My Computer Vision Paper Library (2018)

澹台正真
2023-12-01

2018.

欢迎访问我的个人博客: http://zengzeyu.com

papersource -
O-CNN : Octree-based Convolutional Neural Networks for 3D Shape AnalysisPDF/video/code
OctNet: Learning Deep 3D Representations at High ResolutionsPDF/video/code
Parallel Separable 3D Convolution for Video and Volumetric Data UnderstandingPDF/video/code
PIXOR : Real-time 3D Object Detection from Point CloudsPDF/video/code
PointCNNPDF/video/code
PointNet : Deep Learning on Point Sets for 3D Classification and SegmentationPDF/video/code
PointNet ++ : Deep Hierarchical Feature Learning on Point Sets in a Metric SpacePDF/video/code
Receptive Field Block Net for Accurate and Fast Object DetectionPDF/video/code
Deep Residual Learning for Image Recognition(ResNet)PDF/video/code
Rethinking Atrous Convolution for Semantic Image SegmentationPDF/video/code
Rich feature hierarchies for accurate object detection and semantic segmentationPDF/video/code
Sparse 3D convolutional neural networksPDF/video/code
SPLATNet : Sparse Lattice Networks for Point Cloud ProcessingPDF/video/code
SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point CloudPDF/video/code
The Devil of Face Recognition is in the NoisePDF/video/code
Understanding Convolution for Semantic SegmentationPDF/video/code
V-Net : Fully Convolutional Neural Networks for Volumetric Medical Image SegmentationPDF/video/code
VoxelNet: End-to-End Learning for Point Cloud Based 3D Object DetectionPDF/video/code
Xception: Deep Learning with Depthwise Separable ConvolutionsPDF/video/code
PointFusion : Deep Sensor Fusion for 3D Bounding Box EstimationPDF/video/code
Efficient Convolutions for Real-Time Semantic Segmentation of 3D Point CloudsPDF/video/code
Exploring Spatial Context for 3D Semantic Segmentation of Point CloudsPDF/video/code
Factorized Convolutional Neural NetworksPDF/video/code
Fast Bilateral Solver for Semantic Video SegmentationPDF/video/code
Fast LIDAR-based Road Detection Using Fully Convolutional Neural NetworksPDF/video/code
FishNet : A Versatile Backbone for Image , Region , and Pixel Level PredictionPDF/video/code
Flattened Convolutional Neural Networks for Feedforward AccelerationPDF/video/code
Focal Loss for Dense Object DetectionPDF/video/code
Frustum PointNets for 3D Object Detection from RGB-D DataPDF/video/code
Full-Resolution Residual Networks for Semantic Segmentation in Street ScenesPDF/video/code
Fully Convolutional Networks for Semantic SegmentationPDF/video/code
Fully-Convolutional Point Networks for Large-Scale Point CloudsPDF/video/code
Fast R-CNNPDF/video/code
Going Deeper with Convolutions(GoogLeNet)PDF/video/code
Ground Estimation and Point Cloud Segmentation using SpatioTemporal Conditional Random FieldPDF/video/code
HDNET : Exploiting HD Maps for 3D Object DetectionPDF/video/code
Inception-V4, Inception-ResNet ad the Impact of Residual Connections on LearningPDF/video/code
Instance-aware Semantic Segmentation via Multi-task Network CascadesPDF/video/code
Joint 3D Proposal Generation and Object Detection from View Aggregation(AVOD)PDF/video/code
Large-scale Point Cloud Semantic Segmentation with Superpoint GraphsPDF/video/code
Learning 3D Shape Completion from Laser Scan Data with Weak SupervisionPDF/video/code
Learning a Real-Time 3D Point Cloud Obstacle Discriminator via BootstrappingPDF/video/code
Learning Spatio-Temporal Representation with Pseudo-3D Residual NetworksPDF/video/code
Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and SemanticsPDF/video/code
Multi-View 3D Object Detection Network for Autonomous DrivingPDF/video/code
Not All Pixels Are Equal : Difficulty-Aware Semantic Segmentation via Deep Layer CascadePDF/video/code
3D Fully Convolutional Network for Vehicle Detection in Point CloudPDF/video/code
3D Semantic Segmentation with Submanifold Sparse Convolutional NetworksPDF/video/code
3D U-Net: Learning Dense Volumetric Segmentation from Sparse AnnotationPDF/video/code
Deconvolutional Networks for Point-Cloud Vehicle Detection and Tracking in Driving ScenariosPDF/video/code
Accurate, Large Minibatch SGD: Training ImageNet in 1 HourPDF/video/code
Acquisition of Localization Confidence for Accurate Object Detection(IouNet)PDF/video/code
A Hybrid Conditional Random Field for Estimating the Underlying Ground Surface from Airborne LiDAR DataPDF/video/code
Batch Normalization : Accelerating Deep Network Training by Reducing Internal Covariate ShiftPDF/video/code
BiSeNet : Bilateral Segmentation Network for Real-time Semantic SegmentationPDF/video/code
CNN for Very Fast Ground Segmentation in Velodyne LiDAR DataPDF/video/code
Complex-YOLO: An Euler-Region-Proposal for Real-time 3D Object Detection on Point CloudsPDF/video/code
CornerNet: Detecting Objects as Paired KeypointsPDF/video/code
Conditional Random Fields Meet Deep Neural Networks for Semantic SegmentationPDF/video/code
Decoupled NetworksPDF/video/code
Deep Feature Pyramid Reconfiguration for Object DetectionPDF/video/code
DropBlock : A regularization method for convolutional networksPDF/video/code
RoarNet: A Robust 3D Object Detection based on RegiOn Approximation RefinementPDF/video/code
Dropout: A simple way to prevent neural networks from overfittingPDF/video/code
SECOND: Sparsely Embedded Convolutional DetectionPDF/video/code
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksPDF/video/code
Bag of Tricks for Image Classification with Convolutional Neural NetworksPDF/video/code
Deformable ConvNets v2: More Deformable, Better ResultsPDF/video/code
Non-local Neural NetworksPDF/video/code
PointPillars: Fast Encoders for Object Detection from Point CloudsPDF/video/code
Box2Pix : Single-Shot Instance Segmentation by Assigning Pixels to Object BoxesPDF/video/code
IPOD: Intensive Point-based Object Detector for Point CloudPDF/video/code
Densely connected convolutional networksPDF/video/code
SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point CloudPDF/video/code
SSD: Single Shot MultiBox DetectorPDF/video/code
Residual Networks Behave Like Ensembles of Relatively Shallow NetworksPDF/video/code
Single-Shot Refinement Neural Network for Object Detection (RefineDet)PDF/video/code
MIXED PRECISION TRAININGPDF/video/code
Gradient Harmonized Single-stage DetectorPDF/video/code
Gather-Excite: Exploiting Feature Context in Convolutional Neural NetworksPDF/video/code
GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask NetworksPDF/video/code
 类似资料: