NDLI: Efficient minimal-surface regularization of perspective depth maps in variational stereo

Please wait, while we are loading the content...

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Going deeper with convolutions

Propagated image filtering

Web scale photo hash clustering on a single machine

Expanding object detector's Horizon: Incremental learning framework for object detection in videos

Supervised Discrete Hashing

What do 15,000 object categories tell us about classifying and localizing actions?

Landmarks-based kernelized subspace alignment for unsupervised domain adaptation

Blur kernel estimation using normalized color-line priors

A light transport model for mitigating multipath interference in Time-of-flight sensors

Traditional saliency reloaded: A good old model in new shape

Automatic construction Of robust spherical harmonic subspaces

Leveraging stereo matching with learning-based confidence measures

Saliency detection via Cellular Automata

Efficient sparse-to-dense optical flow estimation using a learned basis and layers

Learning multiple visual tasks while discovering their structure

Projection Metric Learning on Grassmann Manifold with Application to Video based Face Recognition

Structural Sparse Tracking

Data-driven depth map refinement via multi-scale sparse representation

Uncalibrated photometric stereo based on elevation angle recovery from BRDF symmetry of isotropic materials

Attributes and categories for generic instance search from one example

Heat diffusion over weighted manifolds: A new descriptor for textured 3D non-rigid shapes

A dynamic programming approach for fast and robust object pose recognition from range images

Beyond Gaussian Pyramid: Multi-skip Feature Stacking for action recognition

A geodesic-preserving method for image warping

Shape driven kernel adaptation in Convolutional Neural Network for robust facial trait recognition

From categories to subcategories: Large-scale image classification with partial class label refinement

Combination features and models for human detection

Improving object detection with deep convolutional networks via Bayesian optimization and structured prediction

A metric parametrization for trifocal tensors with non-colinear pinholes

An efficient volumetric framework for shape tracking

Structured Sparse Subspace Clustering: A unified optimization framework

Delving into egocentric actions

Latent trees for estimating intensity of Facial Action Units

Robust regression on image manifolds for ordered label denoising

Privacy preserving optics for miniature vision sensors

Deep transfer metric learning

Small-variance nonparametric clustering on the hypersphere

DynamicFusion: Reconstruction and tracking of non-rigid scenes in real-time

Reliable Patch Trackers: Robust visual tracking by exploiting reliable patches

Predicting eye fixations using convolutional neural networks

Kernel fusion for better image deblurring

Direction matters: Depth estimation with a surface normal classifier

Modeling local and global deformations in Deep Learning: Epitomic convolution, Multiple Instance Learning, and sliding window detection

Grasp type revisited: A modern perspective on a classical feature for vision

Learning Hypergraph-regularized Attribute Predictors

A coarse-to-fine model for 3D pose estimation and sub-category recognition

Deep neural networks are easily fooled: High confidence predictions for unrecognizable images

Deformable part models are convolutional neural networks

Hypercolumns for object segmentation and fine-grained localization

Mapping visual features to semantic profiles for retrieval in medical imaging

Event-driven stereo matching for real-time 3D panoramic vision

Graph-based simplex method for pairwise energy minimization with binary variables

Image denoising via adaptive soft-thresholding based on non-local samples

3D scanning deformable objects with a single RGBD sensor

Nested motion descriptors

Efficient minimal-surface regularization of perspective depth maps in variational stereo

Maximum persistency via iterative relaxed inference with graphical models

Deep hierarchical parsing for semantic segmentation

Designing deep networks for surface normal estimation

Layered RGBD scene flow estimation

Hashing with binary autoencoders

SUN RGB-D: A RGB-D scene understanding benchmark suite

Collaborative feature learning from social media

Diversity-induced Multi-view Subspace Clustering

Building a bird recognition app and large scale dataset with citizen scientists: The fine print in fine-grained dataset collection

Early burst detection for memory-efficient image retrieval

Indoor scene structure analysis for single image depth estimation

Light field layer matting

Depth camera tracking with contour cues

Radial distortion homography

Efficient object localization using Convolutional Networks

Just noticeable defocus blur detection and estimation

How do we use our hands? Discovering a diverse set of common grasps

Rotating your face using multi-task deep neural network

Is object localization for free? - Weakly-supervised learning with convolutional neural networks

Super-resolution Person re-identification with semi-coupled low-rank discriminant dictionary learning

Dual domain filters based texture and structure preserving image non-blind deconvolution

Region-based temporally consistent video post-processing

Global refinement of random forest

Adaptive region pooling for object detection

Discriminative and consistent similarities in instance-level Multiple Instance Learning

MUlti-Store Tracker (MUSTer): A cognitive psychology inspired approach to object tracking

Finding action tubes

Learning a convolutional neural network for non-uniform motion blur removal

Complexity-adaptive distance metric for object proposals generation

High-fidelity Pose and Expression Normalization for face recognition in the wild

Transformation of Markov Random Fields for marginal distribution estimation

Sparse Convolutional Neural Networks

FaceNet: A unified embedding for face recognition and clustering

Cascaded hand pose regression

Cross-scene crowd counting via deep convolutional neural networks

The application of two-level attention models in deep convolutional neural network for fine-grained image classification

End-to-end integration of a Convolutional Network, Deformable Parts Model and non-maximum suppression

A mixed bag of emotions: Model, predict, and transfer emotion distributions

Neuroaesthetics in fashion: Modeling the perception of fashionability

Part-based modelling of compound scenes from images

Efficient parallel optimization for potts energy with hierarchical fusion

Pooled motion features for first-person videos

Functional correspondence by matrix completion

Elastic-net regularization of singular values for robust subspace learning

Hardware compliant approximate image codes

Photometric refinement of depth maps for multi-albedo objects

Predicting the future behavior of a time-varying probability distribution

Classifier based graph construction for video segmentation

ActivityNet: A large-scale video benchmark for human activity understanding

Mid-level deep pattern mining

Prediction of search targets from fixations in open-world settings

Understanding image representations by measuring their equivariance and equivalence

Effective learning-based illuminant estimation using simple features

PAIGE: PAirwise Image Geometry Encoding for improved efficiency in Structure-from-Motion

Dense, accurate optical flow estimation with piecewise parametric model

Single-image estimation of the camera response function in near-lighting

Multispectral pedestrian detection: Benchmark dataset and baseline

A low-dimensional step pattern analysis algorithm with application to multimodal retinal image registration

Bilinear heterogeneous information machine for RGB-D action recognition

MRF optimization by graph approximation

SALICON: Saliency in Context

Weakly supervised object detection with convex clustering

Interleaved text/image Deep Mining on a large-scale radiology database

Learning semantic relationships for better action retrieval in images

Hierarchical recurrent neural network for skeleton based action recognition

Depth and surface normal estimation from monocular images using regression on deep features and hierarchical CRFs

Discriminative shape from shading in uncalibrated illumination

Multi-manifold deep metric learning for image set classification

Target Identity-aware Network Flow for online multiple target tracking

Adaptive as-natural-as-possible image stitching

EpicFlow: Edge-preserving interpolation of correspondences for optical flow

Learning coarse-to-fine sparselets for efficient object detection and scene classification

Continuous Visibility Feature

FlowWeb: Joint image set alignment by weaving consistent, pixel-wise correspondences

Unsupervised object discovery and localization in the wild: Part-based matching with bottom-up region proposals

Supervised descriptor learning for multi-output regression

A statistical model of Riemannian metric variation for deformable shape analysis

Temporally coherent interpretations for long videos using pattern theory

Line-sweep: Cross-ratio for wide-baseline matching and 3D reconstruction

Simplified mirror-based camera pose computation via rotation averaging

On the relationship between visual attributes and convolutional networks

Saliency detection by multi-context deep learning

Deepshape: Deep learned shape descriptor for 3D shape matching and retrieval

Bayesian adaptive matrix factorization with automatic model selection

Joint action recognition and pose estimation from video

Fast action proposals for human action detection and search

Joint multi-feature spatial context for scene recognition in the semantic manifold

Large-scale damage detection using satellite imagery

A novel locally linear KNN model for visual recognition

Bilinear random projections for locality-sensitive binary codes

Combining local appearance and holistic view: Dual-Source Deep Neural Networks for human pose estimation

Superpixel segmentation using Linear Spectral Clustering

Person count localization in videos from noisy foreground and detections

Good features to track for visual SLAM

Discovering states and transformations in image collections

Generalized Deformable Spatial Pyramid: Geometry-preserving dense correspondence estimation

