Skip to content

Latest commit

 

History

History
217 lines (109 loc) · 13.8 KB

File metadata and controls

217 lines (109 loc) · 13.8 KB

Convolutional feature masking for joint object and stuff segmentation

BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation

GENERATIVE MODELING OF CONVOLUTIONAL NEURAL NETWORKS

Fully Convolutional Instance-aware Semantic Segmentation

Unsupervised Learning of Dictionaries of Hierarchical Compositional Models

Deformable Convolutional Networks

Deep Feature Flow for Video Recognition

Flow-Guided Feature Aggregation for Video Object Detection

Mining sub-categories for object detection

Instance-aware Semantic Segmentation via Multi-task Network Cascades

Multifeature-Based High-Resolution Palmprint Recognition

Robust and Efficient Ridge-Based Palmprint Matching

Cosegmentation and Cosketch by Unsupervised Learning

ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation

Deep Residual Learning for Image Recognition

Guided Image Filtering

Single Image Haze Removal Using Dark Channel Prior

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Delving Deep into Rectifiers:Surpassing Human-Level Performance on ImageNet Classification

Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition

Learning a Deep Convolutional Network for Image Super-Resolution

Identity Mappings in Deep Residual Networks

K-means Hashing: an Affinity-Preserving Quantization Method for Learning Binary Compact Codes

Optimized Product Quantization for Approximate Nearest Neighbor Search

A Global Sampling Method for Alpha Matting

Constant Time Weighted Median Filtering for Stereo Matching and Beyond

Fast Matting Using Large Kernel Matting Laplacian Matrices

Statistics of Patch Offsets for Image Completion

R-FCN: Object Detection via Region-based Fully Convolutional Networks

Convolutional Neural Networks at Constrained Time Cost

Computing Nearest-Neighbor Fields via Propagation-Assisted KD-Trees

Is Faster R-CNN Doing Well for Pedestrian Detection?

Efficient and Accurate Approximations of Nonlinear Convolutional Networks

Accelerating Very Deep Convolutional Networks for Classification and Detection

Object Detection Networks on Convolutional Feature Maps

Instance-sensitive Fully Convolutional Networks

Joint Inverted Indexing

Sparse Projections for High-Dimensional Binary Codes

Image Completion Approaches Using the Statistics of Similar Patches

Graph Cuts for Supervised Binary Coding

Feature Pyramid Networks for Object Detection

Fast Guided Filter

Rectangling Panoramic Images via Warping

Mask R-CNN

Product Sparse Coding

Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour

Content-Aware Rotation

A Geodesic-Preserving Method for Image Warping

Detecting and Recognizing Human-Object Interaction

Object Detection with Discriminatively Trained Part Based Model

Caffe: Convolutional Architecture for Fast Feature Embedding

Rich feature hierarchies for accurate object detection and semantic segmentation

Microsoft COCO: Common Objects in Context

Fast R-CNN

Cascade Object Detection with Deformable Part Models

You Only Look Once:Unified, Real-Time Object Detection

Learning Rich Features from RGB-D Images for Object Detection and Segmentation

Hypercolumns for Object Segmentation and Fine-grained Localization

Simultaneous Detection and Segmentation

Efficient Regression of General-Activity Human Poses from Depth Images

Efficient Human Pose Estimation from Single Depth Images

Part-based R-CNNs for Fine-grained Category Detection

Region-Based Convolutional Networks for Accurate Object Detection and Segmentation

Object Detection with Grammar Models

Deformable Part Models are Convolutional Neural Networks

Analyzing the Performance of Multilayer Neural Networks for Object Recognition

LSDA: Large Scale Detection through Adaptation

Unsupervised Deep Embedding for Clustering Analysis

REDUCING OVERFITTING IN DEEP NETWORKS BY DECORRELATING REPRESENTATIONS

Aggregated Residual Transformations for Deep Neural Networks

Actions and Attributes from Wholes and Parts

R-CNNs for Pose Estimation and Action Detection

Understanding Objects in Detail with Fine-grained Attributes

DenseNet: Implementing Efficient ConvNet Descriptor Pyramids Technical Report

Using k-poselets for detecting people and localizing their keypoints

Indoor Scene Understanding with RGB-D Images: Bottom-up Segmentation, Object Detection and Semantic Segmentation

Exploring Nearest Neighbor Approaches for Image Captioning

Aligning 3D Models to RGB-D Images of Cluttered Scenes

Training Region-based Object Detectors with Online Hard Example Mining

Contextual Action Recognition with R*CNN

Sparselet Models for Efficient Multiclass Object Detection

On learning to localize objects with minimal supervision

Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks

Discriminatively Trained Mixtures of Deformable Part Models

Discriminative Latent Variable Models for Object Detection

The three R’s of computer vision: Recognition, reconstruction and reorganization

Visibility Constraints on Features of 3D Objects

Predicting joint positions

Inferring and Executing Programs for Visual Reasoning

Accurate, Large Minibatch SGD:Training ImageNet in 1 Hour

Simulating Chinese Brush Painting:The Parametric Hairy Brush

Human body pose estimation

Generalized Sparselet Models for Real-Time Multiclass Object Recognition

Inferring 3D Object Pose in RGB-D Images

Learning Features by Watching Objects Move

Deep3D: Fully Automatic 2D-to-3D Video Conversion with Deep Convolutional Neural Networks

Seeing through the Human Reporting Bias: Visual Classifiers from Noisy Human-Centric Labels

Low-shot Visual Recognition by Shrinking and Hallucinating Features

CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning

Training deformable part models with decorrelated features

Object Instance Segmentation and Fine-Grained Localization Using Hypercolumns

Object Detection with Heuristic Coarse-to-Fine Search

LSVM - Mixtures of Deformable Part Models

YOLO9000: Better, Faster, Stronger

Real-Time Grasp Detection Using Convolutional Neural Networks

XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks