iccv 2015 论文列表
2015 IEEE International Conference on Computer Vision, ICCV 2015, Santiago, Chile, December 7-13, 2015.
|
Learning to Track: Online Multi-object Tracking by Decision Making.
Multiple Hypothesis Tracking Revisited.
Shape Interaction Matrix Revisited and Robustified: Efficient Subspace Clustering with Corrupted and Incomplete Data.
Partial Person Re-Identification.
Generating Notifications for Missing Actions: Don't Forget to Turn the Lights Off!
Uncovering Interactions and Interactors: Joint Estimation of Head, Body Orientation and F-Formations from Surveillance Videos.
Text Flow: A Unified Text Detection System in Natural Scene Images.
Learning Visual Clothing Style with Heterogeneous Dyadic Co-Occurrences.
Unsupervised Extraction of Video Highlights via Robust Recurrent Auto-Encoders.
Love Thy Neighbors: Image Annotation by Exploiting Image Metadata.
Semantic Video Entity Linking Based on Visual Content and Metadata.
Bayesian Non-parametric Inference for Manifold Based MoCap Representation.
Human Action Recognition Using Factorized Spatio-Temporal Convolutional Networks.
Objects2action: Classifying and Localizing Actions without Any Video Example.
Multiresolution Hierarchy Co-Clustering for Semantic Segmentation in Sequences with Small Variations.
Beyond Covariance: Feature Representation with Nonlinear Kernel Matrices.
Selecting Relevant Web Trained Concepts for Automated Event Retrieval.
Action Recognition by Hierarchical Mid-Level Action Elements.
Context Aware Active Learning of Activity Recognition Models.
Sequence to Sequence - Video to Text.
Storyline Representation of Egocentric Videos with an Applications to Story-Based Search.
Person Re-Identification with Discriminatively Trained Viewpoint Invariant Dictionaries.
Describing Videos by Exploiting Temporal Structure.
Temporal Perception and Prediction in Ego-Centric Video.
Learning Spatiotemporal Features with 3D Convolutional Networks.
Unsupervised Semantic Parsing of Video Collections.
Learning Temporal Embeddings for Complex Video Analysis.
Weakly-Supervised Alignment of Video with Text.
Temporal Subspace Clustering for Human Motion Segmentation.
Category-Blind Human Action Recognition: A Practical Recognition System.
Sparse Dynamic 3D Reconstruction from Unsynchronized Videos.
Co-Interest Person Detection from Multiple Wearable Camera Videos.
Large Displacement 3D Scene Flow with Occlusion Reasoning.
Self-Occlusions and Disocclusions in Causal Video Object Segmentation.
Linearization to Nonlinear Learning for Visual Tracking.
A Novel Representation of Parts for Accurate 3D Object Detection and Tracking in Monocular Images.
Minimizing Human Effort in Interactive Tracking by Incremental Learning of Model Parameters.
Learning to Divide and Conquer for Online Multi-target Tracking.
FollowMe: Efficient Online Min-Cost Flow Tracking with Bounded Memory and Computation.
Contour Flow: Middle-Level Motion Estimation by Combining Motion Segmentation and Contour Alignment.
Recurrent Network Models for Human Dynamics.
TRIC-track: Tracking by Regression with Incrementally Learned Cascades.
Unsupervised Trajectory Clustering via Adaptive Multi-kernel-Based Shrinkage.
SpeDo: 6 DOF Ego-Motion Sensor Using Speckle Defocus Imaging.
Learning Spatially Regularized Correlation Filters for Visual Tracking.
Local Subspace Collaborative Tracking.
An Adaptive Data Representation for Robust Point-Set Registration and Merging.
Dual-Feature Warping-Based Motion Model Estimation.
Learning Image and User Features for Recommendation in Social Networks.
Conditional High-Order Boltzmann Machine: A Supervised Learning Model for Relation Learning.
Structured Feature Selection.
Predicting Deep Zero-Shot Convolutional Neural Networks Using Textual Descriptions.
Multi-view Subspace Clustering.
Recursive Fréchet Mean Computation on the Grassmannian and Its Applications to Computer Vision.
A Supervised Low-Rank Method for Learning Invariant Subspaces.
Semi-Supervised Zero-Shot Classification with Label Representation Learning.
Infinite Feature Selection.
Multi-view Domain Generalization for Visual Recognition.
An NMF Perspective on Binary Hashing.
Bayesian Model Adaptation for Crowd Counts.
Zero-Shot Learning via Semantic Similarity Embedding.
ML-MG: Multi-label Learning with Missing Labels Using a Mixed Graph.
