【CVPR2019】完整论文列表二

CVPR 2019 Paper list No.1001-1294

?CVPR2019 完整列表一

---

论文题目与链接
Semantic Component Decomposition for Face Attribute Manipulation
R3 Adversarial Network for Cross Model Face Recognition
Disentangling Latent Hands for Image Synthesis and Pose Estimation
Generating Multiple Hypotheses for 3D Human Pose Estimation With Mixture Density Network
CrossInfoNet: Multi-Task Information Sharing Based Hand Pose Estimation
P2SGrad: Refined Gradients for Optimizing Deep Face Models
Action Recognition From Single Timestamp Supervision in Untrimmed Videos
Time-Conditioned Action Anticipation in One Shot
Dance With Flow: Two-In-One Stream Action Detection
Representation Flow for Action Recognition
LSTA: Long Short-Term Attention for Egocentric Action Recognition
Learning Actor Relation Graphs for Group Activity Recognition
A Structured Model for Action Detection
Out-Of-Distribution Detection for Generalized Zero-Shot Action Recognition
Object Discovery in Videos as Foreground Motion Clustering
Towards Natural and Accurate Future Motion Prediction of Humans and Animals
Automatic Face Aging in Videos via Deep Reinforcement Learning
Multi-Adversarial Discriminative Deep Domain Generalization for Face Presentation Attack Detection
A Content Transformation Block for Image Style Transfer
BeautyGlow: On-Demand Makeup Transfer Framework With Reversible Generative Network
Style Transfer by Relaxed Optimal Transport and Self-Similarity
Inserting Videos Into Videos
Learning Image and Video Compression Through Spatial-Temporal Energy Compaction
Event-Based High Dynamic Range Image and Very High Frame Rate Video Generation Using Conditional Generative Adversarial Networks
Enhancing TripleGAN for Semi-Supervised Conditional Instance Synthesis and Classification
Capture, Learning, and Synthesis of 3D Speaking Styles
Nesti-Net: Normal Estimation for Unstructured 3D Point Clouds Using Convolutional Neural Networks
Ray-Space Projection Model for Light Field Camera
Deep Geometric Prior for Surface Reconstruction
Analysis of Feature Visibility in Non-Line-Of-Sight Measurements
Hyperspectral Imaging With Random Printed Mask
All-Weather Deep Outdoor Lighting Estimation
A Variational EM Framework With Adaptive Edge Selection for Blind Motion Deblurring
Viewport Proposal CNN for 360deg Video Quality Assessment
Beyond Gradient Descent for Regularized Segmentation Losses
MAGSAC: Marginalizing Sample Consensus
Understanding and Visualizing Deep Visual Saliency Models
Divergence Prior and Vessel-Tree Reconstruction
Unsupervised Domain-Specific Deblurring via Disentangled Representations
Douglas-Rachford Networks: Learning Both the Image Prior and Data Fidelity Terms for Blind Image Deconvolution
Speed Invariant Time Surface for Learning to Detect Corner Points With Event-Based Cameras
Training Deep Learning Based Image Denoisers From Undersampled Measurements Without Ground Truth and Without Image Prior
A Variational Pan-Sharpening With Local Gradient Constraints
F-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning
Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation
Graph Attention Convolution for Point Cloud Semantic Segmentation
Normalized Diversification
Learning to Localize Through Compressed Binary Maps
A Parametric Top-View Representation of Complex Road Scenes
Self-Supervised Spatiotemporal Learning via Video Clip Order Prediction
Superquadrics Revisited: Learning 3D Shape Parsing Beyond Cuboids
Unsupervised Disentangling of Appearance and Geometry by Deformable Generator Network
Self-Supervised Representation Learning by Rotation Feature Decoupling
Weakly Supervised Deep Image Hashing Through Tag Embeddings
Improved Road Connectivity by Joint Learning of Orientation and Segmentation
Deep Supervised Cross-Modal Retrieval
A Theoretically Sound Upper Bound on the Triplet Loss for Improving the Efficiency of Deep Distance Metric Learning
Data Representation and Learning With Graph Diffusion-Embedding Networks
Video Relationship Reasoning Using Gated Spatio-Temporal Energy Graph
Image-Question-Answer Synergistic Network for Visual Dialog
Not All Frames Are Equal: Weakly-Supervised Video Grounding With Contextual Similarity and Visual Clustering Losses
Inverse Cooking: Recipe Generation From Food Images
Adversarial Semantic Alignment for Improved Image Captions
Answer Them All! Toward Universal Visual Question Answering Models
Unsupervised Multi-Modal Neural Machine Translation
Multi-Task Learning of Hierarchical Vision-Language Representation
Cross-Modal Self-Attention Network for Referring Image Segmentation
DuDoNet: Dual Domain Network for CT Metal Artifact Reduction
Fast Spatio-Temporal Residual Network for Video Super-Resolution
Complete the Look: Scene-Based Complementary Product Recommendation
Selective Sensor Fusion for Neural Visual-Inertial Odometry
Look More Than Once: An Accurate Detector for Text of Arbitrary Shapes
Learning Binary Code for Personalized Fashion Recommendation
Attention Based Glaucoma Detection: A Large-Scale Database and CNN Model
Privacy Protection in Street-View Panoramas Using Depth and Multi-View Imagery
Grounding Human-To-Vehicle Advice for Self-Driving Vehicles
Multi-Step Prediction of Occupancy Grid Maps With Recurrent Neural Networks
Connecting Touch and Vision via Cross-Modal Prediction
X2CT-GAN: Reconstructing CT From Biplanar X-Rays With Generative Adversarial Networks
Practical Full Resolution Learned Lossless Image Compression
Image-To-Image Translation via Group-Wise Deep Whitening-And-Coloring Transformation
Max-Sliced Wasserstein Distance and Its Use for GANs
Meta-Learning With Differentiable Convex Optimization
RePr: Improved Training of Convolutional Filters
Tangent-Normal Adversarial Regularization for Semi-Supervised Learning
Auto-Encoding Scene Graphs for Image Captioning
Fast, Diverse and Accurate Image Captioning Guided by Part-Of-Speech
Attention Branch Network: Learning of Attention Mechanism for Visual Explanation
Cascaded Projection: End-To-End Network Compression and Acceleration
DeepCaps: Going Deeper With Capsule Networks
FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search
APDrawingGAN: Generating Artistic Portrait Drawings From Face Photos With Hierarchical GANs
Constrained Generative Adversarial Networks for Interactive Image Generation
WarpGAN: Automatic Caricature Generation
Explainability Methods for Graph Convolutional Neural Networks
A Generative Adversarial Density Estimator
SoDeep: A Sorting Deep Net to Learn Ranking Loss Surrogates
High-Quality Face Capture Using Anatomical Muscles
FML: Face Model Learning From Videos
AdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representations
3D Hand Shape and Pose Estimation From a Single RGB Image
3D Hand Shape and Pose From Images in the Wild
Self-Supervised 3D Hand Pose Estimation Through Training by Fitting
CrowdPose: Efficient Crowded Scenes Pose Estimation and a New Benchmark
Towards Social Artificial Intelligence: Nonverbal Social Signal Prediction in a Triadic Interaction
HoloPose: Holistic 3D Human Reconstruction In-The-Wild
Weakly-Supervised Discovery of Geometry-Aware Representation for 3D Human Pose Estimation
In the Wild Human Pose Estimation Using Explicit 2D Features and Intermediate 3D Representations
Slim DensePose: Thrifty Learning From Sparse Annotations and Motion Cues
Self-Supervised Representation Learning From Videos for Facial Action Unit Detection
Combining 3D Morphable Models: A Large Scale Face-And-Head Model
Boosting Local Shape Matching for Dense 3D Face Correspondence
Unsupervised Part-Based Disentangling of Object Shape and Appearance
Monocular Total Capture: Posing Face, Body, and Hands in the Wild
Expressive Body Capture: 3D Hands, Face, and Body From a Single Image
Neural RGB®D Sensing: Depth and Uncertainty From a Video Camera
DAVANet: Stereo Deblurring With View Aggregation
DVC: An End-To-End Deep Video Compression Framework
SOSNet: Second Order Similarity Regularization for Local Descriptor Learning
“Double-DIP”: Unsupervised Image Decomposition via Coupled Deep-Image-Priors
Unprocessing Images for Learned Raw Denoising
Residual Networks for Light Field Image Super-Resolution
Modulating Image Restoration With Continual Levels via Adaptive Feature Modification Layers
Second-Order Attention Network for Single Image Super-Resolution
Devil Is in the Edges: Learning Semantic Boundaries From Noisy Annotations
Path-Invariant Map Networks
FilterReg: Robust and Efficient Probabilistic Point-Set Registration Using Gaussian Filter and Twist Parameterization
Probabilistic Permutation Synchronization Using the Riemannian Structure of the Birkhoff Polytope
Lifting Vectorial Variational Problems: A Natural Formulation Based on Geometric Measure Theory and Discrete Exterior Calculus
A Sufficient Condition for Convergences of Adam and RMSProp
Guaranteed Matrix Completion Under Multiple Linear Transformations
MAP Inference via Block-Coordinate Frank-Wolfe Algorithm
A Convex Relaxation for Multi-Graph Matching
Pixel-Adaptive Convolutional Neural Networks
Single-Frame Regularization for Temporally Stable CNNs
An End-To-End Network for Generating Social Relationship Graphs
Meta-Learning Convolutional Neural Architectures for Multi-Target Concrete Defect Classification With the COncrete DEfect BRidge IMage Dataset
ECC: Platform-Independent Energy-Constrained Deep Neural Network Compression via a Bilinear Regression Model
SeerNet: Predicting Convolutional Neural Network Feature-Map Sparsity Through Low-Bit Quantization
Defending Against Adversarial Attacks by Randomized Diversification
Rob-GAN: Generator, Discriminator, and Adversarial Attacker
Learning From Noisy Labels by Regularized Estimation of Annotator Confusion
Task-Free Continual Learning
Importance Estimation for Neural Network Pruning
Detecting Overfitting of Deep Generative Networks via Latent Recovery
Coloring With Limited Data: Few-Shot Colorization via Memory Augmented Networks
Characterizing and Avoiding Negative Transfer
Building Efficient Deep Neural Networks With Unitary Group Convolutions
Semi-Supervised Learning With Graph Learning-Convolutional Networks
Learning to Remember: A Synaptic Plasticity Driven Framework for Continual Learning
AIRD: Adversarial Learning Framework for Image Repurposing Detection
A Kernelized Manifold Mapping to Diminish the Effect of Adversarial Perturbations
Trust Region Based Adversarial Attack on Neural Networks
PEPSI : Fast Image Inpainting With Parallel Decoding Network
Model-Blind Video Denoising via Frame-To-Frame Training
End-To-End Efficient Representation Learning via Cascading Combinatorial Optimization
Sim-Real Joint Reinforcement Transfer for 3D Indoor Navigation
ChamNet: Towards Efficient Network Design Through Platform-Aware Model Adaptation
Regularizing Activation Distribution for Training Binarized Deep Networks
Robustness Verification of Classification Deep Neural Networks via Linear Programming
Additive Adversarial Learning for Unbiased Authentication
Simultaneously Optimizing Weight and Quantizer of Ternary Neural Network Using Truncated Gaussian Approximation
Adversarial Defense by Stratified Convolutional Sparse Coding
Exploring Object Relation in Mean Teacher for Cross-Domain Detection
Hierarchical Disentanglement of Discriminative Latent Features for Zero-Shot Learning
R2GAN: Cross-Modal Recipe Retrieval With Generative Adversarial Network
Rethinking Knowledge Graph Propagation for Zero-Shot Learning
Learning to Learn Image Classifiers With Visual Analogy
Where’s Wally Now? Deep Generative and Discriminative Embeddings for Novelty Detection
Weakly Supervised Image Classification Through Noise Regularization
Data-Driven Neuron Allocation for Scale Aggregation Networks
Graphical Contrastive Losses for Scene Graph Parsing
Deep Transfer Learning for Multiple Class Novelty Detection
QATM: Quality-Aware Template Matching for Deep Learning
Retrieval-Augmented Convolutional Neural Networks Against Adversarial Examples
Learning Cross-Modal Embeddings With Adversarial Networks for Cooking Recipes and Food Images
FastDraw: Addressing the Long Tail of Lane Detection by Adapting a Sequential Prediction Network
