching across Wide Baselines: From Paper to Practice
论文:https://arxiv.org/abs/2003.01587 -
Improved Few-Shot Visual Classification
论文:https://arxiv.org/pdf/1912.03432.pdf -
A General and Adaptive Robust Loss Function
论文:https://arxiv.org/abs/1701.03077 -
Making Better Mistakes: Leveraging Class Hierarchies with Deep Networks
论文:https://arxiv.org/abs/1912.09393
目标检测和分割
-
Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector
论文:https://arxiv.org/abs/1908.01998 -
Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection
论文:https://arxiv.org/abs/1912.02424
代码:https://github.com/sfzhang15/ATSS -
Semi-Supervised Semantic Image Segmentation with Self-correcting Networks
论文:https://arxiv.org/abs/1811.07073 -
Deep Snake for Real-Time Instance Segmentation
论文:https://arxiv.org/abs/2001.01629 -
SketchGCN: Semantic Sketch Segmentation with Graph Convolutional Networks
论文:https://arxiv.org/abs/2003.00678 -
xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation
论文:https://arxiv.org/abs/1911.12676 -
CenterMask : Real-Time Anchor-Free Instance Segmentation
论文:https://arxiv.org/abs/1911.06667
代码:https://github.com/youngwanLEE/CenterMask -
PolarMask: Single Shot Instance Segmentation with Polar Representation
论文:https://arxiv.org/abs/1909.13226
代码:https://github.com/xieenze/PolarMask -
BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation
论文:https://arxiv.org/abs/2001.00309
视觉目标跟踪
- ROAM: Recurrently Optimizing Tracking Model
论文:https://arxiv.org/abs/1907.12006
视频内容分析(理解)
-
Hierarchical Conditional Relation Networks for Video Question Answering
论文:https://arxiv.org/abs/2002.10698 -
Rethinking Zero-shot Video Classification: End-to-end Training for Realistic Applications
论文:https://arxiv.org/abs/2003.01455
代码:https://github.com/bbrattoli/ZeroShotVideoClassification -
Action Modifiers:Learning from Adverbs in Instructional Video
论文:https://arxiv.org/abs/1912.06617 -
Fine-grained Video-Text Retrieval with Hierarchical Graph Reasoning
论文:https://arxiv.org/abs/2003.00392 -
Blurry Video Frame Interpolation
论文:https://arxiv.org/abs/2002.12259 -
Object Relational Graph with Teacher-Recommended Learning for Video Captioning
论文:https://arxiv.org/abs/2002.11566 -
Say As You Wish: Fine-grained Control of Image Caption Generation with Abstract Scene Graphs
论文:https://arxiv.org/abs/2003.00387 -
Learning Representations by Predicting Bags of Visual Words
论文:https://arxiv.org/abs/2002.12247 -
Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video Super-Resolution
论文:https://arxiv.org/abs/2002.11616
人体关键点检测和姿态估计
-
Distribution-Aware Coordinate Representation for Human Pose Estimation
论文:https://arxiv.org/abs/1910.06278
代码:https://github.com/ilovepose/DarkPose -
VIBE: Video Inference for Human Body Pose and Shape Estimation
论文:https://arxiv.org/abs/1912.05656
代码:https://github.com/mkocabas/VIBE -
The Devil is in the Details: Delving into Unbiased Data Processing for Human Pose Estimation
论文:https://arxiv.org/abs/1911.07524 -
Optimal least-squares solution to the hand-eye calibration problem
论文:https://arxiv.org/abs/2002.10838 -
Distribution Aware Coordinate Representation for Human Pose Estimation
论文:https://arxiv.org/abs/1910.06278 -
D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry
论文:https://arxiv.org/abs/2003.01060 -
Multi-Modal Domain Adaptation for Fine-Grained Action Recognition
论文:https://arxiv.org/abs/2001.09691 -
PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimation
论文:https://arxiv.org/abs/1911.04231 -
4D Association Graph for Realtime Multi-person Motion Capture Using Multiple Video Cameras
论文:https://arxiv.org/abs/2002.12625
模型轻量化和加速
- GPU-Accelerated Mobile Multi-view Style Transfer
论文:https://arxiv.org/abs/2003.00706
神经网络架构设计和搜索NAS
-
GhostNet: More Features from Cheap Operations
论文:https://arxiv.org/abs/1911.11907
代码:https://github.com/iamhankai/ghostnet -
CARS: Contunuous Evolution for Efficient Neural Architecture Search
论文:https://arxiv.org/pdf/1909.04977.pdf
代码:https://github.com/huawei-noah/CARS -
Visual Commonsense R-CNN
论文:https://arxiv.org/abs/2002.12204 -
Watch your Up-Convolution: CNN Based Generative Deep Neural Networks are Failing to Reproduce Spectral
论文:https://arxiv.org/abs/2003.01826 -
AdderNet: Do We Really Need Multiplications in Deep Learning?
论文:https://arxiv.org/pdf/1912.13200 -
Filter Grafting for Deep Neural Networks
论文:https://arxiv.org/pdf/2001.05868.pdf
生成对抗GAN
-
Your Local GAN: Designing Two Dimensional Local Attention Mechanisms for Generative Models
论文:https://arxiv.org/abs/1911.12287
代码:https://github.com/giannisdaras/ylg -
MSG-GAN: Multi-Scale Gradient GAN for Stable Image Synthesis
论文:https://arxiv.org/abs/1903.06048 -
Robust Design of Deep Neural Networks against Adversarial Attacks based on Lyapunov Theory
论文:https://arxiv.org/abs/1911.04636
三维点云&3D重建
-
PointAugment: an Auto-Augmentation Framework for Point Cloud Classification
论文:https://arxiv.org/abs/2002.10876
代码:https://github.com/liruihui/PointAugment/ -
PF-Net: Point Fractal Network for 3D Point Cloud Completion
论文:https://arxiv.org/abs/2003.00410 -
Learning multiview 3D point cloud registration
论文:https://arxiv.org/abs/2001.05119 -
Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image
论文:https://arxiv.org/abs/2002.12212 -
In Perfect Shape: Certifiably Optimal 3D Shape Reconstruction from 2D Landmarks
论文:https://arxiv.org/pdf/1911.11924.pdf -
RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds
论文:https://arxiv.org/abs/1911.11236 -
C-Flow: Conditional Generative Flow Models for Images and 3D Point Clouds
论文:https://arxiv.org/abs/1912.07009 -
Representations, Metrics and Statistics For Shape Analysis of Elastic Graphs
论文:https://arxiv.org/abs/2003.00287 -
Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion
论文:https://arxiv.org/abs/2003.01456
光学字符识别OCR
- ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network
论文:https://arxiv.org/abs/2002.10200
代码:https://github.com/Yuliang-Liu/bezier_curve_text_spotting,https://github.com/aim-uofa/adet
迁移学习
-
Meta-Transfer Learning for Zero-Shot Super-Resolution
论文:https://arxiv.org/abs/2002.12213 -
Transferring Dense Pose to Proximal Animal Classes
论文:https://arxiv.org/abs/2003.00080
弱监督 & 无监督学习
-
Unsupervised Reinforcement Learning of Transferable Meta-Skills for Embodied Navigation
论文:https://arxiv.org/abs/1911.07450 -
Disentangling Physical Dynamics from Unknown Factors for Unsupervised Video Prediction
论文:https://arxiv.org/abs/2003.01460 -
Rethinking the Route Towards Weakly Supervised Object Localization
论文:https://arxiv.org/abs/2002.11359 -
NestedVAE: Isolating Common Factors via Weak Supervision
论文:https://arxiv.org/abs/2002.11576
人脸识别
-
Towards Universal Representation Learning for Deep Face Recognition
论文:https://arxiv.org/abs/2002.11841 -
Suppressing Uncertainties for Large-Scale Facial Expression Recognition
论文:https://arxiv.org/abs/2002.10392
代码:https://github.com/kaiwang960112/Self-Cure-Network -
Face X-ray for More General Face Forgery Detection
论文:https://arxiv.org/pdf/1912.13458.pdf
图神经网络GNN
-
Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction
论文:https://arxiv.org/abs/2002.11927 -
Bundle Adjustment on a Graph Processor
论文:https://arxiv.org/abs/2003.03134
代码:https://github.com/joeaortiz/gbp
视觉 & 语言 混合任务研究
-
Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training
论文:https://arxiv.org/abs/2002.10638
代码:https://github.com/weituo12321/PREVALENT -
12-in-1: Multi-Task Vision and Language Representation Learning
论文:https://arxiv.org/abs/1912.02315 -
Hierarchical Conditional Relation Networks for Video Question Answering
论文:https://arxiv.org/abs/2002.10698
其他问题研究
-
What it Thinks is Important is Important: Robustness Transfers through Input Gradients
论文:https://arxiv.org/abs/1912.05699 -
Holistically-Attracted Wireframe Parsing
论文:https://arxiv.org/abs/2003.01663 -
Attentive Context Normalization for Robust Permutation-Equivariant Learning
论文:https://arxiv.org/abs/1907.02545 -
ClusterFit: Improving Generalization of Visual Representations
论文:https://arxiv.org/abs/1912.03330 -
Learning in the Frequency Domain
论文:https://arxiv.org/abs/2002.12416 -
A Characteristic Function Approach to Deep Implicit Generative Modeling
论文:https://arxiv.org/abs/1909.07425 -
Auto-Encoding Twin-Bottleneck Hashing
论文:https://arxiv.org/abs/2002.11930
论文打包下载地址
链接:https://pan.baidu.com/s/1lo3smbFWiBSNnut9JssYaQ
提取码:公众号内回复 cvpr2020
论文包中有彩蛋一枚~~~~