Learning Binary Codes for Maximum Inner Product Search.
Geometry-Aware Deep Transform.
Secrets of Matrix Factorization: Approximations, Numerics, Manifold Optimization and Random Restarts.
Unsupervised Domain Adaptation with Imbalanced Cross-Domain Data.
Beyond Gauss: Image-Set Matching on the Riemannian Manifold of PDFs.
Improving Ferns Ensembles by Sparsifying and Quantising Posterior Probabilities.
Multi-label Cross-Modal Retrieval.
Unsupervised Learning of Spatiotemporally Coherent Metrics.
Low Dimensional Explicit Feature Maps.
Simultaneous Deep Transfer Across Domains and Tasks.
Learning Ensembles of Potential Functions for Structured Prediction with Latent Variables.
Similarity Gaussian Process Latent Variable Model for Multi-modal Data Analysis.
Differential Recurrent Neural Networks for Action Recognition.
Multi-image Matching via Fast Alternating Minimization.
Dense Semantic Correspondence Where Every Pixel is a Classifier.
Flow Fields: Dense Correspondence Fields for Highly Accurate Large Displacement Optical Flow Estimation.
SPM-BP: Sped-Up PatchMatch Belief Propagation for Continuous MRFs.
Hot or Not: Exploring Correlations between Appearance and Temperature.
Synthesizing Illumination Mosaics from Internet Photo-Collections.
FaceDirector: Continuous Control of Facial Performance in Video.
Personalized Age Progression with Aging Dictionary.
Wide-Area Image Geolocalization with Aerial Reference Imagery.
What Makes Tom Hanks Look Like Tom Hanks.
Learning a Discriminative Model for the Perception of Realism in Composite Images.
Robust RGB-D Odometry Using Point and Line Features.
Extraction of Virtual Baselines from Distorted Document Images Using Curvilinear Projection.
Group Membership Prediction.
Learning to Predict Saliency on Face Images.
Example-Based Modeling of Facial Texture from Deficient Data.
Understanding Everyday Hands in Action from RGB-D Images.
PIEFA: Personalized Incremental and Ensemble Face Alignment.
Robust Statistical Face Frontalization.
Person Recognition in Personal Photo Collections.
Regressive Tree Structured Model for Facial Landmark Localization.
Bi-Shifting Auto-Encoder for Unsupervised Domain Adaptation.
Discriminative Pose-Free Descriptors for Face and Object Matching.
An Accurate Iris Segmentation Framework Under Relaxed Imaging Constraints Using Total Variation Model.
Two Birds, One Stone: Jointly Learning Binary Code for Large-Scale Face Image Retrieval and Attributes Prediction.
A Spatio-Temporal Appearance Representation for Viceo-Based Pedestrian Re-Identification.
Leveraging Datasets with Varying Annotations for Face Alignment via Deep Regression Network.
Multi-conditional Latent Variable Model for Joint Facial Action Unit Detection.
Pairwise Conditional Random Forests for Facial Expression Recognition.
Learning to Transfer: Transferring Latent Task Structures and Its Application to Person-Specific Facial Action Unit Detection.
Multi-Scale Learning for Low-Resolution Person Re-Identification.
Rendering of Eyes for Eye-Shape Registration and Gaze Estimation.
Regressing a 3D Face Shape from a Single Image.
Multi-Task Learning with Low Rank Attribute Embedding for Person Re-Identification.
Deep Learning Face Attributes in the Wild.
Simultaneous Local Binary Feature Learning and Encoding for Face Recognition.
Automated Facial Trait Judgment and Election Outcome Prediction: Social Dimensions of Face.
From Emotions to Action Units with Hidden and Semi-Hidden-Task Learning.
Pose-Invariant 3D Face Alignment.
Efficient PSD Constrained Asymmetric Metric Learning for Person Re-Identification.
From Facial Parts Responses to Face Detection: A Deep Learning Approach.
Conditional Convolutional Neural Network for Modality-Aware Face Recognition.
Robust Facial Landmark Detection Under Significant Head Poses and Occlusion.
Robust Model-Based 3D Head Pose Estimation.
Robust Heart Rate Measurement from Video Using Select Random Patches.
Learning Social Relation Traits from Face Images.
Confidence Preserving Machine for Facial Action Unit Detection.
Selective Encoding for Recognizing Unreliably Localized Faces.
A Groupwise Multilinear Correspondence Optimization for 3D Faces.
Depth Selective Camera: A Direct, On-Chip, Programmable Technique for Depth Selectivity in Photography.
Hyperspectral Super-Resolution by Coupled Spectral Unmixing.
