CVPR2019论文汇总

CVPR2019论文汇总

论文题目与链接

Finding Task-Relevant Features for Few-Shot Learning by Category Traversal
Edge-Labeling Graph Neural Network for Few-Shot Learning
Generating Classification Weights With GNN Denoising Autoencoders for Few-Shot Learning
Kervolutional Neural Networks
Why ReLU Networks Yield High-Confidence Predictions Far Away From the Training Data and How to Mitigate the Problem
On the Structural Sensitivity of Deep Convolutional Networks to the Directions of Fourier Basis Functions
Neural Rejuvenation: Improving Deep Network Training by Enhancing Computational Resource Utilization
Hardness-Aware Deep Metric Learning
Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation
Learning Loss for Active Learning
Striking the Right Balance With Uncertainty
AutoAugment: Learning Augmentation Strategies From Data
SDRSAC: Semidefinite-Based Randomized Approach for Robust Point Cloud Registration Without Correspondences
BAD SLAM: Bundle Adjusted Direct RGB-D SLAM
Revealing Scenes by Inverting Structure From Motion Reconstructions
Strand-Accurate Multi-View Hair Capture
DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation
Pushing the Boundaries of View Extrapolation With Multiplane Images
GA-Net: Guided Aggregation Net for End-To-End Stereo Matching
Real-Time Self-Adaptive Deep Stereo
LAF-Net: Locally Adaptive Fusion Networks for Stereo Confidence Estimation
NM-Net: Mining Reliable Neighbors for Robust Feature Correspondences
Coordinate-Free Carlsson-Weinshall Duality and Relative Multi-View Geometry
Deep Reinforcement Learning of Volume-Guided Progressive View Inpainting for 3D Point Scene Completion From a Single Depth Image
Video Action Transformer Network
Timeception for Complex Action Recognition
STEP: Spatio-Temporal Progressive Learning for Video Action Detection
Relational Action Forecasting
Long-Term Feature Banks for Detailed Video Understanding
Which Way Are You Going? Imitative Decision Learning for Path Forecasting in Dynamic Scenes
What and How Well You Performed? A Multitask Learning Approach to Action Quality Assessment
MHP-VOS: Multiple Hypotheses Propagation for Video Object Segmentation
2.5D Visual Sound
Language-Driven Temporal Activity Localization: A Semantic Matching Reinforcement Learning Model
Gaussian Temporal Awareness Networks for Action Localization
Efficient Video Classification Using Fewer Frames
Parsing R-CNN for Instance-Level Human Analysis
Large Scale Incremental Learning
TopNet: Structural Point Cloud Decoder
Perceive Where to Focus: Learning Visibility-Aware Part-Level Features for Partial Person Re-Identification
Meta-Transfer Learning for Few-Shot Learning
Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentation
Deep RNN Framework for Visual Sequential Applications
Graph-Based Global Reasoning Networks
SSN: Learning Sparse Switchable Normalization via SparsestMax
Spherical Fractal Convolutional Neural Networks for Point Cloud Recognition
Learning to Generate Synthetic Data via Compositing
Divide and Conquer the Embedding Space for Metric Learning
Latent Space Autoregression for Novelty Detection
Attending to Discriminative Certainty for Domain Adaptation
Feature Denoising for Improving Adversarial Robustness
Selective Kernel Networks
On Implicit Filter Level Sparsity in Convolutional Neural Networks
FlowNet3D: Learning Scene Flow in 3D Point Clouds
Scene Memory Transformer for Embodied Agents in Long-Horizon Tasks
Co-Occurrent Features in Semantic Segmentation
Bag of Tricks for Image Classification with Convolutional Neural Networks
Learning Channel-Wise Interactions for Binary Convolutional Neural Networks
Knowledge Adaptation for Efficient Semantic Segmentation
