CVPR 2018
参考链接
Paperlist
Embodied Question Answering
Learning by Asking Questions
Finding Tiny Faces in the Wild With Generative Adversarial Network
Learning Face Age Progression: A Pyramid Architecture of GANs
PairedCycleGAN: Asymmetric Style Transfer for Applying and Removing Makeup
GANerated Hands for Real-Time 3D Hand Tracking From Monocular RGB
Learning Pose Specific Representations by Predicting Different Views
Weakly and Semi Supervised Human Body Part Parsing via Pose-Guided Knowledge Transfer
Person Transfer GAN to Bridge Domain Gap for Person Re-Identification
Cross-Modal Deep Variational Hand Pose Estimation
Disentangled Person Image Generation
Super-FAN: Integrated Facial Landmark Localization and Super-Resolution of Real-World Low Resolution Faces in Arbitrary Poses With GANs
Multistage Adversarial Losses for Pose-Based Human Image Synthesis
Rotation Averaging and Strong Duality
Hybrid Camera Pose Estimation
A Certifiably Globally Optimal Solution to the Non-Minimal Relative Pose Problem
Single View Stereo Matching
Fight Ill-Posedness With Ill-Posedness: Single-Shot Variational Depth Super-Resolution From Shading
Deep Depth Completion of a Single RGB-D Image
Multi-View Harmonized Bilinear Network for 3D Object Recognition
PPFNet: Global Context Aware Local Features for Robust 3D Point Matching
FoldingNet: Point Cloud Auto-Encoder via Deep Grid Deformation
A Papier-Mâché Approach to Learning 3D Surface Generation
LEGO: Learning Edge With Geometry All at Once by Watching Videos
Five-Point Fundamental Matrix Estimation for Uncalibrated Cameras
PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation
Scalable Dense Non-Rigid Structure-From-Motion: A Grassmannian Perspective
GVCNN: Group-View Convolutional Neural Networks for 3D Shape Recognition
Depth and Transient Imaging With Compressive SPAD Array Cameras
GeoNet: Geometric Neural Network for Joint Depth and Surface Normal Estimation
Real-Time Seamless Single Shot 6D Object Pose Prediction
Factoring Shape, Pose, and Layout From the 2D Image of a 3D Scene
Monocular Relative Depth Perception With Web Stereo Data Supervision
Spline Error Weighting for Robust Visual-Inertial Fusion
Single-Image Depth Estimation Based on Fourier Domain Analysis
Unsupervised Learning of Monocular Depth Estimation and Visual Odometry With Deep Feature Reconstruction
Detect-and-Track: Efficient Pose Estimation in Videos
Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark Detectors
Diversity Regularized Spatiotemporal Attention for Video-Based Person Re-Identification
Style Aggregated Network for Facial Landmark Detection
Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervision
Deep Cost-Sensitive and Order-Preserving Feature Learning for Cross-Population Age Estimation
First-Person Hand Action Benchmark With RGB-D Videos and 3D Hand Pose Annotations
A Pose-Sensitive Embedding for Person Re-Identification With Expanded Cross Neighborhood Re-Ranking
Disentangling 3D Pose in a Dendritic CNN for Unconstrained 2D Face Alignment
A Hierarchical Generative Model for Eye Image Synthesis and Eye Gaze Estimation
MiCT: Mixed 3D/2D Convolutional Tube for Human Action Recognition
Learning to Estimate 3D Human Pose and Shape From a Single Color Image
Glimpse Clouds: Human Activity Recognition From Unstructured Feature Points
Context-Aware Deep Feature Compression for High-Speed Visual Tracking
Correlation Tracking via Joint Discrimination and Reliability Learning
PhaseNet for Video Frame Interpolation
The Best of Both Worlds: Combining CNNs and Geometric Constraints for Hierarchical Motion Segmentation
Hyperparameter Optimization for Tracking With Continuous Deep Q-Learning
Scale-Transferrable Object Detection
A Prior-Less Method for Multi-Face Tracking in Unconstrained Videos
End-to-End Flow Correlation Tracking With Spatial-Temporal Attention
Deep Texture Manifold for Ground Terrain Recognition
Learning Superpixels With Segmentation-Aware Affinity Loss
Interactive Image Segmentation With Latent Diversity
The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
Local Descriptors Optimized for Average Precision
Recovering Realistic Texture in Image Super-Resolution by Deep Spatial Feature Transform
Deep Extreme Cut: From Extreme Points to Object Segmentation
Learning to Parse Wireframes in Images of Man-Made Environments
Occlusion-Aware Rolling Shutter Rectification of 3D Scenes
Content-Sensitive Supervoxels via Uniform Tessellations on Video Manifolds
Intrinsic Image Transformation via Scale Space Decomposition
Learned Shape-Tailored Descriptors for Segmentation
PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing
Multi-Image Semantic Matching by Mining Consistent Features
Density-Aware Single Image De-Raining Using a Multi-Stream Dense Network
Joint Cuts and Matching of Partitions in One Graph
Progressive Attention Guided Recurrent Network for Salient Object Detection
Fast and Accurate Single Image Super-Resolution via Information Distillation Network
Hallucinated-IQA: No-Reference Image Quality Assessment via Adversarial Learning
NAG: Network for Adversary Generation
Dynamic-Structured Semantic Propagation Network
Cross-Domain Self-Supervised Multi-Task Feature Learning Using Synthetic Imagery
A Two-Step Disentanglement Method
Robust Facial Landmark Detection via a Fully-Convolutional Local-Global Context Network
Decorrelated Batch Normalization
Learning to Sketch With Shortcut Cycle Consistency
Towards a Mathematical Understanding of the Difficulty in Learning With Feedforward Neural Networks
FaceID-GAN: Learning a Symmetry Three-Player GAN for Identity-Preserving Face Synthesis
A Constrained Deep Neural Network for Ordinal Regression
Modulated Convolutional Networks
Learning Steerable Filters for Rotation Equivariant CNNs
Efficient Interactive Annotation of Segmentation Datasets With Polygon-RNN++
SplineCNN: Fast Geometric Deep Learning With Continuous B-Spline Kernels
GAGAN: Geometry-Aware Generative Adversarial Networks
On the Robustness of Semantic Segmentation Models to Adversarial Attacks
Feedback-Prop: Convolutional Neural Network Inference Under Partial Evidence
Super-Resolving Very Low-Resolution Face Images With Supplementary Attributes
Frustum PointNets for 3D Object Detection From RGB-D Data
W2F: A Weakly-Supervised to Fully-Supervised Framework for Object Detection
3D Object Detection With Latent Support Surfaces
Towards Faster Training of Global Covariance Pooling Networks by Iterative Matrix Square Root Normalization
Recurrent Scene Parsing With Perspective Understanding in the Loop
Improving Occlusion and Hard Negative Handling for Single-Stage Pedestrian Detectors
Learning to Act Properly: Predicting and Explaining Affordances From Images
Pointwise Convolutional Neural Networks
Image-Image Domain Adaptation With Preserved Self-Similarity and Domain-Dissimilarity for Person Re-Identification
A Generative Adversarial Approach for Zero-Shot Learning From Noisy Texts
Tensorize, Factorize and Regularize: Robust Visual Relationship Learning
Transductive Unbiased Embedding for Zero-Shot Learning
Hierarchical Novelty Detection for Visual Object Recognition
Zero-Shot Visual Recognition Using Semantics-Preserving Adversarial Embedding Networks
Learning Rich Features for Image Manipulation Detection
Human Semantic Parsing for Person Re-Identification
Stacked Latent Attention for Multimodal Reasoning
R-FCN-3000 at 30fps: Decoupling Detection and Classification
CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes
Revisiting Knowledge Transfer for Training Object Class Detectors
Deep Sparse Coding for Invariant Multimodal Halle Berry Neurons
On the Convergence of PatchMatch and Its Variants
Rethinking the Faster R-CNN Architecture for Temporal Action Localization
MoNet: Deep Motion Exploitation for Video Object Segmentation
Video Representation Learning Using Discriminative Pooling
Recognizing Human Actions as the Evolution of Pose Estimation Maps
Video Person Re-Identification With Competitive Snippet-Similarity Aggregation and Co-Attentive Snippet Embedding
Mask-Guided Contrastive Attention Model for Person Re-Identification
Blazingly Fast Video Object Segmentation With Pixel-Wise Metric Learning
Learning to Compare: Relation Network for Few-Shot Learning
COCO-Stuff: Thing and Stuff Classes in Context
Image Generation From Scene Graphs
Deep Cauchy Hashing for Hamming Space Retrieval
Learning to Look Around: Intelligently Exploring Unseen Environments for Unknown Tasks
Multi-Scale Location-Aware Kernel Representation for Object Detection
Clinical Skin Lesion Diagnosis Using Representations Inspired by Dermatologist Criteria
Compare and Contrast: Learning Prominent Visual Differences
Multi-Evidence Filtering and Fusion for Multi-Label Classification, Object Detection and Semantic Segmentation Based on Weakly Supervised Learning
HashGAN: Deep Learning to Hash With Pair Conditional Wasserstein GAN
Min-Entropy Latent Model for Weakly Supervised Object Detection
MAttNet: Modular Attention Network for Referring Expression Comprehension
AttnGAN: Fine-Grained Text to Image Generation With Attentional Generative Adversarial Networks
Adversarial Complementary Learning for Weakly Supervised Object Localization
Conditional Generative Adversarial Network for Structured Domain Adaptation
GroupCap: Group-Based Image Captioning With Structured Relevance and Diversity Constraints
Weakly-Supervised Semantic Segmentation by Iteratively Mining Common Object Features
Bootstrapping the Performance of Webly Supervised Semantic Segmentation
DeepVoting: A Robust and Explainable Deep Network for Semantic Part Detection Under Partial Occlusion
Geometry-Aware Scene Text Detection With Instance Transformation Network
Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognition
Motion-Guided Cascaded Refinement Network for Video Object Segmentation
A Memory Network Approach for Story-Based Temporal Summarization of 360° Videos
Cube Padding for Weakly-Supervised Saliency Prediction in 360° Videos
Appearance-and-Relation Networks for Video Classification
Excitation Backprop for RNNs
One-Shot Action Localization by Learning Sequence Matching Network
Structure Preserving Video Prediction
Person Re-Identification With Cascaded Pairwise Convolutions
On the Importance of Label Quality for Semantic Segmentation
Scalable and Effective Deep CCA via Soft Decorrelation
Duplex Generative Adversarial Network for Unsupervised Domain Adaptation
Edit Probability for Scene Text Recognition
Global Versus Localized Generative Adversarial Nets
MoCoGAN: Decomposing Motion and Content for Video Generation
Recurrent Residual Module for Fast Inference in Videos
Improving Landmark Localization With Semi-Supervised Learning
Adversarial Data Programming: Using GANs to Relax the Bottleneck of Curated Labeled Data
Stochastic Variational Inference With Gradient Linearization
Multi-Label Zero-Shot Learning With Structured Knowledge Graphs
MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks
Deep Adversarial Subspace Clustering
Towards Human-Machine Cooperation: Self-Supervised Sample Mining for Object Detection
Discrete-Continuous ADMM for Transductive Inference in Higher-Order MRFs
Robust Physical-World Attacks on Deep Learning Visual Classification
Generating a Fusion Image: One's Identity and Another's Shape
Learning to Promote Saliency Detectors
Image Super-Resolution via Dual-State Recurrent Networks
Deep Back-Projection Networks for Super-Resolution
Focus Manipulation Detection via Photometric Histogram Analysis
Compassionately Conservative Balanced Cuts for Image Segmentation
A High-Quality Denoising Dataset for Smartphone Cameras
Context-Aware Synthesis for Video Frame Interpolation
Salient Object Detection Driven by Fixation Prediction
Enhancing the Spatial Resolution of Stereo Images Using a Parallax Prior
HATS: Histograms of Averaged Time Surfaces for Robust Event-Based Object Classification
A Bi-Directional Message Passing Model for Salient Object Detection
Matching Pixels Using Co-Occurrence Statistics
SeedNet: Automatic Seed Generation With Deep Reinforcement Learning for Robust Interactive Segmentation
Jerk-Aware Video Acceleration Magnification
Defense Against Adversarial Attacks Using High-Level Representation Guided Denoiser
Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal
Image Correction via Deep Reciprocating HDR Transformation
PieAPP: Perceptual Image-Error Assessment Through Pairwise Preference
Normalized Cut Loss for Weakly-Supervised CNN Segmentation
ISTA-Net: Interpretable Optimization-Inspired Deep Network for Image Compressive Sensing
Fast End-to-End Trainable Guided Filter
Disentangling Structure and Aesthetics for Style-Aware Image Completion
Learning a Discriminative Feature Network for Semantic Segmentation
Kernelized Subspace Pooling for Deep Local Descriptors
pOSE: Pseudo Object Space Error for Initialization-Free Bundle Adjustment
Deformable Shape Completion With Graph Convolutional Autoencoders
Learning From Millions of 3D Scans for Large-Scale 3D Face Recognition
CarFusion: Combining Point Tracking and Part Detection for Dynamic 3D Reconstruction of Vehicles
Deep Material-Aware Cross-Spectral Stereo Matching
Augmenting Crowd-Sourced 3D Reconstructions Using Semantic Detections
Matryoshka Networks: Predicting 3D Geometry via Nested Shape Layers
Triplet-Center Loss for Multi-View 3D Object Retrieval
Learning 3D Shape Completion From Laser Scan Data With Weak Supervision
End-to-End Learning of Keypoint Detector and Descriptor for Pose Invariant 3D Matching
ICE-BA: Incremental, Consistent and Efficient Bundle Adjustment for Visual-Inertial SLAM
GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose
Radially-Distorted Conjugate Translations
Deep Ordinal Regression Network for Monocular Depth Estimation
Analytical Modeling of Vanishing Points and Curves in Catadioptric Cameras
Learning Depth From Monocular Videos Using Direct Methods
Salience Guided Depth Calibration for Perceptually Optimized Compressive Light Field 3D Display
MegaDepth: Learning Single-View Depth Prediction From Internet Photos
LayoutNet: Reconstructing the 3D Room Layout From a Single RGB Image
CBMV: A Coalesced Bidirectional Matching Volume for Disparity Estimation
Zoom and Learn: Generalizing Deep Stereo Matching to Novel Domains
Exploring Disentangled Feature Representation Beyond Face Identification
Learning Facial Action Units From Web Images With Scalable Weakly Supervised Clustering
Human Pose Estimation With Parsing Induced Learner
Multi-Level Factorisation Net for Person Re-Identification
Attention-Aware Compositional Network for Person Re-Identification
Look at Boundary: A Boundary-Aware Face Alignment Algorithm
Demo2Vec: Reasoning Object Affordances From Online Videos
Monocular 3D Pose and Shape Estimation of Multiple People in Natural Scenes - The Importance of Multiple Scene Constraints
3D Human Sensing, Action and Emotion Recognition in Robot Assisted Therapy of Children With Autism
Facial Expression Recognition by De-Expression Residue Learning
A Causal And-Or Graph Model for Visibility Fluent Reasoning in Tracking Interacting Objects
Weakly Supervised Facial Action Unit Recognition Through Adversarial Training
Non-Linear Temporal Subspace Representations for Activity Recognition
Towards Pose Invariant Face Recognition in the Wild
Unifying Identification and Context Learning for Person Recognition
Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation
Wing Loss for Robust Facial Landmark Localisation With Convolutional Neural Networks
Multiple Granularity Group Interaction Prediction
Social GAN: Socially Acceptable Trajectories With Generative Adversarial Networks
Deep Group-Shuffling Random Walk for Person Re-Identification
Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-Identification
Harmonious Attention Network for Person Re-Identification
Real-Time Rotation-Invariant Face Detection With Progressive Calibration Networks
Deep Regression Forests for Age Estimation
Weakly-Supervised Deep Convolutional Neural Network Learning for Facial Action Unit Intensity Estimation
Memory Based Online Learning of Deep Representations From Video Streams
Efficient and Deep Person Re-Identification Using Multi-Level Similarity
Multi-Level Fusion Based 3D Object Detection From Monocular Images
A Perceptual Measure for Deep Single Image Camera Calibration
Learning to Generate Time-Lapse Videos Using Multi-Stage Dynamic Generative Adversarial Networks
Document Enhancement Using Visibility Detection
A Weighted Sparse Sampling and Smoothing Frame Transition Approach for Semantic Fast-Forward First-Person Videos
Context Contrasted Feature and Gated Multi-Scale Aggregation for Scene Segmentation
Deep Layer Aggregation
Convolutional Neural Networks With Alternately Updated Clique
Practical Block-Wise Neural Network Architecture Generation
xUnit: Learning a Spatial Activation Function for Efficient Image Restoration
Crafting a Toolchain for Image Restoration by Deep Reinforcement Learning
Deformation Aware Image Compression
Distributable Consistent Multi-Object Matching
Residual Dense Network for Image Super-Resolution
Attentive Generative Adversarial Network for Raindrop Removal From a Single Image
FSRNet: End-to-End Learning Face Super-Resolution With Facial Priors
Burst Denoising With Kernel Prediction Networks
Unsupervised Sparse Dirichlet-Net for Hyperspectral Image Super-Resolution
Dynamic Scene Deblurring Using Spatially Variant Recurrent Neural Networks
SPLATNet: Sparse Lattice Networks for Point Cloud Processing
Surface Networks
Self-Supervised Multi-Level Face Model Learning for Monocular Reconstruction at Over 250 Hz
CodeSLAM â Learning a Compact, Optimisable Representation for Dense Visual SLAM
SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation
PlaneNet: Piece-Wise Planar Reconstruction From a Single RGB Image
Deep Parametric Continuous Convolutional Neural Networks
FeaStNet: Feature-Steered Graph Convolutions for 3D Shape Analysis
Image Collection Pop-Up: 3D Reconstruction and Clustering of Rigid and Non-Rigid Categories
Geometry-Aware Learning of Maps for Camera Localization
Recurrent Slice Networks for 3D Segmentation of Point Clouds
Depth-Based 3D Hand Pose Estimation: From Current Achievements to Future Goals
SobolevFusion: 3D Reconstruction of Scenes Undergoing Free Non-Rigid Motion
AdaDepth: Unsupervised Content Congruent Adaptation for Depth Estimation
Learning to Find Good Correspondences
OATM: Occlusion Aware Template Matching by Consensus Set Maximization
Deep Learning of Graph Matching
Unsupervised Discovery of Object Landmarks as Structural Representations
Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
Lean Multiclass Crowdsourcing
Partial Transfer Learning With Selective Adversarial Networks
Self-Supervised Feature Learning by Learning to Spot Artifacts
LDMNet: Low Dimensional Manifold Regularized Neural Networks
CondenseNet: An Efficient DenseNet Using Learned Group Convolutions
Learning Deep Descriptors With Scale-Aware Triplet Networks
Decoupled Networks
Deep Adversarial Metric Learning
PU-Net: Point Cloud Upsampling Network
Real-Time Monocular Depth Estimation Using Synthetic Data With Domain Adaptation via Image Style Transfer
Learning for Disparity Estimation Through Feature Constancy
DeepMVS: Learning Multi-View Stereopsis
Self-Calibrating Polarising Radiometric Calibration
Coding Kendall's Shape Trajectories for 3D Action Recognition
Efficient, Sparse Representation of Manifold Distance Matrices for Classical Scaling
Motion Segmentation by Exploiting Complementary Geometric Models
Estimation of Camera Locations in Highly Corrupted Scenarios: All About That Base, No Shape Trouble
4D Human Body Correspondences From Panoramic Depth Maps
Reconstructing Thin Structures of Manifold Surfaces by Integrating Spatial Curves
Multi-View Consistency as Supervisory Signal for Learning Shape and Pose Prediction
Probabilistic Plant Modeling via Multi-View Image-to-Image Translation
Deep Marching Cubes: Learning Explicit Surface Representations
Tags2Parts: Discovering Semantic Regions From Shape Tags
Uncalibrated Photometric Stereo Under Natural Illumination
Robust Depth Estimation From Auto Bracketed Images
Free Supervision From Video Games
Planar Shape Detection at Structural Scales
Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling
Camera Pose Estimation With Unknown Principal Point
Inverse Composition Discriminative Optimization for Point Cloud Registration
SurfConv: Bridging 3D and 2D Convolution for RGBD Images
A Fast Resection-Intersection Method for the Known Rotation Problem
3D Pose Estimation and 3D Model Retrieval for Objects in the Wild
Structure From Recurrent Motion: From Rigidity to Recurrency
Learning Patch Reconstructability for Accelerating Multi-View Stereo
Progressively Complementarity-Aware Fusion Network for RGB-D Salient Object Detection
Pixels, Voxels, and Views: A Study of Shape Representations for Single View 3D Object Shape Prediction
Learning Dual Convolutional Neural Networks for Low-Level Vision
Defocus Blur Detection via Multi-Stream Bottom-Top-Bottom Fully Convolutional Network
PiCANet: Learning Pixel-Wise Contextual Attention for Saliency Detection
Curve Reconstruction via the Global Statistics of Natural Curves
What Do Deep Networks Like to See?
âZero-Shotâ Super-Resolution Using Deep Internal Learning
Detect Globally, Refine Locally: A Novel Approach to Saliency Detection
Beyond the Pixel-Wise Loss for Topology-Aware Delineation
KIPPI: KInetic Polygonal Partitioning of Images
Image Blind Denoising With Generative Adversarial Network Based Noise Modeling
Multi-Scale Weighted Nuclear Norm Image Restoration
MoNet: Moments Embedding Network
Active Fixation Control to Predict Saccade Sequences
Densely Connected Pyramid Dehazing Network
Universal Denoising Networks : A Novel CNN Architecture for Image Denoising
Learning Convolutional Networks for Content-Weighted Image Compression
Deep Video Super-Resolution Network Using Dynamic Upsampling Filters Without Explicit Motion Compensation
Erase or Fill? Deep Joint Recurrent Rain Removal and Reconstruction in Videos
Flow Guided Recurrent Neural Encoder for Video Salient Object Detection
Gated Fusion Network for Single Image Dehazing
Learning a Single Convolutional Super-Resolution Network for Multiple Degradations
Non-Blind Deblurring: Handling Kernel Uncertainty With CNNs
Boundary Flow: A Siamese Network That Predicts Boundary Motion Without Training on Motion
Learning to See in the Dark
BPGrad: Towards Global Optimality in Deep Learning via Branch and Pruning
Perturbative Neural Networks
Unsupervised Correlation Analysis
A Biresolution Spectral Framework for Product Quantization
Domain Adaptive Faster R-CNN for Object Detection in the Wild
Low-Shot Learning With Large-Scale Diffusion
Joint Pose and Expression Modeling for Facial Expression Recognition
Lightweight Probabilistic Deep Networks
Adversarially Learned One-Class Classifier for Novelty Detection
Defense Against Universal Adversarial Perturbations
Disentangling Factors of Variation by Mixing Them
Deformable GANs for Pose-Based Human Image Generation
Hierarchical Recurrent Attention Networks for Structured Online Maps
Sliced Wasserstein Distance for Learning Gaussian Mixture Models
Aligning Infinite-Dimensional Covariance Matrices in Reproducing Kernel Hilbert Spaces for Domain Adaptation
CLEAR: Cumulative LEARning for One-Shot One-Class Image Recognition
Local and Global Optimization Techniques in Graph-Based Clustering
Multi-Task Learning by Maximizing Statistical Dependence
Robust Classification With Convolutional Prototype Learning
Generative Modeling Using the Sliced Wasserstein Distance
Learning Time/Memory-Efficient Deep Architectures With Budgeted Super Networks
Cross-View Image Synthesis Using Conditional GANs
Sparse, Smart Contours to Represent and Edit Images
Anticipating Traffic Accidents With Adaptive Loss and Large-Scale Incident DB
A Minimalist Approach to Type-Agnostic Detection of Quadrics in Point Clouds
Facelet-Bank for Fast Portrait Manipulation
Visual to Sound: Generating Natural Sound for Videos in the Wild
3D-RCNN: Instance-Level 3D Object Reconstruction via Render-and-Compare
Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting With a Single Convolutional Net
An Analysis of Scale Invariance in Object Detection  SNIP
Relation Networks for Object Detection
Zero-Shot Sketch-Image Hashing
VizWiz Grand Challenge: Answering Visual Questions From Blind People
Divide and Grow: Capturing Huge Diversity in Crowd Images With Incrementally Growing CNN
Structured Set Matching Networks for One-Shot Part Labeling
Self-Supervised Learning of Geometrically Stable Features Through Probabilistic Introspection
Link and Code: Fast Indexing With Graphs and Compact Regression Codes
Textbook Question Answering Under Instructor Guidance With Memory Networks
Unsupervised Deep Generative Adversarial Hashing Network
Vision-and-Language Navigation: Interpreting Visually-Grounded Navigation Instructions in Real Environments
DenseASPP for Semantic Segmentation in Street Scenes
Efficient Optimization for Rank-Based Loss Functions
Wasserstein Introspective Neural Networks
Taskonomy: Disentangling Task Transfer Learning
Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
Unsupervised Feature Learning via Non-Parametric Instance Discrimination
Multi-Task Adversarial Network for Disentangled Feature Learning
Learning From Synthetic Data: Addressing Domain Shift for Semantic Segmentation
Empirical Study of the Topology and Geometry of Deep Networks
Boosting Domain Adaptation by Discovering Latent Domains
Shape From Shading Through Shape Evolution
Weakly Supervised Instance Segmentation Using Class Peak Response
Collaborative and Adversarial Network for Unsupervised Domain Adaptation
Environment Upgrade Reinforcement Learning for Non-Differentiable Multi-Stage Pipelines
Teaching Categories to Human Learners With Visual Explanations
Density Adaptive Point Set Registration
Left-Right Comparative Recurrent Model for Stereo Matching
Im2Pano3D: Extrapolating 360° Structure and Semantics Beyond the Field of View
Polarimetric Dense Monocular SLAM
A Unifying Contrast Maximization Framework for Event Cameras, With Applications to Motion, Depth, and Optical Flow Estimation
Modeling Facial Geometry Using Compositional VAEs
Tangent Convolutions for Dense Prediction in 3D
RayNet: Learning Volumetric 3D Reconstruction With Ray Potentials
Neural 3D Mesh Renderer
Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimation
Automatic 3D Indoor Scene Modeling From Single Panorama
Extreme 3D Face Reconstruction: Seeing Through Occlusions
Beyond Grobner Bases: Basis Selection for Minimal Solvers
Lions and Tigers and Bears: Capturing Non-Rigid, 3D, Articulated Shape From Images
Deep Cocktail Network: Multi-Source Unsupervised Domain Adaptation With Category Shift
DOTA: A Large-Scale Dataset for Object Detection in Aerial Images
Finding Beans in Burgers: Deep Semantic-Visual Embedding With Localization
Feature Super-Resolution: Make Machine See More Clearly
ClusterNet: Detecting Small Objects in Large Scenes by Exploiting Spatio-Temporal Information
MaskLab: Instance Segmentation by Refining Object Detection With Semantic and Direction Features
Hashing as Tie-Aware Learning to Rank
Classification-Driven Dynamic Image Enhancement
Knowledge Aided Consistency for Weakly Supervised Phrase Grounding
Who Let the Dogs Out? Modeling Dog Behavior From Visual Data
Pseudo Mask Augmented Object Detection
Dual Skipping Networks
Memory Matching Networks for One-Shot Image Recognition
IQA: Visual Question Answering in Interactive Environments
Pose Transferrable Person Re-Identification
Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning
Data Distillation: Towards Omni-Supervised Learning
Object Referring in Videos With Language and Human Gaze
Feature Selective Networks for Object Detection
Learning a Discriminative Filter Bank Within a CNN for Fine-Grained Recognition
Grounding Referring Expressions in Images by Variational Context
Dynamic Graph Generation Network: Generating Relational Knowledge From Diagrams
A Network Architecture for Point Cloud Classification via Automatic Depth Images Generation
Towards Dense Object Tracking in a 2D Honeybee Hive
Long-Term On-Board Prediction of People in Traffic Scenes Under Uncertainty
Single-Shot Refinement Neural Network for Object Detection
Video Captioning via Hierarchical Reinforcement Learning
Tips and Tricks for Visual Question Answering: Learnings From the 2017 Challenge
Learning to Segment Every Thing
Self-Supervised Adversarial Hashing Networks for Cross-Modal Retrieval
Parallel Attention: A Unified Framework for Visual Object Discovery Through Dialogs and Queries
Zigzag Learning for Weakly Supervised Object Detection
Attentive Fashion Grammar Network for Fashion Landmark Detection and Clothing Category Classification
Generalized Zero-Shot Learning via Synthesized Examples
Partially Shared Multi-Task Convolutional Neural Network With Local Constraint for Face Attribute Learning
SYQ: Learning Symmetric Quantization for Efficient Deep Neural Networks
DS*: Tighter Lifting-Free Convex Relaxations for Quadratic Matching Problems
Deep Mutual Learning
Coupled End-to-End Transfer Learning With Generalized Fisher Information
Residual Parameter Transfer for Deep Domain Adaptation
High-Order Tensor Regularization With Application to Attribute Ranking
Learning to Localize Sound Source in Visual Scenes
Dynamic Few-Shot Visual Learning Without Forgetting
Two-Step Quantization for Low-Bit Neural Networks
Improved Lossy Image Compression With Priming and Spatially Adaptive Bit Rates for Recurrent Networks
Conditional Probability Models for Deep Image Compression
Deep Diffeomorphic Transformer Networks
The Lovász-Softmax Loss: A Tractable Surrogate for the Optimization of the Intersection-Over-Union Measure in Neural Networks
Generative Adversarial Perturbations
Learning Strict Identity Mappings in Deep Residual Networks
Geometric Robustness of Deep Networks: Analysis and Improvement
View Extrapolation of Human Body From a Single Image
Geometry Aware Constrained Optimization Techniques for Deep Learning
PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition
An Efficient and Provable Approach for Mixture Proportion Estimation Using Linear Independence Assumption
VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection
Image to Image Translation for Domain Adaptation
MobileNetV2: Inverted Residuals and Linear Bottlenecks
Im2Struct: Recovering 3D Shape Structure From a Single RGB Image
Trust Your Model: Light Field Depth Estimation With Inline Occlusion Handling
Baseline Desensitizing in Translation Averaging
Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling
Large-Scale Point Cloud Semantic Segmentation With Superpoint Graphs
Very Large-Scale Global SfM by Distributed Motion Averaging
ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans
Solving the Perspective-2-Point Problem for Flying-Camera Photo Composition
Reflection Removal for Large-Scale 3D Point Clouds
Attentional ShapeContextNet for Point Cloud Recognition
Geometry-Aware Deep Network for Single-Image Novel View Synthesis
InverseFaceNet: Deep Monocular Inverse Face Rendering
Sparse Photometric 3D Face Reconstruction Guided by Morphable Models
Texture Mapping for 3D Reconstruction With RGB-D Sensor
Learning Less Is More - 6D Camera Localization via 3D Surface Regression
Feature Mapping for Learning Fast and Accurate 3D Pose Inference From Synthetic Images
Indoor RGB-D Compass From a Single Line and Plane
Geometry-Aware Network for Non-Rigid Shape Prediction From a Single View
Sim2Real Viewpoint Invariant Visual Servoing by Recurrent Control
DocUNet: Document Image Unwarping via a Stacked U-Net
Analysis of Hand Segmentation in the Wild
RoadTracer: Automatic Extraction of Road Networks From Aerial Images
Alternating-Stereo VINS: Observability Analysis and Performance Evaluation
Soccer on Your Tabletop
EPINET: A Fully-Convolutional Neural Network Using Epipolar Geometry for Depth From Light Field Images
A Hybrid l1-l0 Layer Decomposition Model for Tone Mapping
Deeply Learned Filter Response Functions for Hyperspectral Reconstruction
CRRN: Multi-Scale Guided Concurrent Reflection Removal Network
Single Image Reflection Separation With Perceptual Losses
A Robust Method for Strong Rolling Shutter Effects Correction Using Lines With Automatic Feature Selection
Time-Resolved Light Transport Decomposition for Thermal Photometric Stereo
Efficient Diverse Ensemble for Discriminative Co-Tracking
Rolling Shutter and Radial Distortion Are Features for High Frame Rate Multi-Camera Tracking
A Twofold Siamese Network for Real-Time Object Tracking
Multi-Cue Correlation Filters for Robust Visual Tracking
Learning Attentions: Residual Attentional Siamese Network for High Performance Online Visual Tracking
SINT++: Robust Visual Tracking via Adversarial Positive Instance Generation
High-Speed Tracking With Multi-Kernel Correlation Filters
Occlusion Aware Unsupervised Learning of Optical Flow
Revisiting Video Saliency: A Large-Scale Benchmark and a New Model
Learning Spatial-Temporal Regularized Correlation Filters for Visual Tracking
Multimodal Visual Concept Learning With Weakly Supervised Techniques
Efficient Large-Scale Approximate Nearest Neighbor Search on OpenCL FPGA
Learning a Complete Image Indexing Pipeline
Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual Reasoning
Fooling Vision and Language Models Despite Localization and Attention Mechanism
Categorizing Concepts With Basic Level for Vision-to-Language
Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering
Learning Pixel-Level Semantic Affinity With Image-Level Supervision for Weakly Supervised Semantic Segmentation
From Lifestyle Vlogs to Everyday Interactions
Cross-Domain Weakly-Supervised Object Detection Through Progressive Domain Adaptation
RotationNet: Joint Object Categorization and Pose Estimation Using Multiviews From Unsupervised Viewpoints
An End-to-End TextSpotter With Explicit Alignment and Attention
WILDTRACK: A Multi-Camera HD Dataset for Dense Unscripted Pedestrian Detection
Direct Shape Regression Networks for End-to-End Face Alignment
Natural and Effective Obfuscation by Head Inpainting
3D Semantic Trajectory Reconstruction From 3D Pixel Continuum
Optimizing Filter Size in Convolutional Neural Networks for Facial Action Unit Recognition
V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation From a Single Depth Map
Ring Loss: Convex Feature Normalization for Face Recognition
Adversarially Occluded Samples for Person Re-Identification
Classifier Learning With Prior Probabilities for Facial Action Unit Recognition
4DFAB: A Large Scale 4D Database for Facial Expression Analysis and Biometric Applications
Seeing Small Faces From Robust Anchor's Perspective
2D/3D Pose Estimation and Action Recognition Using Multitask Deep Learning
Dense 3D Regression for Hand Pose Estimation
Camera Style Adaptation for Person Re-Identification
PoseTrack: A Benchmark for Human Pose Estimation and Tracking
Exploit the Unknown Gradually: One-Shot Video-Based Person Re-Identification by Stepwise Learning
Pose-Robust Face Recognition via Deep Residual Equivariant Mapping
DecideNet: Counting Varying Density Crowds Through Attention Guided Detection and Density Estimation
LSTM Pose Machines
Disentangling Features in 3D Face Shapes for Joint Face Reconstruction and Recognition
Convolutional Sequence to Sequence Model for Human Dynamics
Gesture Recognition: Focus on the Hands
Crowd Counting via Adversarial Cross-Scale Consistency Pursuit
3D Human Pose Estimation in the Wild by Adversarial Learning
CosFace: Large Margin Cosine Loss for Deep Face Recognition
Encoding Crowd Interaction With Deep Neural Network for Pedestrian Trajectory Prediction
Mean-Variance Loss for Deep Age Estimation From a Face
Probabilistic Joint Face-Skull Modelling for Facial Reconstruction
Learning Latent Super-Events to Detect Multiple Activities in Videos
Temporal Hallucinating for Action Recognition With Few Still Images
Deep Progressive Reinforcement Learning for Skeleton-Based Action Recognition
Gaze Prediction in Dynamic 360° Immersive Videos
When Will You Do What? - Anticipating Temporal Occurrences of Activities
Fusing Crowd Density Maps and Visual Object Trackers for People Tracking in Crowd Scenes
Dual Attention Matching Network for Context-Aware Feature Sequence Based Person Re-Identification
Easy Identification From Better Constraints: Multi-Shot Person Re-Identification From Reference Constraints
Crowd Counting With Deep Negative Correlation Learning
Human Appearance Transfer
Domain Generalization With Adversarial Feature Learning
Pyramid Stereo Matching Network
Event-Based Vision Meets Deep Learning on Steering Prediction for Self-Driving Cars
Learning Answer Embeddings for Visual Question Answering
Good View Hunting: Learning Photo Composition From Dense View Pairs
CleanNet: Transfer Learning for Scalable Image Classifier Training With Label Noise
Independently Recurrent Neural Network (IndRNN): Building a Longer and Deeper RNN
Mix and Match Networks: Encoder-Decoder Alignment for Zero-Pair Image Translation
Structured Uncertainty Prediction Networks
Between-Class Learning for Image Classification
Adversarial Feature Augmentation for Unsupervised Domain Adaptation
Generative Image Inpainting With Contextual Attention
CSGNet: Neural Shape Parser for Constructive Solid Geometry
Conditional Image-to-Image Translation
Continuous Relaxation of MAP Inference: A Nonconvex Perspective
Feature Generating Networks for Zero-Shot Learning
Joint Optimization Framework for Learning With Noisy Labels
Convolutional Image Captioning
AON: Towards Arbitrarily-Oriented Text Recognition
Wrapped Gaussian Process Regression on Riemannian Manifolds
Geometry Guided Convolutional Neural Networks for Self-Supervised Video Representation Learning
DiverseNet: When One Right Answer Is Not Enough
Deep Face Detector Adaptation Without Negative Transfer or Catastrophic Forgetting
Analyzing Filters Toward Efficient ConvNet
Regularizing Deep Networks by Modeling and Predicting Label Structure
In-Place Activated BatchNorm for Memory-Optimized Training of DNNs
DVQA: Understanding Data Visualizations via Question Answering
DA-GAN: Instance-Level Image Translation by Deep Attention Generative Adversarial Networks
Unsupervised Learning of Depth and Ego-Motion From Monocular Video Using 3D Geometric Constraints
FOTS: Fast Oriented Text Spotting With a Unified Network
Mobile Video Object Detection With Temporally-Aware Feature Maps
Weakly Supervised Phrase Localization With Multi-Scale Anchored Transformer Network
Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking
Cross-Dataset Adaptation for Visual Question Answering
Globally Optimal Inlier Set Maximization for Atlanta Frame Estimation
End-to-End Convolutional Semantic Embeddings
Referring Image Segmentation via Recurrent Refinement Networks
Two Can Play This Game: Visual Dialog With Discriminative Question Generation and Answering
Generative Adversarial Learning Towards Fast Weakly Supervised Detection
A Deeper Look at Power Normalizations
Dimensionality's Blessing: Clustering Images by Underlying Distribution
Eliminating Background-Bias for Robust Person Re-Identification
Learning to Evaluate Image Captioning
Single-Shot Object Detection With Enriched Semantics
Low-Shot Learning With Imprinted Weights
Neural Motifs: Scene Graph Parsing With Global Context
Variational Autoencoders for Deforming 3D Mesh Models
Fast Monte-Carlo Localization on Aerial Vehicles Using Approximate Continuous Belief Representations
DeLS-3D: Deep Localization and Segmentation With a 3D Semantic Map
LiDAR-Video Driving Dataset: Learning Driving Policies Effectively
Logo Synthesis and Manipulation With Clustered Generative Adversarial Networks
Egocentric Basketball Motion Planning From a Single First-Person Image
Human-Centric Indoor Scene Synthesis Using Stochastic Grammar
Rotation-Sensitive Regression for Oriented Scene Text Detection
Separating Self-Expression and Visual Content in Hashtag Supervision
Distort-and-Recover: Color Enhancement Using Deep Reinforcement Learning
Im2Flow: Motion Hallucination From Static Images for Action Recognition
Finding "It": Weakly-Supervised Reference-Aware Visual Grounding in Instructional Videos
Actor and Action Video Segmentation From a Sentence
Egocentric Activity Recognition on a Budget
CNN in MRF: Video Object Segmentation via Inference in a CNN-Based Higher-Order Spatio-Temporal MRF
Action Sets: Weakly Supervised Action Segmentation Without Ordering Constraints
Low-Latency Video Semantic Segmentation
Fine-Grained Video Captioning for Sports Narrative
End-to-End Learning of Motion Representation for Video Understanding
Compressed Video Action Recognition
Features for Multi-Target Multi-Camera Tracking and Re-Identification
AVA: A Video Dataset of Spatio-Temporally Localized Atomic Visual Actions
Who's Better? Who's Best? Pairwise Deep Ranking for Skill Determination
MX-LSTM: Mixing Tracklets and Vislets to Jointly Forecast Trajectories and Head Poses
Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
Improved Fusion of Visual and Language Representations by Dense Symmetric Co-Attention for Visual Question Answering
FlipDial: A Generative Model for Two-Way Visual Dialogue
Are You Talking to Me? Reasoned Visual Dialog Generation Through Adversarial Learning
Visual Question Generation as Dual Task of Visual Question Answering
Unsupervised Textual Grounding: Linking Words to Image Concepts
Focal Visual-Text Attention for Visual Question Answering
SeGAN: Segmenting and Generating the Invisible
Cascade R-CNN: Delving Into High Quality Object Detection
Learning Semantic Concepts and Order for Image and Sentence Matching
Functional Map of the World
MegDet: A Large Mini-Batch Object Detector
Learning Globally Optimized Object Detector via Policy Gradient
Photographic Text-to-Image Synthesis With a Hierarchically-Nested Adversarial Network
Illuminant Spectra-Based Source Separation Using Flash Photography
Trapping Light for Time of Flight
The Perception-Distortion Tradeoff
Label Denoising Adversarial Network (LDAN) for Inverse Lighting of Faces
Optimal Structured Light à La Carte
Tracking Multiple Objects Outside the Line of Sight Using Speckle Imaging
Inferring Light Fields From Shadows
Modifying Non-Local Variations Across Multiple Views
Robust Video Content Alignment and Compensation for Rain Removal in a CNN Framework
SfSNet: Learning Shape, Reflectance and Illuminance of Faces `in the Wild'
Deep Photo Enhancer: Unpaired Learning for Image Enhancement From Photographs With GANs
LIME: Live Intrinsic Material Estimation
Learning to Detect Features in Texture Images
Learning to Extract a Video Sequence From a Single Motion-Blurred Image
Lose the Views: Limited Angle CT Reconstruction via Implicit Sinogram Completion
A Common Framework for Interactive Texture Transfer
AMNet: Memorability Estimation With Attention
Blind Predicting Similar Quality Map for Image Quality Assessment
Deep End-to-End Time-of-Flight Imaging
Aperture Supervision for Monocular Depth Estimation
Seeing Temporal Modulation of Lights From Standard Cameras
Statistical Tomography of Microscopic Life
Divide and Conquer for Full-Resolution Light Field Deblurring
Multispectral Image Intrinsic Decomposition via Subspace Constraint
Improving Color Reproduction Accuracy on Cameras
A Closer Look at Spatiotemporal Convolutions for Action Recognition
Inferring Shared Attention in Social Scene Videos
Making Convolutional Networks Recurrent for Visual Sequence Learning
Real-World Anomaly Detection in Surveillance Videos
Viewpoint-Aware Attentive Multi-View Inference for Vehicle Re-Identification
Efficient Video Object Segmentation via Network Modulation
Weakly-Supervised Action Segmentation With Iterative Soft Boundary Assignment
Depth-Aware Stereo Video Retargeting
Instance Embedding Transfer to Unsupervised Video Object Segmentation
Future Frame Prediction for Anomaly Detection â A New Baseline
Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?
Dynamic Video Segmentation Network
Recognize Actions by Disentangling Components of Dynamics
Motion-Appearance Co-Memory Networks for Video Question Answering
Learning to Understand Image Blur
Dense Decoder Shortcut Connections for Single-Pass Semantic Segmentation
Generative Adversarial Image Synthesis With Decision Tree Latent Controller
Learning a Discriminative Prior for Blind Image Deblurring
Frame-Recurrent Video Super-Resolution
Discovering Point Lights With Intensity Distance Fields
Video Rain Streak Removal by Multiscale Convolutional Sparse Coding
Stereoscopic Neural Style Transfer
Multi-Frame Quality Enhancement for Compressed Video
CNN Based Learning Using Reflection and Retinex Models for Intrinsic Image Decomposition
Image Restoration by Estimating Frequency Distribution of Local Patches
Latent RANSAC
Two-Stream Convolutional Networks for Dynamic Texture Synthesis
Towards Open-Set Identity Preserving Face Synthesis
A Revised Underwater Image Formation Model
Graph-Cut RANSAC
Temporal Deformable Residual Networks for Action Segmentation in Videos
Weakly Supervised Action Localization by Sparse Temporal Pooling Network
PoseFlow: A Deep Motion Representation for Understanding Human Behaviors in Videos
FFNet: Video Fast-Forwarding via Reinforcement Learning
Multi-Shot Pedestrian Re-Identification via Sequential Decision Making
Attend and Interact: Higher-Order Object Interactions for Video Understanding
Where and Why Are They Looking? Jointly Inferring Human Attention and Intentions in Complex Tasks
Fully Convolutional Adaptation Networks for Semantic Segmentation
Semantic Video Segmentation by Gated Recurrent Flow Propagation
Interpretable Video Captioning via Trajectory Structured Localization
Deep Hashing via Discrepancy Minimization
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
Zero-Shot Recognition via Semantic Embeddings and Knowledge Graphs
Referring Relationships
Improving Object Localization With Fitness NMS and Bounded IoU Loss
End-to-End Deep Kronecker-Product Matching for Person Re-Identification
Semantic Visual Localization
Objects as Context for Detecting Their Semantic Parts
End-to-End Weakly-Supervised Semantic Alignment
Dynamic Zoom-In Network for Fast Object Detection in Large Images
Learning Markov Clustering Networks for Scene Text Detection
Deep Reinforcement Learning of Region Proposal Networks for Object Detection
Beyond Holistic Object Recognition: Enriching Image Understanding With Part States
Discriminability Objective for Training Descriptive Captions
Visual Question Answering With Memory-Augmented Networks
Structure Inference Net: Object Detection Using Scene-Level Context and Instance-Level Relationships
Occluded Pedestrian Detection Through Guided Attention in CNNs
Reward Learning From Narrated Demonstrations
Weakly-Supervised Semantic Segmentation Network With Deep Seeded Region Growing
PoTion: Pose MoTion Representation for Action Recognition
Bilateral Ordinal Relevance Multi-Instance Regression for Facial Action Unit Intensity Estimation
Pulling Actions out of Context: Explicit Separation for Effective Combination
Dynamic Feature Learning for Partial Face Recognition
Exploiting Transitivity for Learning Person Re-Identification Models on a Budget
Deep Spatial Feature Reconstruction for Partial Person Re-Identification: Alignment-Free Approach
Every Smile Is Unique: Landmark-Guided Diverse Smile Generation
UV-GAN: Adversarial Facial UV Map Completion for Pose-Invariant Face Recognition
Cascaded Pyramid Network for Multi-Person Pose Estimation
A Face-to-Face Neural Conversation Model
End-to-End Recovery of Human Shape and Pose
Squeeze-and-Excitation Networks
Revisiting Salient Object Detection: Simultaneous Detection, Ranking, and Subitizing of Multiple Salient Objects
Context Encoding for Semantic Segmentation
Creating Capsule Wardrobes From Fashion Images
Webly Supervised Learning Meets Zero-Shot Learning: A Hybrid Approach for Fine-Grained Classification
Look, Imagine and Match: Improving Textual-Visual Cross-Modal Retrieval With Generative Models
Bidirectional Attentive Fusion With Context Gating for Dense Video Captioning
InLoc: Indoor Visual Localization With Dense Matching and View Synthesis
Towards High Performance Video Object Detection
Neural Baby Talk
Few-Shot Image Recognition by Predicting Parameters From Activations
Iterative Visual Reasoning Beyond Convolutions
Visual Question Reasoning on General Dependency Tree
CVM-Net: Cross-View Matching Network for Image-Based Ground-to-Aerial Geo-Localization
Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi-Supervised Semantic Segmentation
Low-Shot Learning From Imaginary Data
DoubleFusion: Real-Time Capture of Human Performances With Inner Body Shapes From a Single Depth Sensor
DensePose: Dense Human Pose Estimation in the Wild
Ordinal Depth Supervision for 3D Human Pose Estimation
Consensus Maximization for Semantic Region Correspondences
Robust Hough Transform Based 3D Reconstruction From Circular Light Fields
Alive Caricature From 2D to 3D
Nonlinear 3D Face Morphable Model
Through-Wall Human Pose Estimation Using Radio Signals
What Makes a Video a Video: Analyzing Temporal Information in Video Understanding Models and Datasets
Fast Video Object Segmentation by Reference-Guided Mask Propagation
NeuralNetwork-Viterbi: A Framework for Weakly Supervised Video Learning
Actor and Observer: Joint Modeling of First and Third-Person Videos
HSA-RNN: Hierarchical Structure-Adaptive RNN for Video Summarization
Fast and Accurate Online Video Object Segmentation via Tracking Parts
Now You Shake Me: Towards Automatic 4D Cinema
Viewpoint-Aware Video Summarization
Photometric Stereo in Participating Media Considering Shape-Dependent Forward Scatter
Direction-Aware Spatial Context Features for Shadow Detection
Discriminative Learning of Latent Features for Zero-Shot Recognition
Learning to Adapt Structured Output Space for Semantic Segmentation
Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
Jointly Localizing and Describing Events for Dense Video Captioning
Going From Image to Video Saliency: Augmenting Image Salience With Dynamic Attentional Push
M3: Multimodal Memory Modelling for Video Captioning
Emotional Attention: A Study of Image Sentiment and Visual Attention
A Low Power, High Throughput, Fully Event-Based Stereo System
VITON: An Image-Based Virtual Try-On Network
Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation
Multi-Content GAN for Few-Shot Font Style Transfer
Audio to Body Dynamics
Weakly Supervised Coupled Networks for Visual Sentiment Analysis
Future Person Localization in First-Person Videos
Preserving Semantic Relations for Zero-Shot Learning
Show Me a Story: Towards Coherent Neural Story Illustration
Reconstruction Network for Video Captioning
Fast Spectral Ranking for Similarity Search
Mining on Manifolds: Metric Learning Without Labels
PIXOR: Real-Time 3D Object Detection From Point Clouds
Leveraging Unlabeled Data for Crowd Counting by Learning to Rank
Zero-Shot Kernel Learning
Differential Attention for Visual Question Answering
Learning From Noisy Web Data With Category-Level Supervision
Toward Driving Scene Understanding: A Dataset for Learning Driver Behavior and Causal Reasoning
Learning Attribute Representations With Localization for Flexible Fashion Search
Bidirectional Retrieval Made Simple
Learning Multi-Instance Enriched Image Representations via Non-Greedy Ratio Maximization of the l1-Norm Distances
Learning Visual Knowledge Memory Networks for Visual Question Answering
Visual Grounding via Accumulated Attention
Beyond Trade-Off: Accelerate FCN-Based Face Detector With Higher Accuracy
PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning
Repulsion Loss: Detecting Pedestrians in a Crowd
Neural Sign Language Translation
Non-Local Neural Networks
LAMV: Learning to Align and Match Videos With Kernelized Temporal Layers
Optimizing Video Object Detection via a Scale-Time Lattice
Learning Compressible 360° Video Isomers
Attention Clusters: Purely Attention Based Local Feature Integration for Video Classification
What Have We Learned From Deep Representations for Action Recognition?
Controllable Video Generation With Sparse Trajectories
Representing and Learning High Dimensional Data With the Optimal Transport Map From a Probabilistic Viewpoint
CLIP-Q: Deep Network Compression Learning by In-Parallel Pruning-Quantization
Inference in Higher Order MRF-MAP Problems With Small and Large Cliques
ROAD: Reality Oriented Adaptation for Semantic Segmentation of Urban Scenes
Eye In-Painting With Exemplar Generative Adversarial Networks
ClcNet: Improving the Efficiency of Convolutional Neural Network Using Channel Local Convolutions
Towards Effective Low-Bitwidth Convolutional Neural Networks
Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks
Face Aging With Identity-Preserved Conditional Generative Adversarial Networks
Unsupervised Cross-Dataset Person Re-Identification by Transfer Learning of Spatial-Temporal Patterns
Feature Quantization for Defending Against Distortion of Images
Tagging Like Humans: Diverse and Distinct Image Annotation
Re-Weighted Adversarial Adaptation Network for Unsupervised Domain Adaptation
Inferring Semantic Layout for Hierarchical Text-to-Image Synthesis
Regularizing RNNs for Caption Generation by Reconstructing the Past With the Present
Unsupervised Domain Adaptation With Similarity Learning
Learning Deep Sketch Abstraction
Matching Adversarial Networks
SoS-RSC: A Sum-of-Squares Polynomial Approach to Robustifying Subspace Clustering Algorithms
Resource Aware Person Re-Identification Across Multiple Resolutions
Learning and Using the Arrow of Time
Neural Style Transfer via Meta Networks
People, Penguins and Petri Dishes: Adapting Object Counting Models to New Visual Domains and Object Types Without Forgetting
HydraNets: Specialized Dynamic Architectures for Efficient Inference
SketchMate: Deep Hashing for Million-Scale Human Sketch Retrieval
From Source to Target and Back: Symmetric Bi-Directional Adaptive GAN
OLÃ: Orthogonal Low-Rank Embedding - A Plug and Play Geometric Loss for Deep Learning
Efficient Parametrization of Multi-Domain Deep Neural Networks
Deep Density Clustering of Unconstrained Faces
Geometric Multi-Model Fitting With a Convex Relaxation Algorithm
Fast and Robust Estimation for Unit-Norm Constrained Linear Fitting Problems
Importance Weighted Adversarial Nets for Partial Domain Adaptation
Efficient Subpixel Refinement With Symbolic Linear Predictors
Scale-Recurrent Network for Deep Image Deblurring
DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks
A2-RL: Aesthetics Aware Reinforcement Learning for Image Cropping
Single Image Dehazing via Conditional Generative Adversarial Network
On the Duality Between Retinex and Image Dehazing
Arbitrary Style Transfer With Deep Feature Reshuffle
Nonlocal Low-Rank Tensor Factor Analysis for Image Restoration
Avatar-Net: Multi-Scale Zero-Shot Style Transfer by Feature Decoration
Missing Slice Recovery for Tensors Using a Low-Rank Model in Embedded Space
Deep Semantic Face Deblurring
GraphBit: Bitwise Interaction Mining via Deep Reinforcement Learning
Recurrent Saliency Transformation Network: Incorporating Multi-Stage Visual Cues for Small Organ Segmentation
Thoracic Disease Identification and Localization With Limited Supervision
Quantization of Fully Convolutional Networks for Accurate Biomedical Image Segmentation