Model-Based Tracking at 300Hz Using Raw Time-of-Flight Observations.
Active One-Shot Scan for Wide Depth Range Using a Light Field Projector Based on Coded Aperture.
A Gaussian Process Latent Variable Model for BRDF Inference.
Hyperspectral Compressive Sensing Using Manifold-Structured Sparsity Prior.
Complementary Sets of Shutter Sequences for Motion Deblurring.
Frequency-Based Environment Matting by Compressive Sensing.
Separating Fluorescent and Reflective Components by Using a Single Hyperspectral Image.
Intrinsic Depth: Improving Depth Transfer with Intrinsic Images.
Extended Depth of Field Catadioptric Imaging Using Focal Sweep.
Oriented Light-Field Windows for Scene Flow.
Occlusion-Aware Depth Estimation Using Light-Field Cameras.
Photometric Stereo with Small Angular Variations.
Learning Data-Driven Reflectance Priors for Intrinsic Image Decomposition.
Depth Map Estimation and Colorization of Anaglyph Images Using Local Color Prior and Reverse Intensity Distribution.
Depth Recovery from Light Field Using Focal Stack Symmetry.
TransCut: Transparent Object Segmentation from a Light-Field Image.
Single-Shot Specular Surface Reconstruction with Gonio-Plenoptic Imaging.
Resolving Scale Ambiguity via XSlit Aspect Ratio Analysis.
Photometric Stereo in a Scattering Medium.
Mutual-Structure for Joint Filtering.
Removing Rain from a Single Image via Discriminative Sparse Coding.
Leave-One-Out Kernel Optimization for Shadow Detection.
Airborne Three-Dimensional Cloud Tomography.
Polarized 3D: High-Quality Depth Sensing with Polarization Cues.
Learning Complexity-Aware Cascades for Deep Pedestrian Detection.
Multi-task Recurrent Neural Network for Immediacy Prediction.
Where to Buy It: Matching Street Clothing Photos in Online Shops.
Panoptic Studio: A Massively Multiview System for Social Motion Capture.
Opening the Black Box: Hierarchical Sampling Optimization for Estimating Human Hand Pose.
Training a Feedback Loop for Hand Pose Estimation.
Simultaneous Foreground Detection and Classification with Hybrid Features.
Action Detection by Implicit Intentional Motion Clustering.
RGB-W: When Vision Meets Wireless.
Action Localization in Videos through Context Walk.
Motion Trajectory Segmentation via Minimum Cost Multicuts.
Multi-cue Structure Preserving MRF for Unconstrained Video Segmentation.
COUNT Forest: CO-Voting Uncertain Number of Targets Using Random Forest for Crowd Density Estimation.
Actionness-Assisted Recognition of Actions.
Video Segmentation with Just a Few Strokes.
Fully Connected Object Proposals for Video Segmentation.
P-CNN: Pose-Based CNN Features for Action Recognition.
Adaptive Exponential Smoothing for Online Filtering of Pixel Prediction Maps.
Person Re-Identification with Correspondence Structure Learning.
Activity Auto-Completion: Predicting Human Activities from Partial Videos.
Car that Knows Before You Do: Anticipating Maneuvers via Learning Temporal Driving Models.
Unsupervised Object Discovery and Tracking in Video Collections.
Learning to Track for Spatio-Temporal Action Localization.
Efficient Video Segmentation Using Parametric Graph Partitioning.
Unsupervised Synchrony Discovery in Human Interaction.
Pedestrian Travel Time Estimation in Crowded Scenes.
Multiple Feature Fusion via Weighted Entropy for Visual Tracking.
Visual Tracking with Fully Convolutional Networks.
Integrating Dashcam Views through Inter-Video Mapping.
Understanding and Diagnosing Visual Tracking Systems.
Online Object Tracking with Proposal Selection.
Robust Non-rigid Motion Tracking and Surface Reconstruction Using L0 Regularization.
Hierarchical Convolutional Features for Visual Tracking.
Exploring Causal Relationships in Visual Object Tracking.
Tracking-by-Segmentation with Online Gradient Boosting Decision Tree.
Joint Probabilistic Data Association Revisited.
Multi-kernel Correlation Filter for Visual Tracking.
Near-Online Multi-target Tracking with Aggregated Local Flow Descriptor.
Live Repetition Counting.
SOWP: Spatially Ordered and Weighted Patch Descriptor for Visual Tracking.
Discriminative Low-Rank Tracking.
Face Flow.
Direct Intrinsics: Learning Albedo-Shading Decomposition by Convolutional Regression.
Joint Fine-Tuning in Deep Neural Networks for Facial Expression Recognition.
Introducing Geometry in Active Learning for Image Segmentation.
Matrix Backpropagation for Deep Networks with Structured Layers.
Look and Think Twice: Capturing Top-Down Visual Attention with Feedback Convolutional Neural Networks.
Predicting Multiple Structured Visual Interpretations.
PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization.
Fast Orthogonal Projection Based on Kronecker Product.
Entropy-Based Latent Structured Output Prediction.
Highly-Expressive Spaces of Well-Behaved Transformations: Keeping it Simple.
Mode-Seeking on Hypergraphs for Robust Geometric Model Fitting.
Context-Aware CNNs for Person Head Detection.
Interpolation on the Manifold of K Component GMMs.
Understanding Deep Features with Computer-Generated Imagery.
Additive Nearest Neighbor Feature Maps.
An Exploration of Parameter Redundancy in Deep Networks with Circulant Projections.
Maximum-Margin Structured Learning with Deep Networks for 3D Human Pose Estimation.
Multi-class Multi-annotator Active Learning with Robust Gaussian Process for Visual Recognition.
Robust Optimization for Deep Regression.
Projection Bank: From High-Dimensional Data to Medium-Length Binary Codes.
Robust Principal Component Analysis on Graphs.
A Nonparametric Bayesian Approach toward Stacked Convolutional Independent Component Analysis.
Unsupervised Learning of Visual Representations Using Videos.
Learning to Rank Based on Subsequences.
Context-Guided Diffusion for Label Propagation on Graphs.
Learning Semi-Supervised Representation Towards a Unified Optimization Framework for Semi-Supervised Learning.
FlowNet: Learning Optical Flow with Convolutional Networks.
Learning the Structure of Deep Convolutional Networks.
HD-CNN: Hierarchical Deep Convolutional Neural Networks for Large Scale Visual Recognition.
Active Transfer Learning with Zero-Shot Priors: Reusing Past Datasets for Future Tasks.
DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving.
MANTRA: Minimum Maximum Latent Structural SVM for Image Classification and Ranking.
Camera Pose Voting for Large-Scale Image-Based Localization.
Lost Shopping! Monocular Localization in Large Indoor Spaces.
Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views.
3D-Assisted Feature Synthesis for Novel Views of an Object.
Common Subspace for Model and Similarity: Phrase Learning for Caption Generation from Images.
AttentionNet: Aggregating Weak Directions for Accurate Object Detection.
Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-scale Convolutional Architecture.
Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models.
Structural Kernel Learning for Large Scale Multiclass Object Co-detection.
Multimodal Convolutional Neural Networks for Matching Image and Sentence.
Monocular Object Instance Segmentation and Depth Ordering with CNNs.
Simpler Non-Parametric Methods Provide as Good or Better Results to Multiple-Instance Learning.
Automatic Concept Discovery from Parallel Text and Visual Corpora.
Semantic Segmentation with Object Clique Potential.
DeepProposal: Hunting Objects by Cascading Deep Convolutional Layers.
Box Aggregation for Proposal Decimation: Last Mile of Object Detection.
Square Localization for Efficient and Accurate Object Detection.
Domain Generalization for Object Recognition with Multi-task Autoencoders.
Learning Common Sense through Visual Abstraction.
Learning Like a Child: Fast Novel Visual Concept Learning from Sentence Descriptions of Images.
Augmenting Strong Supervision Using Web Data for Fine-Grained Categorization.
Contractive Rectifier Networks for Nonlinear Maximum Margin Classification.
A Unified Multiplicative Framework for Attribute Learning.
Scene-Domain Active Part Models for Object Representation.
Active Object Localization with Deep Reinforcement Learning.
DeepBox: Learning Objectness with Convolutional Networks.
Actions and Attributes from Wholes and Parts.
Visual Madlibs: Fill in the Blank Description Generation and Question Answering.
Unsupervised Domain Adaptation for Zero-Shot Learning.
Dense Optical Flow Prediction from a Static Image.
Localize Me Anywhere, Anytime: A Multi-task Point-Retrieval Approach.
VQA: Visual Question Answering.
Just Noticeable Differences in Visual Attributes.
Guiding the Long-Short Term Memory Model for Image Caption Generation.
Multiple Granularity Descriptors for Fine-Grained Categorization.
Understanding and Predicting Image Memorability at a Large Scale.
Real-Time Pose Estimation Piggybacked on Object Detection.
Attributed Grammars for Joint Estimation of Human Attributes, Part and Pose.
Towards Pointless Structure from Motion: 3D Reconstruction and Camera Parameters from General 3D Curves.
A Linear Generalized Camera Calibration from Three Intersecting Reference Planes.
On the Equivalence of Moving Entrance Pupil and Radial Distortion for Camera Calibration.
A Collaborative Filtering Approach to Real-Time Hand Pose Estimation.
Component-Wise Modeling of Articulated Objects.
Learning a Descriptor-Specific 3D Keypoint Detector.
Efficient Solution to the Epipolar Geometry for Radially Distorted Cameras.
Detailed Full-Body Reconstructions of Moving People from Monocular RGB-D Sequences.
Reflection Modeling for Passive Stereo.
The Likelihood-Ratio Test and Efficient Robust Estimation.
Dense Image Registration and Deformable Surface Reconstruction in Presence of Occlusions and Minimal Texture.
Dense Continuous-Time Tracking and Mapping with Rolling Shutter RGB-D Cameras.
Classical Scaling Revisited.
Hierarchical Higher-Order Regression Forest Fields: An Application to 3D Indoor Scene Labelling.
Interactive Visual Hull Refinement for Specular and Transparent Object Surface Reconstruction.
Wide Baseline Stereo Matching with Convex Bounded Distortion Constraints.
MAP Disparity Estimation Using Hidden Markov Trees.
You are Here: Mimicking the Human Thinking Process in Reading Floor-Plans.
Exploiting Object Similarity in 3D Reconstruction.
Non-parametric Structure-Based Calibration of Radially Symmetric Cameras.
Deformable 3D Fusion: From Partial Dynamic 3D Observations to Complete 4D Models.
Peeking Template Matching for Depth Extension.
Guaranteed Outlier Removal for Rotation Search.
Semantically-Aware Aerial Reconstruction from Multi-modal Data.
Procedural Editing of 3D Building Point Clouds.
3D Fragment Reassembly Using Integrated Template Guidance and Fracture-Region Matching.
Merging the Unmatchable: Stitching Visually Disconnected SfM Models.
The HCI Stereo Metrics: Geometry-Aware Performance Analysis of Stereo Algorithms.
Globally Optimal 2D-3D Registration from Points or Lines without Correspondences.
Hyperpoints and Fine Vocabularies for Large-Scale Location Recognition.
Higher-Order CRF Structural Segmentation of 3D Reconstructed Surfaces.
Joint Camera Clustering and Surface Segmentation for Large-Scale Multi-view Stereo.
Structure from Motion Using Structure-Less Resection.
CV-HAZOP: Introducing Test Data Validation for Computer Vision.
MeshStereo: A Global Stereo Model with Mesh Alignment Regularization for View Interpolation.
Robust and Optimal Sum-of-Squares-Based Point-to-Plane Registration of Image Sets and Structured Scenes.
Robust Nonrigid Registration by Convex Optimization.
Registering Images to Untextured Geometry Using Average Shading Gradients.
Contour Box: Rejecting Object Proposals without Explicit Closed Contours.
Human Pose Estimation in Videos.
Spatial Semantic Regularisation for Large Scale Object Detection.
Visual Phrases for Exemplar Face Detection.
Relaxing from Vocabulary: Robust Weakly-Supervised Deep Learning for Vocabulary-Free Image Tagging.
Beyond Tree Structure Models: A New Occlusion Aware Graphical Model for Human Pose Estimation.
An MRF-Poselets Model for Detecting Highly Articulated Humans.
Fast and Accurate Head Pose Estimation via Random Projection Forests.
Lending A Hand: Detecting Hands and Recognizing Activities in Complex Egocentric Interactions.
PQTable: Fast Exact Asymmetric Distance Neighbor Search for Product Quantization Using Hash Tables.
BubbLeNet: Foveated Imaging for Visual Discovery.
Top Rank Supervised Binary Coding for Visual Search.
Flowing ConvNets for Human Pose Estimation in Videos.
Deep Learning Strong Parts for Pedestrian Detection.
Learning Deep Representation with Large-Scale Attributes.
Alternating Co-Quantization for Cross-Modal Hashing.
Adaptive Dither Voting for Robust Spatial Verification.
Depth-Based Hand Pose Estimation: Data, Methods, and Challenges.
Higher-Order Inference for Multi-class Log-Supermodular Models.
Optimizing Expected Intersection-Over-Union with Candidate-Constrained CRFs.
A Projection Free Method for Generalized Eigenvalue Problem with a Nonsmooth Regularizer.
A Wavefront Marching Method for Solving the Eikonal Equation on Cartesian Grids.
Convolutional Sparse Coding for Image Super-Resolution.
Inferring M-Best Diverse Labelings in a Single One.
A Multiscale Variable-Grouping Framework for MRF Energy Minimization.
Constrained Convolutional Neural Networks for Weakly Supervised Segmentation.
Adaptively Unified Semi-Supervised Dictionary Learning with Active Points.
Entropy Minimization for Convex Relaxation Approaches.
Volumetric Bias in Segmentation and Reconstruction: Secrets and Solutions.
Parsimonious Labeling.
Efficient Decomposition of Image and Mesh Graphs by Lifted Multicuts.
Weakly-and Semi-Supervised Learning of a Deep Convolutional Network for Semantic Image Segmentation.
Semantic Segmentation of RGBD Images with Mutex Constraints.
StereoSnakes: Contour Based Consistent Object Extraction for Stereo Images.
Semi-Supervised Normalized Cuts for Image Segmentation.
A Randomized Ensemble Approach to Industrial CT Segmentation.
Probabilistic Appearance Models for Segmentation and Classification.
Enhancing Road Maps by Parsing Aerial Images Around the World.
Learning to Combine Mid-Level Cues for Object Proposal Generation.
Shell PCA: Statistical Shape Modelling in Shell Space.
Compositional Hierarchical Representation of Shape Manifolds for Classification of Non-manifold Shapes.
Unsupervised Tube Extraction Using Transductive Learning and Dense Trajectories.
Detection and Segmentation of 2D Curved Reflection Symmetric Structures.
BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation.
Joint Optimization of Segmentation and Color Clustering.
Robust Image Segmentation Using Contour-Guided Color Palettes.
Contour Guided Hierarchical Model for Shape Matching.
The Middle Child Problem: Revisiting Parametric Min-Cut and Seeds for Object Proposals.
BodyPrint: Pose Invariant 3D Shape Matching of Human Bodies.
Low-Rank Tensor Constrained Multiview Subspace Clustering.
Joint Object and Part Segmentation Using Deep Learned Potentials.
Video Matting via Sparse and Low-Rank Representation.
Secrets of GrabCut and Kernel K-Means.
Boosting Object Proposals: From Pascal to COCO.
The One Triangle Three Parallelograms Sampling Strategy and Its Application in Shape Regression.
Conditional Random Fields as Recurrent Neural Networks.
Learning Deconvolution Network for Semantic Segmentation.
Learning Discriminative Reconstructions for Unsupervised Outlier Removal.
Web-Scale Image Clustering Revisited.
Low-Rank Matrix Factorization under General Mixture Noise Distributions.
Semantic Component Analysis.
Deep Fried Convnets.
Deep Neural Decision Forests.
Discovering the Spatial Extent of Relative Attributes.
Bilinear CNN Models for Fine-Grained Visual Recognition.
Fast R-CNN.
Webly Supervised Learning of Convolutional Networks.
Unsupervised Visual Representation Learning by Context Prediction.
Learning Image Representations Tied to Ego-Motion.
Minimum Barrier Salient Object Detection at 80 FPS.
Holistically-Nested Edge Detection.
Human Parsing with Contextualized Convolutional Neural Network.
Semantic Image Segmentation via Deep Parsing Network.
Piecewise Flat Embedding for Image Segmentation.
Weakly Supervised Graph Based Semantic Segmentation by Learning Communities of Image-Parts.
On the Visibility of Point Clouds.
Global, Dense Multiscale Reconstruction for a Billion Points.
3D Time-Lapse Reconstruction from Internet Photos.
Structured Indoor Modeling.
Unsupervised Generation of a View Point Annotated Car Dataset from Videos.
Person Re-Identification Ranking Optimisation by Discriminant Context Information Analysis.
Scalable Nonlinear Embeddings for Semantic Category-Based Image Retrieval.
Harvesting Discriminative Meta Objects with Deep CNN Features for Scene Classification.
Learning Deep Object Detectors from 3D Models.
Aggregating Local Deep Features for Image Retrieval.
Fine-Grained Change Detection of Misaligned Scenes with Varied Illuminations.
Per-Sample Kernel Adaptation for Visual Recognition and Grouping.
LEWIS: Latent Embeddings for Word Images and Their Semantics.
Im2Calories: Towards an Automated Mobile Vision Food Diary.
Relaxed Multiple-Instance SVM with Application to Object Discovery.
Multi-scale Recognition with DAG-CNNs.
FASText: Efficient Unconstrained Scene Text Detector.
One Shot Learning via Compositions of Meaningful Patches.
Cutting Edge: Soft Correspondences in Multimodal Scene Parsing.