Parametric Noise Injection: Trainable Randomness to Improve Deep Neural Network Robustness Against Adversarial Attack
Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-Identification
Dissecting Person Re-Identification From the Viewpoint of Viewpoint
Learning to Reduce Dual-Level Discrepancy for Infrared-Visible Person Re-Identification
Progressive Feature Alignment for Unsupervised Domain Adaptation
Feature-Level Frankenstein: Eliminating Variations for Discriminative Recognition
Learning a Deep ConvNet for Multi-Label Classification With Partial Labels
Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression
Densely Semantically Aligned Person Re-Identification
Generalising Fine-Grained Sketch-Based Image Retrieval
Adapting Object Detectors via Selective Cross-Domain Alignment
Cyclic Guidance for Weakly Supervised Joint Detection and Segmentation
Thinking Outside the Pool: Active Training Image Creation for Relative Attributes
Generalizable Person Re-Identification by Domain-Invariant Mapping Network
Visual Attention Consistency Under Image Transforms for Multi-Label Image Classification
Re-Ranking via Metric Fusion for Object Retrieval and Person Re-Identification
Unsupervised Open Domain Recognition by Semantic Discrepancy Minimization
Weakly Supervised Person Re-Identification
PointRCNN: 3D Object Proposal Generation and Detection From Point Cloud
Automatic Adaptation of Object Detectors to New Domains Using Self-Training
Deep Sketch-Shape Hashing With Segmented 3D Stochastic Viewing
Generative Dual Adversarial Network for Generalized Zero-Shot Learning
Query-Guided End-To-End Person Search
Libra R-CNN: Towards Balanced Learning for Object Detection
Learning a Unified Classifier Incrementally via Rebalancing
Feature Selective Anchor-Free Module for Single-Shot Object Detection
Bottom-Up Object Detection by Grouping Extreme and Center Points
Feature Distillation: DNN-Oriented JPEG Compression Against Adversarial Examples
SCOPS: Self-Supervised Co-Part Segmentation
Unsupervised Moving Object Detection via Contextual Information Separation
Pose2Seg: Detection Free Human Instance Segmentation
DrivingStereo: A Large-Scale Dataset for Stereo Matching in Autonomous Driving Scenarios
PartNet: A Large-Scale Benchmark for Fine-Grained and Hierarchical Part-Level 3D Object Understanding
A Dataset and Benchmark for Large-Scale Multi-Modal Face Anti-Spoofing
Unsupervised Learning of Consensus Maximization for 3D Vision Problems
VizWiz-Priv: A Dataset for Recognizing the Presence and Purpose of Private Visual Information in Images Taken by Blind People
Structural Relational Reasoning of Point Clouds
MVF-Net: Multi-View 3D Face Morphable Model Regression
Photometric Mesh Optimization for Video-Aligned 3D Object Reconstruction
Guided Stereo Matching
Unsupervised Event-Based Learning of Optical Flow, Depth, and Egomotion
Modeling Local Geometric Structure of 3D Point Clouds Using Geo-CNN
3D Point Capsule Networks
GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving
Single-Image Piece-Wise Planar 3D Reconstruction via Associative Embedding
3DN: 3D Deformation Network
HorizonNet: Learning Room Layout With 1D Representation and Pano Stretch Data Augmentation
Deep Fitting Degree Scoring Network for Monocular 3D Object Detection
Pushing the Envelope for RGB-Based Dense 3D Hand Pose Estimation via Neural Rendering
Self-Supervised Learning of 3D Human Pose Using Multi-View Geometry
FSA-Net: Learning Fine-Grained Structure Aggregation for Head Pose Estimation From a Single Image
Dense 3D Face Decoding Over 2500FPS: Joint Texture & Shape Convolutional Mesh Decoders
Does Learning Specific Features for Related Parts Help Human Pose Estimation?