Weakly Supervised Video Moment Retrieval From Text Queries
Content-Aware Multi-Level Guidance for Interactive Instance Segmentation
Greedy Structure Learning of Hierarchical Compositional Models
Interactive Full Image Segmentation by Considering All Regions Jointly
Learning Active Contour Models for Medical Image Segmentation
Customizable Architecture Search for Semantic Segmentation
Local Features and Visual Words Emerge in Activations
Hyperspectral Image Super-Resolution With Optimized RGB Guidance
Adaptive Confidence Smoothing for Generalized Zero-Shot Learning
PMS-Net: Robust Haze Removal Based on Patch Map for Single Images
Deep Spherical Quantization for Image Search
Large-Scale Interactive Object Segmentation With Human Annotators
A Poisson-Gaussian Denoising Dataset With Real Fluorescence Microscopy Images
Task Agnostic Meta-Learning for Few-Shot Learning
Progressive Ensemble Networks for Zero-Shot Recognition
Direct Object Recognition Without Line-Of-Sight Using Optical Coherence
Atlas of Digital Pathology: A Generalized Hierarchical Histological Tissue Type-Annotated Database for Deep Learning
Perturbation Analysis of the 8-Point Algorithm: A Case Study for Wide FoV Cameras
Robustness of 3D Deep Learning in an Adversarial Setting
SceneCode: Monocular Dense Semantic Reconstruction Using Learned Encoded Scene Representations
StereoDRNet: Dilated Residual StereoNet
The Alignment of the Spheres: Globally-Optimal Spherical Mixture Alignment for Camera Pose Estimation
Learning Joint Reconstruction of Hands and Manipulated Objects
Deep Single Image Camera Calibration With Radial Distortion
CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depth
Translate-to-Recognize Networks for RGB-D Scene Recognition
Re-Identification Supervised Texture Generation
Action4D: Online Action Recognition in the Crowd and Clutter
Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction
Attribute-Aware Face Aging With Wavelet-Based Generative Adversarial Networks
Noise-Tolerant Paradigm for Training Face Recognition CNNs
Low-Rank Laplacian-Uniform Mixed Model for Robust Face Recognition
Generalizing Eye Tracking With Bayesian Adversarial Learning
Local Relationship Learning With Person-Specific Shape Regularization for Facial Action Unit Detection
Point-To-Pose Voting Based Hand Pose Estimation Using Residual Permutation Equivariant Layer
Improving Few-Shot User-Specific Gaze Adaptation via Gaze Redirection Synthesis
AdaptiveFace: Adaptive Margin and Sampling for Face Recognition
Disentangled Representation Learning for 3D Face Shape
LBS Autoencoder: Self-Supervised Fitting of Articulated Meshes to Point Clouds
PifPaf: Composite Fields for Human Pose Estimation
TACNet: Transition-Aware Context Network for Spatio-Temporal Action Detection
Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videos
Local Temporal Bilinear Pooling for Fine-Grained Action Parsing
Improving Action Localization by Progressive Cross-Stream Cooperation
Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition
A Neural Network Based on SPD Manifold Learning for Skeleton-Based Hand Gesture Recognition
Large-Scale Weakly-Supervised Pre-Training for Video Action Recognition
Learning Spatio-Temporal Representation With Local and Global Diffusion
Unsupervised Learning of Action Classes With Continuous Temporal Embedding
Double Nuclear Norm Based Low Rank Representation on Grassmann Manifolds for Clustering
SR-LSTM: State Refinement for LSTM Towards Pedestrian Trajectory Prediction
Unsupervised Deep Epipolar Flow for Stationary or Dynamic Scenes
An Efficient Schmidt-EKF for 3D Visual-Inertial SLAM
A Neural Temporal Model for Human Motion Prediction
Multi-Agent Tensor Fusion for Contextual Trajectory Prediction
Coordinate-Based Texture Inpainting for Pose-Guided Human Image Generation
On Stabilizing Generative Adversarial Training With Noise
Self-Supervised GANs via Auxiliary Rotation Loss
Texture Mixer: A Network for Controllable Synthesis and Interpolation of Texture
Object-Driven Text-To-Image Synthesis via Adversarial Training
Zoom-In-To-Check: Boosting Video Interpolation via Instance-Level Discrimination
Disentangling Latent Space for VAE by Label Relevant/Irrelevant Dimensions
Spectral Reconstruction From Dispersive Blur: A Novel Light Efficient Spectral Imager
Quasi-Unsupervised Color Constancy
Deep Defocus Map Estimation Using Domain Adaptation
Using Unknown Occluders to Recover Hidden Scenes
Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation
Learning Parallax Attention for Stereo Image Super-Resolution
Knowing When to Stop: Evaluation and Verification of Conformity to Output-Size Specifications
Spatial Attentive Single-Image Deraining With a High Quality Real Rain Dataset
Focus Is All You Need: Loss Functions for Event-Based Vision
Scalable Convolutional Neural Network for Image Compressed Sensing
Event Cameras, Contrast Maximization and Reward Functions: An Analysis
Convolutional Neural Networks Can Be Deceived by Visual Illusions
PDE Acceleration for Active Contours
Dichromatic Model Based Temporal Color Constancy for AC Light Sources
Semantic Attribute Matching Networks
Skin-Based Identification From Multispectral Image Data Using CNNs
Large-Scale Distributed Second-Order Optimization Using Kronecker-Factored Approximate Curvature for Deep Convolutional Neural Networks
Putting Humans in a Scene: Learning Affordance in 3D Indoor Environments
PIEs: Pose Invariant Embeddings
Representation Similarity Analysis for Efficient Task Taxonomy & Transfer Learning
Object Counting and Instance Segmentation With Image-Level Supervision
Variational Autoencoders Pursue PCA Directions (by Accident)
A Relation-Augmented Fully Convolutional Network for Semantic Segmentation in Aerial Scenes
Temporal Transformer Networks: Joint Learning of Invariant and Discriminative Time Warping
PCAN: 3D Attention Map Learning Using Contextual Information for Point Cloud Based Retrieval
Depth Coefficients for Depth Completion
Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detection
Good News, Everyone! Context Driven Entity-Aware Captioning for News Images
Multi-Level Multimodal Common Semantic Space for Image-Phrase Grounding
Spatio-Temporal Dynamics and Semantic Attribute Enriched Visual Encoding for Video Captioning
Pointing Novel Objects in Image Captioning
Informative Object Annotations: Tell Me Something I Don’t Know
Engaging Image Captioning via Personality
Vision-Based Navigation With Language-Based Assistance via Imitation Learning With Indirect Intervention
TOUCHDOWN: Natural Language Navigation and Spatial Reasoning in Visual Street Environments
A Simple Baseline for Audio-Visual Scene-Aware Dialog
End-To-End Learned Random Walker for Seeded Image Segmentation
Efficient Neural Network Compression
Cascaded Generative and Discriminative Learning for Microcalcification Detection in Breast Mammograms
C3AE: Exploring the Limits of Compact Model for Age Estimation
Adaptive Weighting Multi-Field-Of-View CNN for Semantic Segmentation in Pathology
In Defense of Pre-Trained ImageNet Architectures for Real-Time Semantic Segmentation of Road-Driving Images
Context-Aware Visual Compatibility Prediction
Sim-To-Real via Sim-To-Sim: Data-Efficient Robotic Grasping via Randomized-To-Canonical Adaptation Networks
Multiview 2D/3D Rigid Registration via a Point-Of-Interest Network for Tracking and Triangulation
Context-Aware Spatio-Recurrent Curvilinear Structure Segmentation
An Alternative Deep Feature Approach to Line Level Keyword Spotting
Dynamics Are Important for the Recognition of Equine Pain in Video
LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving
Machine Vision Guided 3D Medical Image Compression for Efficient Transmission and Accurate Segmentation in the Clouds
PointPillars: Fast Encoders for Object Detection From Point Clouds
Motion Estimation of Non-Holonomic Ground Vehicles From a Single Feature Correspondence Measured Over N Views
From Coarse to Fine: Robust Hierarchical Localization at Large Scale
Large Scale High-Resolution Land Cover Mapping With Multi-Resolution Data
Leveraging Heterogeneous Auxiliary Tasks to Assist Crowd Counting