Task-Driven Feature Pooling for Image Classification.
Predicting Good Features for Image Geo-Localization Using Per-Bundle VLAD.
Probabilistic Label Relation Graphs with Ising Models.
Cascaded Sparse Spatial Bins for Efficient and Effective Generic Object Detection.
Neural Activation Constellations: Unsupervised Part Model Discovery with Convolutional Networks.
Object Detection via a Multi-region and Semantic Segmentation-Aware CNN Model.
MMSS: Multi-modal Sharable and Specific Feature Learning for RGB-D Object Recognition.
Scalable Person Re-identification: A Benchmark.
Multi-View Complementary Hash Tables for Nearest Neighbor Search.
kNN Hashing with Factorized Neighborhood Representation.
What Makes an Object Memorable?
Contextual Action Recognition with R*CNN.
Attribute-Graph: A Graph Based Approach to Image Ranking.
Cross-Domain Image Retrieval with a Dual Attribute-Aware Ranking Network.
Single Image 3D without a Single 3D Image.
Adaptive Hashing for Fast Similarity Search.
Continuous Pose Estimation with a Spatial Ensemble of Fisher Regressors.
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification.
HICO: A Benchmark for Recognizing Human-Object Interactions in Images.
Improving Image Classification with Location Context.
Towards Computational Baby Learning: A Weakly-Supervised Approach for Object Detection.
Deep Multi-patch Aggregation Network for Image Style, Aesthetics, and Quality Estimation.
Learning Concept Embeddings with Combined Human-Machine Expertise.
A Deep Visual Correspondence Embedding Model for Stereo Matching Costs.
3D Surface Profilometry Using Phase Shifting of De Bruijn Pattern.
Learning Analysis-by-Synthesis for 6D Pose Estimation in RGB-D Images.
Multi-view Convolutional Neural Networks for 3D Shape Recognition.
Learning Informative Edge Maps for Indoor Scene Layout Prediction.
Single Image Pop-Up from Discriminatively Learned Parts.
Direct, Dense, and Deformable: Template-Based Non-rigid 3D Reconstruction from RGB Video.
The Joint Image Handbook.
General Dynamic Scene Reconstruction from Multiple View Video.
As-Rigid-as-Possible Volumetric Shape-from-Template.
Variational PatchMatch MultiView Reconstruction and Refinement.
Massively Parallel Multiview Stereopsis by Surface Normal Diffusion.
Global Structure-from-Motion by Similarity Averaging.
Blur-Aware Disparity Estimation from Defocus Stereo Images.
Photogeometric Scene Flow for High-Detail Dynamic 3D Reconstruction.
High Quality Structure from Small Motion for Rolling Shutter Cameras.
Accurate Camera Calibration Robust to Defocus Using a Smartphone.
3D Hand Pose Estimation Using Randomized Decision Forest with Segmentation Index Points.
Intrinsic Scene Decomposition from RGB-D Images.
Optimizing the Viewing Graph for Structure-from-Motion.
Point Triangulation through Polyhedron Collapse Using the l∞ Norm.
Exploiting High Level Scene Cues in Stereo Reconstruction.
Semantic Pose Using Deep Networks Trained on Synthetic RGB-D.
A Versatile Scene Model with Differentiable Visibility Applied to Generative Pose Estimation.
Learning Shape, Motion and Elastic Models in Force Space.
An Efficient Minimal Solution for Multi-camera Motion.
Minimal Solvers for 3D Geometry from Satellite Imagery.
3D Object Reconstruction from Hand-Object Interactions.
On Linear Structure from Motion for Light Field Cameras.
Fill and Transfer: A Simple Physics-Based Approach for Containability Reasoning.
Realtime Edge-Based Visual Odometry for a Monocular Camera.
A Versatile Learning-Based 3D Temporal Tracker: Scalable, Robust, Online.
Building Dynamic Cloud Maps from the Ground Up.
Convex Optimization with Abstract Linear Operators.
On Statistical Analysis of Neuroimages with Imperfect Registration.
Efficient Classifier Training to Minimize False Merges in Electron Microscopy Segmentation.
Weakly-Supervised Structured Output Learning with Flexible and Latent Graphs Using High-Order Loss Functions.
Learning to Boost Filamentary Structure Segmentation.
Unsupervised Cross-Modal Synthesis of Subject-Specific Scans.
Illumination Robust Color Naming via Label Propagation.
Self-Calibration of Optical Lenses.
External Patch Prior Guided Internal Clustering for Image Denoising.
A Self-Paced Multiple-Instance Learning Framework for Co-Saliency Detection.
Multiple-Hypothesis Affine Region Estimation with Anisotropic LoG Filters.
Compression Artifacts Reduction by a Deep Convolutional Network.
Learning Large-Scale Automatic Image Colorization.
Rolling Shutter Super-Resolution.
Video Restoration Against Yin-Yang Phasing.
Pan-Sharpening with a Hyper-Laplacian Penalty.
Video Super-Resolution via Deep Draft-Ensemble Learning.
Conditioned Regression Models for Non-blind Single Image Super-Resolution.
Variational Depth Superresolution Using Example-Based Edge Representations.
High-for-Low and Low-for-High: Efficient Boundary Detection from Deep Object Features and Its Applications to High-Level Vision.
Class-Specific Image Deblurring.
Contour Detection and Characterization for Asynchronous Event Sensors.
An Efficient Statistical Method for Image Noise Level Estimation.
See the Difference: Direct Pre-Image Reconstruction and Pose Estimation by Differentiating HOG.
Improving Image Restoration with Soft-Rounding.
Learning Parametric Distributions for Image Super-Resolution: Where Patch Matching Meets Sparse Coding.
Low-Rank Tensor Approximation with Laplacian Scale Mixture Modeling for Multiframe Image Denoising.
Intrinsic Decomposition of Image Sequences from Local Temporal Variations.
Image Matting with KL-Divergence Based Sparse Sampling.
Deep Colorization.
HARF: Hierarchy-Associated Rich Features for Salient Object Detection.
Thin Structure Estimation with Curvature Regularization.
Learning Ordinal Relationships for Mid-Level Vision.
Convolutional Color Constancy.
Deep Networks for Image Super-Resolution with Sparse Prior.
Segment Graph Based Image Filtering: Fast Structure-Preserving Smoothing.
Fully Connected Guided Image Filtering.
Adaptive Spatial-Spectral Dictionary Learning for Hyperspectral Image Denoising.
POP Image Fusion - Derivative Domain Image Fusion without Reintegration.
Naive Bayes Super-Resolution Forest.
Projection onto the Manifold of Elongated Structures for Accurate Extraction.
RGB-Guided Hyperspectral Image Upsampling.
Beyond White: Ground Truth Colors for Color Constancy Correction.
Learning Nonlinear Spectral Filters for Color Image Reconstruction.
Oriented Object Proposals.
A Novel Sparsity Measure for Tensor Recovery.
SALICON: Reducing the Semantic Gap in Saliency Prediction by Adapting Deep Neural Networks.
Automatic Thumbnail Generation Based on Visual Representativeness and Foreground Recognizability.
Patch Group Based Nonlocal Self-Similarity Prior Learning for Image Denoising.
Conformal and Low-Rank Sparse Representation for Image Restoration.
Nighttime Haze Removal with Glow and Multiple Light Colors.
Generic Promotion of Diffusion-Based Salient Object Detection.
Fast and Effective L0 Gradient Minimization by Region Fusion.
A Matrix Decomposition Perspective to Multiple Graph Matching.
A Data-Driven Metric for Comprehensive Evaluation of Saliency Models.
PatchMatch-Based Automatic Lattice Detection for Near-Regular Textures.
A Comprehensive Multi-Illuminant Dataset for Benchmarking of the Intrinsic Image Algorithms.
Cluster-Based Point Set Saliency.
Listening with Your Eyes: Towards a Practical Visual Speech Recognition System Using Deep Boltzmann Machines.
Query Adaptive Similarity Measure for RGB-D Object Recognition.
Learning Where to Position Parts in 3D.
Amodal Completion and Size Constancy in Natural Scenes.
Discriminative Learning of Deep Convolutional Feature Point Descriptors.
Discrete Tabu Search for Graph Matching.
RIDE: Reversal Invariant Descriptor Enhancement.
Local Convolutional Features with Unsupervised Training for Image Retrieval.
Convolutional Channel Features.
Dynamic Texture Recognition via Orthogonal Tensor Dictionary Learning.
Pose Induction for Novel Object Categories.
Mining And-Or Graphs for Graph Matching and Object Discovery.
Object Detection Using Generalization and Efficiency Balanced Co-Occurrence Features.
Learning to See by Moving.
Learning Query and Image Similarities with Ranking Canonical Correlation Analysis.
Aligning Books and Movies: Towards Story-Like Visual Explanations by Watching Movies and Reading Books.
Segment-Phrase Table for Semantic Segmentation, Visual Entailment and Paraphrasing.
Ask Your Neurons: A Neural-Based Approach to Answering Questions about Images.
