CVPR2020-Code

CVPR 2020 论文开源项目合集，同时欢迎各位大佬提交issue，分享CVPR 2020开源项目

图像分类

Spatially Attentive Output Layer for Image Classification

目标检测

Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection

BiDet: An Efficient Binarized Object Detector

3D目标检测

Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud

目标跟踪

MAST: A Memory-Augmented Self-supervised Tracker

语义分割

Cars Can't Fly up in the Sky: Improving Urban-Scene Segmentation via Height-driven Attention Networks

实例分割

PolarMask: Single Shot Instance Segmentation with Polar Representation

CenterMask : Real-Time Anchor-Free Instance Segmentation

Deep Snake for Real-Time Instance Segmentation

视频目标分割

State-Aware Tracker for Real-Time Video Object Segmentation

Learning Fast and Robust Target Models for Video Object Segmentation

NAS

Rethinking Performance Estimation in Neural Architecture Search

CARS: Continuous Evolution for Efficient Neural Architecture Search

GAN

Watch your Up-Convolution: CNN Based Generative Deep Neural Networks are Failing to Reproduce Spectral Distributions

Re-ID

Weakly supervised discriminative feature learning with state information for person identification

3D点云

点云卷积

FPConv: Learning Local Flattening for Point Convolution

3D点云配准

D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features

人脸检测

活体检测

Searching Central Difference Convolutional Networks for Face Anti-Spoofing

人脸表情识别

Suppressing Uncertainties for Large-Scale Facial Expression Recognition

人体姿态估计

2D人体姿态估计

The Devil is in the Details: Delving into Unbiased Data Processing for Human Pose Estimation

Distribution-Aware Coordinate Representation for Human Pose Estimation

3D人体姿态估计

Compressed Volumetric Heatmaps for Multi-Person 3D Pose Estimation

VIBE: Video Inference for Human Body Pose and Shape Estimation

Back to the Future: Joint Aware Temporal Deep Learning 3D Human Pose Estimation

Cross-View Tracking for Multi-Human 3D Pose Estimation at over 100 FPS

点云

点云分类

PointAugment: an Auto-Augmentation Framework for Point Cloud Classification

场景文本检测

ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network

场景文本识别

ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network

超分辨率

视频超分辨率

Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video Super-Resolution

模型剪枝

HRank: Filter Pruning using High-Rank Feature Map

行为识别

人群计数

深度估计

单目深度估计

Domain Decluttering: Simplifying Images to Mitigate Synthetic-Real Domain Shift and Improve Depth Estimation

去模糊

视频去模糊

Cascaded Deep Video Deblurring Using Temporal Sharpness Prior

视觉问答

视觉问答

VC R-CNN：Visual Commonsense R-CNN

视觉语言导航

Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training

视频压缩

Learning for Video Compression with Hierarchical Quality and Recurrent Enhancement

行人轨迹预测

Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction

数据集

IntrA: 3D Intracranial Aneurysm Dataset for Deep Learning

Cross-View Tracking for Multi-Human 3D Pose Estimation at over 100 FPS

其他

GhostNet: More Features from Cheap Operations

AdderNet: Do We Really Need Multiplications in Deep Learning?

Deep Image Harmonization via Domain Verification

Blurry Video Frame Interpolation

Extremely Dense Point Correspondences using a Learned Feature Descriptor

Filter Grafting for Deep Neural Networks

Action Segmentation with Joint Self-Supervised Temporal Domain Adaptation

Detecting Attended Visual Targets in Video

Deep Image Spatial Transformation for Person Image Generation

Rethinking Zero-shot Video Classification: End-to-end Training for Realistic Applications