Classifier adaptation at prediction time

Phase-based frame interpolation for video

Matching-CNN meets KNN: Quasi-parametric human parsing

Absolute pose for cameras under flat refractive interfaces

Protecting against screenshots: An image processing approach

Pose-conditioned joint angle limits for 3D human pose reconstruction

VisKE: Visual knowledge extraction and question answering by visual verification of relation phrases

A graphical model approach for matching partial signatures

From captions to visual concepts and back

Semi-supervised low-rank mapping learning for multi-label classification

ConceptLearner: Discovering visual concepts from weakly labeled image collections

Computationally bounded retrieval

Viewpoints and keypoints

Discrete hyper-graph matching

Rolling shutter motion deblurring

Learning to generate chairs with convolutional neural networks

Accurate depth map estimation from a lenslet light field camera

Deep semantic ranking based hashing for multi-label image retrieval

Similarity learning on an explicit polynomial kernel feature map for person re-identification

Learning to propose objects

Basis mapping based boosting for object detection

Computing the stereo matching cost with a convolutional neural network

Recognize complex events from static images by fusing deep channels

Multi-feature max-margin hierarchical Bayesian model for action recognition

Model recommendation: Generating object detectors from few samples

A linear least-squares solution to elastic Shape-from-Template

Robust large scale monocular visual SLAM

Membership representation for detecting block-diagonal structure in low-rank or sparse subspace clustering

Bayesian inference for neighborhood filters with application in denoising

Deep LAC: Deep localization, alignment and classification for fine-grained recognition

Unconstrained realtime facial performance capture

Blind optical aberration correction by exploring geometric and visual priors

Ontological supervision for fine grained classification of Street View storefronts

Finding distractors in images

From image-level to pixel-level labeling with Convolutional Networks

Semantic alignment of LiDAR data at city scale

Oriented edge forests for boundary detection

Query-adaptive late fusion for image search and person re-identification

Filtered channel features for pedestrian detection

GRSA: Generalized range swap algorithm for the efficient optimization of MRFs

PatchCut: Data-driven object segmentation via local shape transfer

Illumination and reflectance spectra separation of a hyperspectral image meets low-rank matrix factorization

Semantic part segmentation using compositional model combining shape and appearance

A discriminative CNN video representation for event detection

24/7 place recognition by view synthesis

Understanding image virality

Book2Movie: Aligning video scenes with book chapters

3D model-based continuous emotion recognition

Learning to rank in person re-identification with metric ensembles

Making better use of edges via perceptual grouping

Real-time joint estimation of camera orientation and vanishing points

Sketch-based 3D shape retrieval using Convolutional Neural Networks

Salient object detection via bootstrap learning

Towards Open World Recognition

Data-driven 3D Voxel Patterns for object category recognition

3D ShapeNets: A deep representation for volumetric shapes

Robust image alignment with multiple feature descriptors and matching-guided neighborhoods

Pushing the frontiers of unconstrained face detection and recognition: IARPA Janus Benchmark A

Depth from shading, defocus, and correspondence using light-field angular coherence

New insights into Laplacian similarity search

Feature-independent context estimation for automatic image annotation

Category-specific object reconstruction from a single image

Active sample selection and correction propagation on a gradually-augmented graph

Efficient and accurate approximations of nonlinear convolutional networks

Ranking and retrieval of image sequences from multiple paragraph queries

Casual stereoscopic panorama stitching

Superpixel meshes for fast edge-preserving surface reconstruction

Best-Buddies Similarity for robust template matching

Superdifferential cuts for binary energies

The S-HOCK dataset: Analyzing crowds at the stadium

Discriminant analysis on Riemannian manifold of Gaussian distributions for face recognition with image sets

Texture representations for image and video synthesis

Shadow optimization from structured deep edge detection

Total variation regularization of shape signals

Learning similarity metrics for dynamic scene segmentation

Subspace clustering by Mixture of Gaussian Regression

DASC: Dense adaptive self-correlation descriptor for multi-modal and multi-spectral correspondence

In defense of color-based model-free tracking

Best of both worlds: Human-machine collaboration for object annotation

Robust multiple homography estimation: An ill-solved problem

Semi-supervised Domain Adaptation with Subspace Learning for visual recognition

Articulated motion discovery using pairs of trajectories

A solution for multi-alignment by transformation synchronisation

A convex optimization approach to robust fundamental matrix estimation

Simultaneous pose and non-rigid shape with particle dynamics

Semi-supervised learning with explicit relationship regularization

Person re-identification by Local Maximal Occurrence representation and metric learning

Joint patch and multi-label learning for facial action unit detection

Real-time visual analysis of microvascular blood flow for critical care

JOTS: Joint Online Tracking and Segmentation

Gaze-enabled egocentric video summarization via constrained submodular maximization

Sparse depth super resolution

Efficient illuminant estimation for color constancy using grey pixels

Can humans fly? Action understanding with multiple classes of actors

Reweighted laplace prior based hyperspectral compressive sensing for unknown sparsity

Class consistent multi-modal fusion with binary features

R6P - Rolling shutter absolute pose problem

Embedded phase shifting: Robust phase shifting with embedded signals

Shape and light directions from shading and polarization

3D deep shape descriptor

Cross-age face verification by coordinating with cross-face age verification

Beyond Mahalanobis metric: Cayley-Klein metric learning

From dictionary of visual words to subspaces: Locality-constrained affine subspace coding

FPA-CS: Focal plane array-based compressive imaging in short-wave infrared

BOLD - Binary online learned descriptor for efficient image matching

Defocus deblurring and superresolution for time-of-flight depth cameras

Burst deblurring: Removing camera shake through fourier burst accumulation

SOM: Semantic obviousness metric for image quality assessment

DeepID-Net: Deformable deep convolutional neural networks for object detection

Efficient globally optimal consensus maximisation with tree search

Mind's eye: A recurrent visual representation for image caption generation

Hierarchical sparse coding with geometric prior for visual geo-location

P3.5P: Pose estimation with unknown focal length

Joint vanishing point extraction and tracking

Learning a non-linear knowledge transfer model for cross-view action recognition

Random tree walk toward instantaneous 3D human pose estimation

Deep hashing for compact binary codes learning

Completing 3D object shape from one depth image

Encoding based saliency detection for videos and images

Online sketching hashing

Enriching object detection with 2D-3D registration and continuous viewpoint estimation

Representing 3D texture on mesh manifolds for retrieval and recognition applications

Saliency propagation from simple to difficult

Learning an efficient model of hand shape variation from depth images

On the minimal problems of low-rank matrix factorization

Symmetry-based text line detection in natural scenes

DevNet: A Deep Event Network for multimedia event detection and evidence recounting

Learning to detect Motion Boundaries

Improving object proposals with multi-thresholding straddling expansion

Visual recognition by counting instances: A multi-instance cardinality potential kernel

Unconstrained 3D face reconstruction

Becoming the expert - interactive multi-class machine teaching

Long-term recurrent convolutional networks for visual recognition and description

Zero-shot object recognition by semantic manifold distance

Hyper-class augmented and regularized deep learning for fine-grained image classification

Direct structure estimation for 3D reconstruction

Global supervised descent method

Robust camera location estimation by convex programming

Practical robust two-view translation estimation

Learning from massive noisy labeled data for image classification

KL divergence based agglomerative clustering for automated Vitiligo grading

Robust saliency detection via regularized random walks ranking

Weakly supervised semantic segmentation for social images

Image specificity

A multi-plane block-coordinate frank-wolfe algorithm for training structural SVMs with a costly max-oracle

Web-scale training for face identification

Dynamically encoded actions based on spacetime saliency

Three viewpoints toward exemplar SVM

Visual recognition by learning from web data: A weakly supervised domain generalization approach

Clustering of static-adaptive correspondences for deformable object tracking

Geo-semantic segmentation

Towards unified depth and semantic prediction from a single image

Towards force sensing from vision: Observing hand-object interactions to infer manipulation forces

A MRF shape prior for facade parsing with occlusions

Probability occupancy maps for occluded depth images

Segment based 3D object shape priors

Shape-from-Template in Flatland

Understanding tools: Task-oriented object modeling, learning and recognition

Deep roto-translation scattering for object classification

Non-rigid registration of images with geometric and photometric deformation by using local affine Fourier-moment matching

Detector discovery in the wild: Joint multiple instance and representation learning

Deeply learned face representations are sparse, selective, and robust

Unsupervised visual alignment with similarity graphs

Video anomaly detection and localization using hierarchical feature representation and Gaussian process regression

Inferring 3D layout of building facades from a single image

Evaluation of output embeddings for fine-grained image classification

Virtual view networks for object reconstruction

Real-time coarse-to-fine topologically preserving segmentation

Supervised mid-level features for word image representation

Learning lightness from human judgement on relative reflectance

Scene classification with semantic Fisher vectors

Don't just listen, use your imagination: Leveraging visual common sense for non-visual tasks

Co-saliency detection via looking deep and wide

Adopting an unconstrained ray model in light-field cameras for 3D shape reconstruction

Towards 3D object detection with bimodal deep Boltzmann machines over RGBD imagery

An active search strategy for efficient object class detection

Geodesic exponential kernels: When curvature and linearity conflict

Transformation-Invariant Convolutional Jungles

Exemplar SVMs as visual feature encoders

Object scene flow for autonomous vehicles

Reflectance hashing for material recognition

Joint photo stream and blog post summarization and exploration

Video summarization by learning submodular mixtures of objectives

Building proteins in a day: Efficient 3D molecular reconstruction

Learning descriptors for object recognition and 3D pose estimation

Image partitioning into convex polygons

Deep visual-semantic alignments for generating image descriptions

Unsupervised learning of complex articulated kinematic structures combining motion and skeleton information

Elastic functional coding of human actions: From vector-fields to latent variables

Show and tell: A neural image caption generator

Descriptor free visual indoor localization with line segments

Fixation bank: Learning to reweight fixation candidates

Deep networks for saliency detection via local estimation and global search

Reflection removal using ghosting cues

A dataset for Movie Description

Fast and robust hand tracking using detection-guided optimization

Efficient SDP inference for fully-connected CRFs based on low-rank decomposition

Discriminative learning of iteration-wise priors for blind deconvolution

Eye tracking assisted extraction of attentionally important objects from videos

Multi-view feature engineering and learning

Self Scaled Regularized Robust Regression

Simultaneous feature learning and hash coding with deep neural networks

MatchNet: Unifying feature and metric learning for patch-based matching

Reconstructing the world* in six days

Exact bias correction and covariance estimation for stereo vision

Computing similarity transformations from only image correspondences

Image segmentation in Twenty Questions

Interaction part mining: A mid-level approach for fine-grained action recognition

Sparse projections for high-dimensional binary codes

Hierarchically-constrained optical flow

The k-support norm and convex envelopes of cardinality and rank

Matching bags of regions in RGBD images

Recurrent convolutional neural network for object recognition

Feedforward semantic segmentation with zoom-out features

The aperture problem for refractive motion

Saliency-aware geodesic video object segmentation

DEEP-CARVING: Discovering visual attributes by carving deep neural nets

Rent3D: Floor-plan priors for monocular layout estimation

Learning a sequential search for landmarks

Fully convolutional networks for semantic segmentation

Deep correlation for matching images and text

Multi-objective convolutional learning for face labeling

Deep multiple instance learning for image classification and auto-annotation

Multi-instance object segmentation with occlusion handling

Material recognition in the wild with the Materials in Context Database

Understanding pedestrian behaviors from stationary crowd groups

Depth from focus with your mobile phone

Fusion moves for correlation clustering

Second-order constrained parametric proposals and sequential search-based structured prediction for semantic segmentation in RGB-D images

Metric imitation by manifold transfer for efficient vision applications

The stitched puppet: A graphical model of 3D human shape and pose

Scene labeling with LSTM recurrent neural networks

FAemb: A function approximation-based embedding method for image retrieval

Automatically discovering local visual material attributes

Depth image enhancement using local tangent plane approximations

Video co-summarization: Video summarization by visual co-occurrence

Watch and learn: Semi-supervised learning of object detectors from videos

Generalized Tensor Total Variation minimization for visual data recovery?

Active learning for structured probabilistic models with histogram approximation

Image parsing with a wide range of classes and scene-level context

Bayesian sparse representation for hyperspectral image super resolution

Semantic object segmentation via detection in weakly labeled video

Learning with dataset bias in latent subcategory models

Project-Out Cascaded Regression with an application to face alignment

Image retrieval using scene graphs

Unifying holistic and Parts-Based Deformable Model fitting

Small instance detection by integer programming on object density maps

Motion Part Regularization: Improving action recognition via trajectory group selection

Multi-task deep visual-semantic embedding for video thumbnail selection

Fine-grained visual categorization via multi-stage metric learning

Saturation-preserving specular reflection separation

Joint SFM and detection cues for monocular 3D localization in road scenes

Fisher vectors meet Neural Networks: A hybrid classification architecture

UniHIST: A unified framework for image restoration with marginal histogram constraints

Human action segmentation with hierarchical supervoxel consistency

Robust Manhattan Frame estimation from a single RGB-D image

Learning to segment under various forms of weak supervision

Fast and accurate image upscaling with super-resolution forests

Light field from micro-baseline image pair

Efficient ConvNet-based marker-less motion capture in general scenes with a low number of cameras

Learning scene-specific pedestrian detectors without real data

Deep filter banks for texture recognition and segmentation

Multiple random walkers and their application to image cosegmentation

Beyond the shortest path: Unsupervised domain adaptation by Sampling Subspaces along the Spline Flow

Spherical embedding of inlier silhouette dissimilarities

Semantics-preserving hashing for cross-view retrieval

Object proposal by multi-branch hierarchical segmentation

Ambient occlusion via compressive visibility estimation

Shape-tailored local descriptors and their application to segmentation and tracking

Scalable object detection by filter compression with regularized sparse coding

An improved deep learning architecture for person re-identification

Understanding classifier errors by examining influential neighbors

Riemannian coding and dictionary learning: Kernels to the rescue

Scalable structure from motion for densely sampled videos

Parsing occluded people by flexible compositions

Joint calibration of Ensemble of Exemplar SVMs

Holistic 3D scene understanding from a single geo-tagged image

A large-scale car dataset for fine-grained categorization and verification

DeepContour: A deep convolutional feature learned by positive-sharing loss for contour detection

Convolutional feature masking for joint object and stuff segmentation

A fixed viewpoint approach for dense reconstruction of transparent objects

Low-level vision by consensus in a spatial hierarchy of regions

Line drawing interpretation in a multi-view context

Toward user-specific tracking by detection of human shapes in multi-cameras

Intra-frame deblurring by leveraging inter-frame camera motion

Salient Object Subitizing

Hierarchical-PEP model for real-world face recognition

The common self-polar triangle of concentric circles and its application to camera calibration

Taking a deeper look at pedestrians

Learning to segment moving objects in videos

GMMCP tracker: Globally optimal Generalized Maximum Multi Clique problem for multiple object tracking

Learning graph structure for multi-label image classification via clique generation

Matrix completion for resolving label ambiguity

Video magnification in presence of large motions

Flying objects detection from a single moving camera

Line-based Multi-Label Energy Optimization for fisheye image rectification and calibration

Adaptive eye-camera calibration for head-worn devices

Modeling object appearance using Context-Conditioned Component Analysis

Displets: Resolving stereo ambiguities using object knowledge

Time-to-contact from image intensity

Transferring a semantic representation for person re-identification and search

Robust video segment proposals with painless occlusion handling

Face alignment using cascade Gaussian process regression trees

Regularizing max-margin exemplars by reconstruction and generative models

A fast algorithm for elastic shape distances between closed planar curves

Reflection removal for in-vehicle black box videos

Tree quantization for large-scale similarity search and classification

Integrating parametric and non-parametric models for scene labeling

Mining semantic affordances of visual object categories

Causal video object segmentation from persistence of occlusions

Multiple instance learning for soft bags via top instances

Multiclass semantic video segmentation with object-level active inference

Effective face frontalization in unconstrained images

Action recognition with trajectory-pooled deep-convolutional descriptors

Weakly supervised localization of novel objects using appearance transfer

First-person pose recognition using egocentric workspaces

Simultaneous Time-of-Flight sensing and photometric stereo with a single ToF sensor

Active learning and discovery of object categories in the presence of unnameable instances

Learning to compare image patches via convolutional neural networks

Watch-n-patch: Unsupervised understanding of actions and relations

Optimal graph learning with partial tags and multiple features for image and video annotation

DeepEdge: A multi-scale bifurcated deep network for top-down contour detection

Picture: A probabilistic programming language for scene perception

Exploiting uncertainty in regression forests for accurate camera relocalization

Fusing subcategory probabilities for texture classification

Video event recognition with deep hierarchical context model

Object-based RGBD image co-segmentation with mutex constraint

Associating neural word embeddings with deep image representations using Fisher Vectors

3D shape estimation from 2D landmarks: A convex relaxation approach

3D all the way: Semantic segmentation of urban scenes from start to end in 3D

Fast bilateral-space stereo for synthetic defocus

Large-scale and drift-free surface reconstruction using online subvolume registration

Fast randomized Singular Value Thresholding for Nuclear Norm Minimization

LMI-based 2D-3D registration: From uncalibrated images to Euclidean scene

Clique-graph matching by preserving global & local structure

Appearance-based gaze estimation in the wild

One-day outdoor photometric stereo via skylight estimation

A new retraction for accelerating the Riemannian three-factor low-rank matrix completion algorithm

Heteroscedastic max-min distance analysis

Sparse composite quantization

Sparse representation classification with manifold constraints transfer

CIDEr: Consensus-based image description evaluation

Joint inference of groups, events and human roles in aerial videos

Photometric stereo with near point lighting: A solution by mesh deformation

Efficient label collection for unlabeled image datasets

Separating objects and clutter in indoor scenes

FaLRR: A fast low rank representation solver

Simulating makeup through physics-based manipulation of intrinsic image layers

Correlation filters with limited boundaries

Shape-based automatic detection of a large number of 3D facial landmarks

Material classification with thermal imagery

Deeply learned attributes for crowded scene understanding

Learning to look up: Realtime monocular gaze correction using machine learning

Background Subtraction via generalized fused lasso foreground modeling

Mirror, mirror on the wall, tell me, is the error small?

Beyond short snippets: Deep networks for video classification

segDeepM: Exploiting segmentation and context in deep neural networks for object detection

Situational object boundary detection

Real-time 3D head pose and facial landmark estimation from depth images using triangular surface patch features

Aligning 3D models to RGB-D images of cluttered scenes

A stable multi-scale kernel for topological machine learning

The treasure beneath convolutional layers: Cross-convolutional-layer pooling for image classification

Face video retrieval with image query via hashing across Euclidean space and Riemannian manifold

EgoSampling: Fast-forward and stereo for egocentric videos

Social saliency prediction

Beyond Principal Components: Deep Boltzmann Machines for face modeling

Statistical inference models for image datasets with systematic variations

Beyond frontal faces: Improving Person Recognition using multiple cues

Superpixel-based video object segmentation using perceptual organization and location prior

Robust image filtering using joint static and dynamic guidance

Solving multiple square jigsaw puzzles with missing pieces

A Dynamic Convolutional Layer for short rangeweather prediction

SWIFT: Sparse Withdrawal of Inliers in a First Trial

VIP: Finding important people in images

Dataset fingerprints: Exploring image collections through data mining

Transport-based single frame super resolution of very low resolution face images

3D Reconstruction in the presence of glasses by acoustic and stereo fusion

Deep sparse representation for robust image registration

Real-time part-based visual tracking via adaptive correlation filters

Beyond spatial pooling: Fine-grained representation learning in multiple domains

ℋC-search for structured prediction in computer vision

Revisiting kernelized locality-sensitive hashing for improved large-scale image retrieval

High-speed hyperspectral video acquisition with a dual-camera architecture

More about VLAD: A leap from Euclidean to Riemannian manifolds

Camera intrinsic blur kernel estimation: A reliable framework

Classifier learning with hidden information

Single target tracking using adaptive clustered decision trees and dynamic multi-level appearance models

Simultaneous video defogging and stereo reconstruction

Face alignment by coarse-to-fine shape searching

Learning deep representations for ground-to-aerial geolocalization

Unsupervised Simultaneous Orthogonal basis Clustering Feature Selection

Space-time tree ensemble for action recognition

Subgraph decomposition for multi-target tracking

Understanding image structure via hierarchical shape parsing

Coarse-to-fine region selection and matching

Label Consistent Quadratic Surrogate model for visual saliency prediction

Subgraph matching using compactness prior for robust feature correspondence

Pedestrian detection aided by deep learning semantic tasks

Multihypothesis trajectory analysis for robust visual tracking

Domain-size pooling in local descriptors: DSP-SIFT

Object detection by labeling superpixels

Fast 2D border ownership assignment

From single image query to detailed 3D reconstruction

Fast and flexible convolutional sparse coding

Iteratively reweighted graph cut for multi-label MRFs with non-convex priors

Pairwise geometric matching for large-scale object retrieval

Deep convolutional neural fields for depth estimation from a single image

Data-driven sparsity-based restoration of JPEG-compressed images in dual transform-pixel domain

TVSum: Summarizing web videos using titles

Understanding deep image representations by inverting them

Single image super-resolution from transformed self-exemplars

Constrained planar cuts - Object partitioning for point clouds

A weighted sparse coding framework for saliency detection

Handling motion blur in multi-frame super-resolution

Approximate nearest neighbor fields in video

Inverting RANSAC: Global model detection via inlier rate estimation

Robust multi-image based blind face hallucination

On learning optimized reaction diffusion processes for effective image restoration

A flexible tensor block coordinate ascent scheme for hypergraph matching

TILDE: A Temporally Invariant Learned DEtector

A maximum entropy feature descriptor for age invariant face recognition

Sense discovery via co-clustering on images and text

An approximate shading model for object relighting

Deep domain adaptation for describing people based on fine-grained clothing attributes

A convolutional neural network cascade for face detection

Visual vibrometry: Estimating material properties from small motions in video

Jointly learning heterogeneous features for RGB-D activity recognition

Convolutional neural networks at constrained time cost

Fine-grained histopathological image analysis via robust segmentation and large-scale retrieval

ℓ0TV: A new method for image restoration in the presence of impulse noise

Modeling video evolution for action recognition

Long-term correlation tracking

Joint tracking and segmentation of multiple targets

RGBD-fusion: Real-time high precision depth recovery

Modeling deformable gradient compositions for single-image super-resolution

Generalized video deblurring for dynamic scenes

Active Pictorial Structures

Ego-surfing first person videos

Visual saliency based on multiscale deep features

Recovering inner slices of translucent objects by multi-frequency illumination

Local high-order regularization on data manifolds

Fine-grained classification of pedestrians in video: Benchmark and state of the art

Curriculum learning of multiple tasks

How many bits does it take for a stimulus to be salient?

Discrete optimization of ray potentials for semantic 3D reconstruction

SOLD: Sub-optimal low-rank decomposition for efficient video segmentation

On the appearance of translucent edges

On pairwise costs for network flow multi-object tracking

Fine-grained recognition without part annotations

Robust reconstruction of indoor scenes

2014 IEEE Conference on Computer Vision and Pattern Recognition

2013 IEEE Conference on Computer Vision and Pattern Recognition

2012 IEEE Conference on Computer Vision and Pattern Recognition

2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition

2009 IEEE Conference on Computer Vision and Pattern Recognition

2008 IEEE Conference on Computer Vision and Pattern Recognition

2007 IEEE Conference on Computer Vision and Pattern Recognition

2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)

2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)

Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004.

2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings.

Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001

Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662)

Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)

Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition

Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231)

Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition

1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition

Proceedings of IEEE Conference on Computer Vision and Pattern Recognition

Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition

Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition

Proceedings CVPR '89: IEEE Computer Society Conference on Computer Vision and Pattern Recognition

Proceedings CVPR '88: The Computer Society Conference on Computer Vision and Pattern Recognition

Efficient minimal-surface regularization of perspective depth maps in variational stereo

Content Provider	IEEE Xplore Digital Library
Author	Graber, G. Balzer, J. Soatto, S. Pock, T.
Copyright Year	2015
Description	Author affiliation: Graz Univ. of Technol., Graz, Austria (Graber, G.; Pock, T.) \|\| UCLA, Los Angeles, CA, USA (Balzer, J.; Soatto, S.)
Abstract	We propose a method for dense three-dimensional surface reconstruction that leverages the strengths of shape-based approaches, by imposing regularization that respects the geometry of the surface, and the strength of depth-map-based stereo, by avoiding costly computation of surface topology. The result is a near real-time variational reconstruction algorithm free of the staircasing artifacts that affect depth-map and plane-sweeping approaches. This is made possible by exploiting the gauge ambiguity to design a novel representation of the regularizer that is linear in the parameters and hence amenable to be optimized with state-of-the-art primal-dual numerical schemes.
Starting Page	511
Ending Page	520
File Size	2391982
Page Count	10
File Format	PDF
ISSN	10636919
e-ISBN	9781467369640
DOI	10.1109/CVPR.2015.7298649
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2015-06-07
Publisher Place	USA
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Content Type	Text
Resource Type	Article
Subject	Computer Vision and Pattern Recognition Software

Central Library (ISO-9001:2015 Certified)
Indian Institute of Technology Kharagpur
Kharagpur, West Bengal, India | PIN - 721302

See location in the Map
03222 282435
Mail: support@ndl.gov.in

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in