ICCV 2017 paper

参考链接

• ICCV 2017 open access

Paperlist

Globally-Optimal Inlier Set Maximisation for Simultaneous Camera Pose and Feature Correspondence
Robust Pseudo Random Fields for Light-Field Stereo Matching
A Lightweight Approach for On-The-Fly Reflectance Estimation
Distributed Very Large Scale Bundle Adjustment by Global Camera Consensus
Practical Projective Structure From Motion (P2SfM)
Anticipating Daily Intention Using On-Wrist Motion Triggered Sensing
Rethinking Reprojection: Closing the Loop for Pose-Aware Shape Reconstruction From a Single Image
End-To-End Learning of Geometry and Context for Deep Stereo Regression
Using Sparse Elimination for Solving Minimal Problems in Computer Vision
High-Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inference
Temporal Tessellation: A Unified Approach for Video Analysis
Learning Policies for Adaptive Tracking With Deep Feature Cascades
Temporal Shape Super-Resolution by Intra-Frame Motion Encoding Using High-Fps Structured Light
Real-Time Monocular Pose Estimation of 3D Objects Using Temporally Consistent Local Color Histograms
CAD Priors for Accurate and Flexible Instance Reconstruction
Colored Point Cloud Registration Revisited
Learning Compact Geometric Features
Joint Layout Estimation and Global Multi-View Registration for Indoor Reconstruction
A Geometric Framework for Statistical Analysis of Trajectories With Distinct Temporal Spans
An Optimal Transportation Based Univariate Neuroimaging Index
S3FD: Single Shot Scale-Invariant Face Detector
Amulet: Aggregating Multi-Level Convolutional Features for Salient Object Detection
Learning Uncertain Convolutional Features for Accurate Saliency Detection
Zero-Order Reverse Filtering
Learning Blind Motion Deblurring
Joint Adaptive Sparsity and Low-Rankness on the Fly: An Online Tensor Reconstruction Scheme for Video Denoising
Learning to Super-Resolve Blurry Face and Text Images
Video Frame Interpolation via Adaptive Separable Convolution
Deep Occlusion Reasoning for Multi-Camera Multi-Target Detection
Encouraging LSTMs to Anticipate Actions Very Early
PathTrack: Fast Trajectory Annotation With Path Supervision
Tracking the Untrackable: Learning to Track Multiple Cues With Long-Term Dependencies
MirrorFlow: Exploiting Symmetries in Joint Optical Flow and Occlusion Estimation
Tracking as Online Decision-Making: Learning a Policy From Streaming Videos With Reinforcement Learning
Non-Convex Rank/Sparsity Regularization and Local Minima
A Revisit of Sparse Coding Based Anomaly Detection in Stacked RNN Framework
HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis
No Fuss Distance Metric Learning Using Proxies
Benchmarking and Error Diagnosis in Multi-Instance Pose Estimation
Orientation Invariant Feature Embedding and Spatial Temporal Regularization for Vehicle Re-Identification
Fashion Forward: Forecasting Visual Style in Fashion
Towards 3D Human Pose Estimation in the Wild: A Weakly-Supervised Approach
Flow-Guided Feature Aggregation for Video Object Detection
Reasoning About Fine-Grained Attribute Phrases Using Reference Games
DeNet: Scalable Real-Time Object Detection With Directed Sparse Sampling
MIHash: Online Hashing With Mutual Information
SafetyNet: Detecting and Rejecting Adversarial Examples Robustly
Recurrent Models for Situation Recognition
Multi-Label Image Recognition by Recurrently Discovering Attentional Regions
Deep Determinantal Point Process for Large-Scale Multi-Label Classification
Visual Semantic Planning Using Deep Successor Representations
Neural Person Search Machines
DualNet: Learn Complementary Features for Image Recognition
Higher-Order Integration of Hierarchical Convolutional Activations for Fine-Grained Visual Categorization
Show, Adapt and Tell: Adversarial Training of Cross-Domain Image Captioner
Attribute Recognition by Joint Recurrent Learning of Context and Correlation
VegFru: A Domain-Specific Dataset for Fine-Grained Visual Categorization
Increasing CNN Robustness to Occlusions by Reducing Filter Support
Exploiting Multi-Grain Ranking Constraints for Precisely Searching Visually-Similar Vehicles
Recurrent Scale Approximation for Object Detection in CNN
Embedding 3D Geometric Features for Rigid Object Part Segmentation
Towards Context-Aware Interaction Recognition for Visual Relationship Detection
When Unsupervised Domain Adaptation Meets Tensor Representations
Look, Listen and Learn
Grad-CAM: Visual Explanations From Deep Networks via Gradient-Based Localization
Image-Based Localization Using LSTMs for Structured Feature Correlation
Personalized Image Aesthetics
Predicting Deeper Into the Future of Semantic Segmentation
Coordinating Filters for Faster Deep Neural Networks
Unsupervised Representation Learning by Sorting Sequences
A Read-Write Memory Network for Movie Story Understanding
SegFlow: Joint Learning for Video Object Segmentation and Optical Flow
Unsupervised Action Discovery and Localization in Videos
Dense-Captioning Events in Videos
Learning Long-Term Dependencies for Action Recognition With a Biologically-Inspired Deep Network
Compressive Quantization for Fast Object Instance Search in Videos
Complex Event Detection by Identifying Reliable Shots From Untrimmed Videos
Deep Direct Regression for Multi-Oriented Scene Text Detection
Open Set Domain Adaptation
Deformable Convolutional Networks
Ensemble Diffusion for Retrieval
FoveaNet: Perspective-Aware Urban Scene Parsing
Beyond Planar Symmetry: Modeling Human Perception of Reflection and Rotation Symmetries in the Wild
Learning to Reason: End-To-End Module Networks for Visual Question Answering
Hard-Aware Deeply Cascaded Embedding
Query-Guided Regression Network With Context Policy for Phrase Grounding
SUBIC: A Supervised, Structured Binary Code for Image Search
Revisiting Unreasonable Effectiveness of Data in Deep Learning Era
A Generative Model of People in Clothing
Escape From Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Models
Improved Image Captioning via Policy Gradient Optimization of SPIDEr
Rolling Shutter Correction in Manhattan World
Local-To-Global Point Cloud Registration Using a Dictionary of Viewpoint Descriptors
3D-PRNN: Generating Shape Primitives With Recurrent Neural Networks
BodyFusion: Real-Time Capture of Human Motion and Surface Geometry Using a Single Depth Camera
Quasiconvex Plane Sweep for Triangulation With Outliers
"Maximizing Rigidity" Revisited: A Convex Programming Approach for Generic 3D Shape Reconstruction From Multiple Perspective Views
Surface Registration via Foliation
Rolling-Shutter-Aware Differential SfM and Image Rectification
Corner-Based Geometric Calibration of Multi-Focus Plenoptic Cameras
Focal Track: Depth and Accommodation With Oscillating Lens Deformation
Reconfiguring the Imaging Pipeline for Computer Vision
Catadioptric HyperSpectral Light Field Imaging
Cross-View Asymmetric Metric Learning for Unsupervised Person Re-Identification
Real Time Eye Gaze Tracking With 3D Deformable Eye-Face Model
Ensemble Deep Learning for Skeleton-Based Action Recognition Using Temporal Sliding LSTM Networks
How Far Are We From Solving the 2D & 3D Face Alignment Problem? (And a Dataset of 230,000 3D Facial Landmarks)
Large Pose 3D Face Reconstruction From a Single Image via Direct Volumetric CNN Regression
RankIQA: Learning From Rankings for No-Reference Image Quality Assessment
Look, Perceive and Segment: Finding the Salient Objects in Images via Two-Stream Fixation-Semantic CNNs
Delving Into Salient Object Subitizing and Detection
Learning Discriminative Data Fitting Functions for Blind Image Deblurring
Video Deblurring via Semantic Segmentation and Pixel-Wise Non-Linear Kernel
On-Demand Learning for Deep Image Restoration
Multi-Channel Weighted Nuclear Norm Minimization for Real Color Image Denoising
Coherent Online Video Style Transfer
SHaPE: A Novel Graph Theoretic Algorithm for Making Consensus-Based Decisions in Person Re-Identification Systems
Need for Speed: A Benchmark for Higher Frame Rate Object Tracking
Learning Background-Aware Correlation Filters for Visual Tracking
Robust Object Tracking Based on Temporal and Spatial Deep Networks
Real-Time Hand Tracking Under Occlusion From an Egocentric RGB-D Sensor
Predicting Human Activities Using Stochastic Grammar
ProbFlow: Joint Optical Flow and Uncertainty Estimation
Sublabel-Accurate Discretization of Nonconvex Free-Discontinuity Problems
DeepContext: Context-Encoding Neural Pathways for 3D Holistic Scene Understanding
BAM! The Behance Artistic Media Dataset for Recognition Beyond Photography
Adversarial PoseNet: A Structure-Aware Convolutional Network for Human Pose Estimation
An Empirical Study of Language CNN for Image Captioning
Attributes2Classname: A Discriminative Model for Attribute-Based Unsupervised Zero-Shot Learning
Areas of Attention for Image Captioning
Generative Modeling of Audible Shapes for Object Perception
Scene Graph Generation From Objects, Phrases and Region Captions
Recurrent Multimodal Interaction for Referring Image Segmentation
Learning Feature Pyramids for Human Pose Estimation
Structured Attentions for Visual Question Answering
Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection
Cascaded Feature Network for Semantic Segmentation of RGB-D Images
Encoder Based Lifelong Learning
Transitive Invariance for Self-Supervised Visual Representation Learning
Weakly Supervised Learning of Deep Metrics for Stereo Reconstruction
Fine-Grained Recognition in the Wild: A Multi-Task Domain Adaptation Approach
SORT: Second-Order Response Transform for Visual Recognition
Adversarial Examples for Semantic Segmentation and Object Detection
Genetic CNN
Channel Pruning for Accelerating Very Deep Neural Networks
Infinite Latent Feature Selection: A Probabilistic Latent Graph-Based Ranking Approach
Video Fill in the Blank Using LR/RL LSTMs With Spatial-Temporal Attentions
Primary Video Object Segmentation via Complementary CNNs and Neighborhood Reversible Flow
Attentive Semantic Video Generation Using Captions
Following Gaze in Video
Adaptive RNN Tree for Large-Scale Human Action Recognition
Spatio-Temporal Person Retrieval via Natural Language Queries
Automatic Spatially-Aware Fashion Concept Discovery
ChromaTag: A Colored Marker and Fast Detection Algorithm
Adversarial Image Perturbation for Privacy Protection -- A Game Theory Perspective
WeText: Scene Text Detection Under Weak Supervision
Arbitrary Style Transfer in Real-Time With Adaptive Instance Normalization
Photographic Image Synthesis With Cascaded Refinement Networks
SSD-6D: Making RGB-Based 3D Detection and 6D Pose Estimation Great Again
Unsupervised Creation of Parameterized Avatars
Learning for Active 3D Mapping
Toward Perceptually-Consistent Stereo: A Scanline Study
Surface Normals in the Wild
Unsupervised Learning of Stereo Matching
Unrestricted Facial Geometry Reconstruction Using Image-To-Image Translation
Learned Multi-Patch Similarity
Click Here: Human-Localized Keypoints as Guidance for Viewpoint Estimation
Unsupervised Adaptation for Deep Stereo
Composite Focus Measure for High Quality Depth Maps
Reconstruction-Based Disentanglement for Pose-Invariant Face Recognition
Recurrent 3D-2D Dual Learning for Large-Pose Facial Landmark Detection
Anchored Regression Networks Applied to Age Estimation and Super Resolution
Infant Footprint Recognition
Self-Paced Kernel Estimation for Robust Blind Image Deblurring
Super-Trajectory for Video Segmentation
Be Your Own Prada: Fashion Synthesis With Structural Coherence
Wavelet-SRNet: A Wavelet-Based CNN for Multi-Scale Face Super Resolution
Learning Gaze Transitions From Depth to Improve Video Saliency Estimation
Joint Convolutional Analysis and Synthesis Sparse Representation for Single Image Layer Separation
Modelling the Scene Dependent Imaging in Cameras With a Deep Neural Network
Transformed Low-Rank Model for Line Pattern Noise Removal
Weakly Supervised Manifold Learning for Dense Semantic Object Correspondence
Dual Motion GAN for Future-Flow Embedded Video Prediction
Online Robust Image Alignment via Subspace Learning From Gradient Orientations
Learning Dynamic Siamese Network for Visual Object Tracking
High Order Tensor Formulation for Convolutional Sparse Coding
Learning Proximal Operators: Using Denoising Networks for Regularizing Inverse Imaging Problems
ScaleNet: Guiding Object Proposal Generation in Supermarkets and Beyond
Temporal Dynamic Graph LSTM for Action-Driven Video Object Detection
VQS: Linking Segmentations to Questions and Answers for Supervised Attention in VQA and Question-Focused Semantic Segmentation
Multi-Modal Factorized Bilinear Pooling With Co-Attention Learning for Visual Question Answering
SCNet: Learning Semantic Correspondence
Soft Proposal Networks for Weakly Supervised Object Localization
Class Rectification Hard Mining for Imbalanced Deep Learning
Generating High-Quality Crowd Density Maps Using Contextual Pyramid CNNs
See the Glass Half Full: Reasoning About Liquid Containers, Their Volume and Content
Hierarchical Multimodal LSTM for Dense Visual-Semantic Embedding
Identity-Aware Textual-Visual Matching With Latent Co-Attention
Learning Deep Neural Networks for Vehicle Re-ID With Visual-Spatio-Temporal Path Proposals
Learning From Noisy Labels With Distillation
DSOD: Learning Deeply Supervised Object Detectors From Scratch
Phrase Localization and Visual Relationship Detection With Comprehensive Image-Language Cues
Chained Cascade Network for Object Detection
VPGNet: Vanishing Point Guided Network for Lane and Road Marking Detection and Recognition
Unsupervised Learning of Important Objects From First-Person Videos
An Analysis of Visual Question Answering Algorithms
Visual Relationship Detection With Internal and External Linguistic Knowledge Distillation
A Two Stream Siamese Convolutional Neural Network for Person Re-Identification
No More Discrimination: Cross City Adaptation of Road Scene Segmenters
Open Vocabulary Scene Parsing
Learned Watershed: End-To-End Learning of Seeded Segmentation
Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes
Scale-Adaptive Convolutions for Scene Parsing
Privacy-Preserving Visual Learning Using Doubly Permuted Homomorphic Encryption
Multi-Task Self-Supervised Visual Learning
A Self-Balanced Min-Cut Algorithm for Image Clustering
Is Second-Order Information Helpful for Large-Scale Visual Recognition?
Factorized Bilinear Models for Image Recognition
Octree Generating Networks: Efficient Convolutional Architectures for High-Resolution 3D Outputs
Truncating Wide Networks Using Binary Tree Architectures
Bringing Background Into the Foreground: Making All Classes Equal in Weakly-Supervised Video Semantic Segmentation
View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition From Skeleton Data
Joint Discovery of Object States and Manipulation Actions
What Actions Are Needed for Understanding Human Actions in Videos?
Lattice Long Short-Term Memory for Human Action Recognition
Common Action Discovery and Localization in Unconstrained Videos
Pixel-Level Matching for Video Object Segmentation Using Convolutional Neural Networks
Am I a Baller? Basketball Performance Assessment From First-Person Videos
Deep Cropping via Attention Box Prediction and Aesthetics Assessment
Raster-To-Vector: Revisiting Floorplan Transformation
Deep TextSpotter: An End-To-End Trainable Scene Text Localization and Recognition Framework
Playing for Benchmarks
Unpaired Image-To-Image Translation Using Cycle-Consistent Adversarial Networks
GANs for Biological Image Synthesis
Learning to Synthesize a 4D RGBD Light Field From a Single Image
Neural EPI-Volume Networks for Shape From Light Field
Material Editing Using a Physically Based Rendering Network
Turning Corners Into Cameras: Principles and Methods
Linear Differential Constraints for Photo-Polarimetric Height Estimation
Polynomial Solvers for Saturated Ideals
Shape Inpainting Using 3D Generative Adversarial Network and Recurrent Convolutional Networks
SurfaceNet: An End-To-End 3D Neural Network for Multiview Stereopsis
Making Minimal Solvers for Absolute Pose Estimation Compact and Robust
3D Surface Detail Enhancement From a Single Normal Map
RMPE: Regional Multi-Person Pose Estimation
 Online Video Object Detection Using Association LSTM
PolyFit: Polygonal Surface Reconstruction From Point Clouds
Progressive Large Scale-Invariant Image Matching in Scale Space
Efficient Global 2D-3D Matching for Camera Localization in a Large-Scale 3D Map
Multi-View Non-Rigid Refinement and Normal Selection for High Quality 3D Reconstruction
Multi-Stage Multi-Recursive-Input Fully Convolutional Networks for Neuronal Boundary Detection
Depth and Image Restoration From Light Field in a Scattering Medium
Video Reflection Removal Through Spatio-Temporal Optimization
Efficient Online Local Metric Adaptation via Negative Samples for Person Re-Identification
Stepwise Metric Promotion for Unsupervised Video Person Re-Identification
Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesis
Group Re-Identification via Unsupervised Transfer of Sparse Features Encoding
Visual Transformation Aided Contrastive Learning for Video-Based Kinship Verification
Decoder Network Over Lightweight Reconstructed Feature for Fast Semantic Style Transfer
Blind Image Deblurring With Outlier Handling
Paying Attention to Descriptions Generated by Image Captioning Models
Fast Image Processing With Fully-Convolutional Networks
Robust Video Super-Resolution With Learned Temporal Dynamics
Should We Encode Rain Streaks in Video as Deterministic or Stochastic?
Joint Bi-Layer Optimization for Single-Image Rain Streak Removal
Low-Dimensionality Calibration Through Local Anisotropic Scaling for Robust Hand Model Personalization
Non-Markovian Globally Consistent Multi-Object Tracking
CREST: Convolutional Residual Learning for Visual Tracking
Volumetric Flow Estimation for Incompressible Fluids Using the Stationary Stokes Equations
Bounding Boxes, Segmentations and Object Coordinates: How Important Is Recognition for 3D Scene Flow Estimation in Autonomous Driving Scenarios?
Performance Guaranteed Network Acceleration via High-Order Residual Quantization
Deep Metric Learning With Angular Loss
Compositional Human Pose Regression
MUTAN: Multimodal Tucker Fusion for Visual Question Answering
Revisiting IM2GPS in the Deep Learning Era
Scene Parsing With Global Context Embedding
A Simple yet Effective Baseline for 3D Human Pose Estimation
Dual-Glance Model for Deciphering Social Relationships
Sketching With Style: Visual Search With Sketches and Aesthetic Context
Point Set Registration With Global-Local Correspondence and Transformation Estimation
SceneNet RGB-D: Can 5M Synthetic Images Beat Generic ImageNet Pre-Training on Indoor Segmentation?
A Unified Model for Near and Remote Sensing
Directionally Convolutional Networks for 3D Shape Segmentation
AMAT: Medial Axis Transform for Natural Images
Deep Dual Learning for Semantic Image Segmentation
Regional Interactive Image Segmentation Networks
Learning Efficient Convolutional Networks Through Network Slimming
CVAE-GAN: Fine-Grained Image Generation Through Asymmetric Training
Universal Adversarial Perturbations Against Semantic Image Segmentation
Associative Domain Adaptation
Introspective Neural Networks for Generative Modeling
Towards a Unified Compositional Model for Visual Pattern Modeling
Least Squares Generative Adversarial Networks
Centered Weight Normalization in Accelerating Training of Deep Neural Networks
Deep Growing Learning
Smart Mining for Deep Metric Learning
Temporal Generative Adversarial Nets With Singular Value Clipping
Sampling Matters in Deep Embedding Learning
DualGAN: Unsupervised Dual Learning for Image-To-Image Translation
Learning View-Invariant Features for Person Identification in Temporally Synchronized Videos Taken by Wearable Cameras
MarioQA: Answering Questions by Watching Gameplay Videos
SBGAR: Semantics Based Group Activity Recognition
Trespassing the Boundaries: Labeling Temporal Bounds for Object Interactions in Egocentric Video
Unmasking the Abnormal Events in Video
Chained Multi-Stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection
Temporal Action Detection With Structured Segment Networks
Jointly Recognizing Object Fluents and Tasks in Egocentric Videos
Transferring Objects: Joint Inference of Container and Human Pose
Interpretable Learning for Self-Driving Cars by Visualizing Causal Attention
Learning Cooperative Visual Dialog Agents With Deep Reinforcement Learning
Mask R-CNN
Towards Diverse and Natural Image Descriptions via a Conditional GAN
Focal Loss for Dense Object Detection
Inferring and Executing Programs for Visual Reasoning
Visual Forecasting by Imitating Dynamics in Natural Sequences
TorontoCity: Seeing the World With a Million Eyes
Low-Shot Visual Recognition by Shrinking and Hallucinating Features
A Coarse-Fine Network for Keypoint Localization
Detect to Track and Track to Detect
Single Shot Text Detector With Regional Attention
SubUNets: End-To-End Hand Shape and Continuous Sign Language Recognition
A Spatiotemporal Oriented Energy Network for Dynamic Texture Recognition
Probabilistic Structure From Motion With Objects (PSfMO)
A 3D Morphable Model of Craniofacial Shape and Texture Variation
Multi-View Dynamic Shape Refinement Using Local Temporal Integration
Learning Hand Articulations by Hallucinating Heat Distribution
Intrinsic3D: High-Quality 3D Reconstruction by Joint Appearance and Geometry Optimization With Spatially-Varying Lighting
Robust Hand Pose Estimation During the Interaction With an Unknown Object
Detailed Surface Geometry and Albedo Recovery From RGB-D Video Under Natural Illumination
Monocular Free-Head 3D Gaze Tracking With Deep Learning and Geometry Constraints
Filter Selection for Hyperspectral Estimation
A Microfacet-Based Reflectance Model for Photometric Stereo With Highly Specular Surfaces
Detecting Faces Using Inside Cascaded Contextual CNN
A Novel Space-Time Representation on the Positive Semidefinite Cone for Facial Expression Recognition
DeepCoder: Semi-Parametric Variational Autoencoders for Automatic Facial Action Coding
Pose-Invariant Face Alignment With a Single CNN
Unsupervised Domain Adaptation for Face Recognition in Unlabeled Videos
Deeply-Learned Part-Aligned Representations for Person Re-Identification
Semantic Line Detection and Its Applications
A Generic Deep Architecture for Single Image Reflection Removal and Image Smoothing
Revisiting Cross-Channel Information Transfer for Chromatic Aberration Correction
High-Quality Correspondence and Segmentation Estimation for Dual-Lens Smart-Phone Portraits
Learning Visual Attention to Identify People With Autism Spectrum Disorder
DSLR-Quality Photos on Mobile Devices With Deep Convolutional Networks
Non-Uniform Blind Deblurring by Reblurring
Misalignment-Robust Joint Filter for Cross-Modal Image Pairs
Low-Rank Tensor Completion: A Pseudo-Bayesian Learning Approach
DeepCD: Learning Deep Complementary Descriptors for Patch Representations
Beyond Standard Benchmarks: Parameterizing Performance Evaluation in Visual Object Tracking
The Pose Knows: Video Forecasting by Generating Pose Futures
What Will Happen Next? Forecasting Player Moves in Sports Videos
Robust Kronecker-Decomposable Component Analysis for Low-Rank Modeling
Recurrent Topic-Transition GAN for Visual Paragraph Generation
A Two-Streamed Network for Estimating Fine-Scaled Depth Maps From Single RGB Images
Weakly Supervised Object Localization Using Things and Stuff Transfer
Single Image Action Recognition Using Semantic Body Part Actions
Incremental Learning of Object Detectors Without Catastrophic Forgetting
Generative Adversarial Networks Conditioned by Brain Signals
Learning to Disambiguate by Asking Discriminative Questions
Interpretable Explanations of Black Boxes by Meaningful Perturbation
DeepRoadMapper: Extracting Road Topology From Aerial Images
Monocular 3D Human Pose Estimation by Predicting Depth on Joints
Large-Scale Image Retrieval With Attentive Deep Local Features
Deep Globally Constrained MRFs for Human Pose Estimation
Predicting Visual Exemplars of Unseen Classes for Zero-Shot Learning
Multi-Label Learning of Part Detectors for Heavily Occluded Pedestrian Detection
SGN: Sequential Grouping Networks for Instance Segmentation
Adaptive Feeding: Achieving Fast and Accurate Detections by Adaptively Combining Object Detectors
Aesthetic Critiques Generation for Photos
Hide-And-Seek: Forcing a Network to Be Meticulous for Weakly-Supervised Object and Action Localization
Two-Phase Learning for Weakly Supervised Object Localization
Curriculum Dropout
Predictor Combination at Test Time
Guided Perturbations: Self-Corrective Behavior in Convolutional Neural Networks
Learning Robust Visual-Semantic Embeddings
PUnDA: Probabilistic Unsupervised Domain Adaptation for Knowledge Transfer Across Visual Categories
Learning in an Uncertain World: Representing Ambiguity Through Multiple Hypotheses
CDTS: Collaborative Detection, Tracking, and Segmentation for Online Multiple Object Segmentation in Videos
Temporal Superpixels Based on Proximity-Weighted Patch Matching
Joint Detection and Recounting of Abnormal Events by Learning Deep Generic Knowledge
TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals
Online Real-Time Multiple Spatiotemporal Action Localisation and Prediction
Leveraging Weak Semantic Relevance for Complex Video Event Classification
Weakly Supervised Summarization of Web Videos
FCN-rLSTM: Deep Spatio-Temporal Neural Networks for Vehicle Counting in City Cameras
Fast Face-Swap Using Convolutional Neural Networks
Towards a Visual Privacy Advisor: Understanding and Predicting Privacy Risks in Images
First-Person Activity Forecasting With Online Inverse Reinforcement Learning
Binarized Convolutional Landmark Localizers for Human Pose Estimation and Face Alignment With Limited Resources
MoFA: Model-Based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstruction
RPAN: An End-To-End Recurrent Pose-Attention Network for Action Recognition in Videos
Temporal Non-Volume Preserving Approach to Facial Age-Progression and Age-Invariant Face Recognition
Attribute-Enhanced Face Recognition With Neural Tensor Fusion Networks
Unlabeled Samples Generated by GAN Improve the Person Re-Identification Baseline in Vitro
Egocentric Gesture Recognition Using Recurrent 3D Convolutional Neural Networks With Spatiotemporal Transformer Modules
Recursive Spatial Transformer (ReST) for Alignment-Free Face Recognition
Learning Discriminative Aggregation Network for Video-Based Face Recognition
Synergy Between Face Alignment and Tracking via Discriminative Global Consensus Optimization
SVDNet for Pedestrian Retrieval
Towards More Accurate Iris Recognition Using Deeply Learned Spatially Corresponding Features
Semantically Informed Multiview Surface Refinement
BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects Without Using Depth
Modeling Urban Scenes From Pointclouds
Parameter-Free Lens Distortion Calibration of Central Cameras
Pose Guided RGBD Feature Learning for 3D Object Pose Estimation
Efficient Global Illumination for Morphable Models
Low Compute and Fully Parallel Computer Vision With HashMatch
Dense Non-Rigid Structure-From-Motion and Shading With Unknown Albedos
From Point Clouds to Mesh Using Regression
Stereo DSO: Large-Scale Direct Sparse Visual Odometry With Stereo Cameras
Space-Time Localization and Mapping
Benchmarking Single-Image Reflection Removal Algorithms
Attention-Aware Deep Reinforcement Learning for Video Face Recognition
Learning to Fuse 2D and 3D Image Cues for Monocular Body Pose Estimation
Deep Facial Action Unit Recognition From Partially Labeled Data
Pose-Driven Deep Convolutional Model for Person Re-Identification
Recognition of Action Units in the Wild With Deep Nets and a New Global-Local Loss
Faster Than Real-Time Facial Alignment: A 3D Spatial Transformer Network Approach in Unconstrained Poses
Towards Large-Pose Face Frontalization in the Wild
A Joint Intrinsic-Extrinsic Prior Model for Retinex
Going Unconstrained With Rolling Shutter Deblurring
A Stagewise Refinement Model for Detecting Salient Objects in Images
From Square Pieces to Brick Walls: The Next Challenge in Solving Jigsaw Puzzles
Online Video Deblurring via Dynamic Temporal Blending Network
Supervision by Fusion: Towards Unsupervised Learning of Deep Salient Object Detector
Fast Multi-Image Matching via Density-Based Clustering
Characterizing and Improving Stability in Neural Style Transfer
Cross-Modal Deep Variational Hashing
Spatial Memory for Context Reasoning in Object Detection
Deep Binaries: Encoding Semantic-Rich Cues for Efficient Textual-Visual Cross Retrieval
Learning a Recurrent Residual Fusion Network for Multimodal Matching
Rotational Subgroup Voting and Pose Clustering for Robust 3D Object Recognition
CoupleNet: Coupling Global Structure With Local Parts for Object Detection
Speaking the Same Language: Matching Machine to Human Captions by Adversarial Training
Drone-Based Object Counting by Spatially Regularized Regional Proposal Network
BlitzNet: A Real-Time Deep Network for Scene Understanding
Joint Learning of Object and Action Detectors
Situation Recognition With Graph Neural Networks
Learning Visual N-Grams From Web Data
Attention-Based Multimodal Fusion for Video Description
Learning the Latent "Look": Unsupervised Discovery of a Style-Coherent Embedding From Fashion Images
Aligned Image-Word Representations Improve Inductive Transfer Across Vision-Language Tasks
Learning Discriminative Latent Attributes for Zero-Shot Classification
PPR-FCN: Weakly Supervised Visual Relation Detection via Parallel Pairwise R-FCN
Higher-Order Minimum Cost Lifted Multicuts for Motion Segmentation
Deep Free-Form Deformation Network for Object-Mask Registration
Region-Based Correspondence Between 3D Shapes via Spatially Smooth Biclustering
Learning Discriminative ab-Divergences for Positive Definite Matrices
Consensus Convolutional Sparse Coding
Domain-Adaptive Deep Network Compression
Self-Supervised Learning of Pose Embeddings From Spatiotemporal Relations in Videos
Approximate Grassmannian Intersections: Subspace-Valued Subspace Learning
Side Information in Robust Principal Component Analysis: Algorithms and Applications
Summarization and Classification of Wearable Camera Streams by Learning the Distributions Over Deep Features of Out-Of-Sample Image Sequences
Unsupervised Learning From Video to Detect Foreground Objects in Single Images
Supplementary Meta-Learning: Towards a Dynamic Model for Deep Neural Networks
Adversarial Inverse Graphics Networks: Learning 2D-To-3D Lifting and Image-To-Image Translation From Unpaired Supervision
Active Learning for Human Pose Estimation
Interleaved Group Convolutions
Learning-Based Cloth Material Recovery From Video
Unsupervised Video Understanding by Reconciliation of Posture Similarities
Action Tubelet Detector for Spatio-Temporal Action Localization
AMTnet: Action-Micro-Tube Regression by End-To-End Trainable Deep Architecture
Constrained Convolutional Sparse Coding for Parametric Based Reconstruction of Line Drawings
Neural Ctrl-F: Segmentation-Free Query-By-String Word Spotting in Handwritten Manuscript Collections
Spatial-Aware Object Embeddings for Zero-Shot Localization and Classification of Actions
Semantic Video CNNs Through Representation Warping
Video Frame Synthesis Using Deep Voxel Flow
Detail-Revealing Deep Video Super-Resolution
Learning Video Object Segmentation With Visual Memory
EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis
Makeup-Go: Blind Reversion of Portrait Edit
Shadow Detection With Conditional Generative Adversarial Networks
Learning High Dynamic Range From Outdoor Panoramas
DCTM: Discrete-Continuous Transformation Matching for Semantic Flow
MemNet: A Persistent Memory Network for Image Restoration
Structure-Measure: A New Way to Evaluate Foreground Maps
Weakly- and Self-Supervised Learning for Content-Aware Deep Image Retargeting
Practical and Efficient Multi-View Matching
Unrolled Memory Inner-Products: An Abstract GPU Operator for Efficient Vision-Related Computations
Learning to Push the Limits of Efficient FFT-Based Image Deconvolution
Learning Spread-Out Local Feature Descriptors
Visual Odometry for Pixel Processor Arrays
Joint Estimation of Camera Pose, Depth, Deblurring, and Super-Resolution From a Blurred Image Sequence
2D-Driven 3D Object Detection in RGB-D Images
Ray Space Features for Plenoptic Structure-From-Motion
Depth Estimation Using Structured Light Flow -- Analysis of Projected Pattern Flow on an Object's Surface
Monocular Dense 3D Reconstruction of a Complex Dynamic Scene From Two Perspective Frames
Optimal Transformation Estimation With Semantic Cues
Dynamics Enhanced Multi-Camera Motion Segmentation From Unsynchronized Videos
Taking the Scenic Route to 3D: Optimising Reconstruction From Moving Cameras
FLaME: Fast Lightweight Mesh Estimation Using Variational Smoothing on Delaunay Graphs
Efficient Algorithms for Moral Lineage Tracing
From RGB to Spectrum for Natural Scenes via Manifold-Based Mapping
DeepFuse: A Deep Unsupervised Approach for Exposure Fusion With Extreme Exposure Image Pairs
Learning Dense Facial Correspondences in Unconstrained Images
Jointly Attentive Spatial-Temporal Pooling Networks for Video-Based Person Re-Identification
Automatic Content-Aware Projection for 360deg Videos
Blur-Invariant Deep Learning for Blind-Deblurring
Non-Linear Convolution Filters for CNN-Based Learning
AOD-Net: All-In-One Dehazing Network
Simultaneous Detection and Removal of High Altitude Clouds From an Image
Understanding Low- and High-Level Contributions to Fixation Prediction
Image Super-Resolution Using Dense Skip Connections
Convergence Analysis of MAP Based Blur Kernel Estimation
Blob Reconstruction Using Unilateral Second Order Gaussian Kernels With Application to High-ISO Long-Exposure Image Denoising
Deep Generative Adversarial Compression Artifact Removal
Online Multi-Object Tracking Using CNN-Based Single Object Tracker With Spatial-Temporal Attention Mechanism
Mutual Enhancement for Detection of Multiple Logos in Sports Videos
Referring Expression Generation and Comprehension via Attributes
RoomNet: End-To-End Room Layout Estimation
SSH: Single Stage Headless Face Detector
AnnArbor: Approximate Nearest Neighbors Using Arborescence Coding
Boosting Image Captioning With Attributes
Learning to Estimate 3D Hand Pose From Single RGB Images
Locally-Transferred Fisher Vectors for Texture Classification
Object-Level Proposals
Extreme Clicking for Efficient Object Annotation
WordSup: Exploiting Word Annotations for Character Based Text Detection
Illuminating Pedestrians via Simultaneous Detection & Segmentation
Generalized Orderless Pooling Performs Implicit Salient Matching
Exploiting Spatial Structure for Localizing Manipulated Image Regions
RDFNet: RGB-D Multi-Level Residual Feature Fusion for Indoor Semantic Segmentation
The Mapillary Vistas Dataset for Semantic Understanding of Street Scenes
Self-Organized Text Detection With Minimal Post-Processing via Border Learning
Sparse Exact PGA on Riemannian Manifolds
Tensor RPCA by Bayesian CP Factorization With Complex Noise
Multimodal Gaussian Process Latent Variable Models With Harmonization
Segmentation-Aware Convolutional Networks Using Local Attention Masks
Rotation Equivariant Vector Field Networks
ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression
AutoDIAL: Automatic DomaIn Alignment Layers
Focusing Attention: Towards Accurate Text Recognition in Natural Images
Unsupervised Object Segmentation in Video by Efficient Selection of Highly Probable Positive Features
Nonparametric Variational Auto-Encoders for Hierarchical Representation Learning
Dense and Low-Rank Gaussian CRFs Using Deep Embeddings
A Multimodal Deep Regression Bayesian Network for Affective Video Content Analyses
Moving Object Detection in Time-Lapse or Motion Trigger Image Sequences Using Low-Rank and Invariant Sparse Decomposition
A Multilayer-Based Framework for Online Background Subtraction With Freely Moving Cameras
Dynamic Label Graph Matching for Unsupervised Video Re-Identification
Spatiotemporal Modeling for Crowd Counting in Videos
Personalized Cinemagraphs Using Semantic Understanding and Collaborative Learning
What Is Around the Camera?
Weakly-Supervised Learning of Visual Relations
BIER - Boosting Independent Embeddings Robustly
3D Graph Neural Networks for RGBD Semantic Segmentation
Learning Multi-Attention Convolutional Neural Network for Fine-Grained Image Recognition
Learning 3D Object Categories by Looking Around Them
Quantitative Evaluation of Confidence Measures in a Machine Learning World
Towards End-To-End Text Spotting With Convolutional Recurrent Neural Networks
DeepSetNet: Predicting Sets With Deep Neural Networks
Learning From Video and Text via Large-Scale Discriminative Clustering
TALL: Temporal Activity Localization via Language Query
End-To-End Face Detection and Cast Grouping in Movies Using Erdos-Renyi Clustering
Active Decision Boundary Annotation With Deep Generative Models
Convolutional Dictionary Learning via Local Processing
Editable Parametric Dense Foliage From 3D Capture
Refractive Structure-From-Motion Through a Flat Refractive Interface
Submodular Trajectory Optimization for Aerial 3D Scanning
Camera Calibration by Global Constraints on the Motion of Silhouettes
Deltille Grids for Geometric Camera Calibration
A Lightweight Single-Camera Polarization Compass With Covariance Estimation
Reflectance Capture Using Univariate Sampling of BRDFs
Estimating Defocus Blur via Rank of Local Patches
RGB-Infrared Cross-Modality Person Re-Identification
Intrinsic 3D Dynamic Surface Tracking Based on Dynamic Ricci Flow and Teichmuller Map
Multi-Scale Deep Learning Architectures for Person Re-Identification
Range Loss for Deep Face Recognition With Long-Tailed Training Data
Face Sketch Matching via Coupled Deep Transform Learning
Realistic Dynamic Facial Textures From a Single Image Using GANs
Pixel Recursive Super Resolution
PanNet: A Deep Network Architecture for Pan-Sharpening
Recurrent Color Constancy
Saliency Pattern Detection by Ranking Structured Trees
Monocular Video-Based Trailer Coupler Detection Using Multiplexer Convolutional Neural Network
Parallel Tracking and Verifying: A Framework for Real-Time and High Accuracy Visual Tracking
Non-Rigid Object Tracking via Deformable Patches Using Shape-Preserved KCF and Level Sets
A Discriminative View of MRF Pre-Processing Algorithms
Offline Handwritten Signature Modeling and Verification Based on Archetypal Analysis
Long Short-Term Memory Kalman Filters: Recurrent Neural Estimators for Pose Regularization
Learning Spatio-Temporal Representation With Pseudo-3D Residual Networks
Deeper, Broader and Artier Domain Generalization
Deep Spatial-Semantic Attention for Fine-Grained Sketch-Based Image Retrieval
Soft-NMS -- Improving Object Detection With One Line of Code
Semantic Jitter: Dense Supervision for Visual Comparisons via Synthetic Images
Video Scene Parsing With Predictive Feature Learning
Understanding and Mapping Natural Beauty
Human Pose Estimation Using Global and Local Normalization
HashNet: Deep Learning to Hash by Continuation
Scaling the Scattering Transform: Deep Hybrid Networks
Flip-Invariant Motion Representation
Scene Categorization With Spectral Features
Image2song: Song Retrieval via Bridging Image Content and Lyric Words
Deep Functional Maps: Structured Prediction for Dense Shape Correspondence
Training Deep Networks to Be Spatially Sensitive
3DCNN-DQN-RNN: A Deep Reinforcement Learning Framework for Semantic Parsing of Large-Scale 3D Point Clouds
 Semi Supervised Semantic Segmentation Using Generative Adversarial Network
Efficient Low Rank Tensor Ring Completion
Semantic Image Synthesis via Adversarial Learning
Unified Deep Supervised Domain Adaptation and Generalization
Interpretable Transformations With Encoder-Decoder Networks
Deep Clustering via Joint Convolutional Autoencoder Embedding and Relative Entropy Minimization
Deep Scene Image Classification With the MFAFVNet
Learning Bag-Of-Features Pooling for Deep Convolutional Neural Networks