Linkage Based Face Clustering via Graph Convolution Network
Towards High-Fidelity Nonlinear 3D Face Morphable Model
RegularFace: Deep Face Recognition via Exclusive Regularization
BridgeNet: A Continuity-Aware Probabilistic Network for Age Estimation
GANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face Reconstruction
Improving the Performance of Unimodal Dynamic Hand-Gesture Recognition With Multimodal Training
Learning to Reconstruct People in Clothing From a Single RGB Camera
Distilled Person Re-Identification: Towards a More Scalable System
A Perceptual Prediction Framework for Self Supervised Event Segmentation
COIN: A Large-Scale Dataset for Comprehensive Instructional Video Analysis
Recurrent Attentive Zooming for Joint Crowd Counting and Precise Localization
An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition
Graph Convolutional Label Noise Cleaner: Train a Plug-And-Play Action Classifier for Anomaly Detection
MAN: Moment Alignment Network for Natural Language Moment Retrieval via Iterative Graph Adjustment
Less Is More: Learning Highlight Detection From Video Duration
DMC-Net: Generating Discriminative Motion Cues for Fast Compressed Video Action Recognition
AdaFrame: Adaptive Frame Selection for Fast Video Recognition
Spatio-Temporal Video Re-Localization by Warp LSTM
Completeness Modeling and Context Separation for Weakly Supervised Temporal Action Localization
Unsupervised Deep Tracking
Tracking by Animation: Unsupervised Learning of Multi-Object Attentive Trackers
Fast Online Object Tracking and Segmentation: A Unifying Approach
Object Tracking by Reconstruction With View-Specific Discriminative Correlation Filters
SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraints
Leveraging Shape Completion for 3D Siamese Tracking
Target-Aware Deep Tracking
Spatiotemporal CNN for Video Object Segmentation
Towards Rich Feature Discovery With Class Activation Maps Augmentation for Person Re-Identification
Wide-Context Semantic Image Extrapolation
End-To-End Time-Lapse Video Synthesis From a Single Outdoor Image
GIF2Video: Color Dequantization and Temporal Interpolation of GIF Images
Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis
Pluralistic Image Completion
Salient Object Detection With Pyramid Attention and Salient Edges
Latent Filter Scaling for Multimodal Unsupervised Image-To-Image Translation
Attention-Aware Multi-Stroke Style Transfer
Feedback Adversarial Learning: Spatial Feedback for Improving Generative Adversarial Networks
Learning Pyramid-Context Encoder Network for High-Quality Image Inpainting
Example-Guided Style-Consistent Image Synthesis From Semantic Labeling
MirrorGAN: Learning Text-To-Image Generation by Redescription
Light Field Messaging With Deep Photographic Steganography
Im2Pencil: Controllable Pencil Illustration From Photographs
When Color Constancy Goes Wrong: Correcting Improperly White-Balanced Images
Beyond Volumetric Albedo – A Surface Optimization Framework for Non-Line-Of-Sight Imaging
Reflection Removal Using a Dual-Pixel Sensor
Practical Coding Function Design for Time-Of-Flight Imaging
Meta-SR: A Magnification-Arbitrary Network for Super-Resolution
Multispectral and Hyperspectral Image Fusion by MS/HS Fusion Net
Learning Attraction Field Representation for Robust Line Segment Detection
Blind Super-Resolution With Iterative Kernel Correction
Video Magnification in the Wild Using Fractional Anisotropy in Temporal Distribution
Attentive Feedback Network for Boundary-Aware Salient Object Detection
Heavy Rain Image Restoration: Integrating Physics Model and Conditional Adversarial Learning
Learning to Calibrate Straight Lines for Fisheye Image Rectification
Camera Lens Super-Resolution
Frame-Consistent Recurrent Video Deraining With Dual-Level Flow
Deep Plug-And-Play Super-Resolution for Arbitrary Blur Kernels
Sea-Thru: A Method for Removing Water From Underwater Images
Deep Network Interpolation for Continuous Imagery Effect Transition
Spatially Variant Linear Representation Models for Joint Filtering
Toward Convolutional Blind Denoising of Real Photographs
Towards Real Scene Super-Resolution With Raw Images
ODE-Inspired Network Design for Single Image Super-Resolution
Blind Image Deblurring With Local Maximum Gradient Prior
Attention-Guided Network for Ghost-Free High Dynamic Range Imaging
Searching for a Robust Neural Architecture in Four GPU Hours
Hierarchy Denoising Recursive Autoencoders for 3D Scene Layout Prediction
Adaptively Connected Neural Networks
CrDoCo: Pixel-Level Domain Transfer With Cross-Domain Consistency
Temporal Cycle-Consistency Learning
Predicting Future Frames Using Retrospective Cycle GAN
Density Map Regression Guided Detection Network for RGB-D Crowd Counting and Localization
TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learning
Learning Semantic Segmentation From Synthetic Data: A Geometrically Guided Input-Output Adaptation Approach
Attentive Single-Tasking of Multiple Tasks
Deep Metric Learning to Rank
End-To-End Multi-Task Learning With Attention
Self-Supervised Learning via Conditional Motion Propagation
Bridging Stereo Matching and Optical Flow via Spatiotemporal Correspondence
All About Structure: Adapting Structural Information Across Domains for Boosting Semantic Segmentation
Iterative Reorganization With Weak Spatial Constraints: Solving Arbitrary Jigsaw Puzzles for Unsupervised Representation Learning
Revisiting Self-Supervised Visual Representation Learning
It’s Not About the Journey; It’s About the Destination: Following Soft Paths Under Question-Guidance