iccv 2011 论文列表IEEE International Conference on Computer Vision, ICCV 2011, Barcelona, Spain, November 6-13, 2011. |
Scalable object-class retrieval with approximate and top-k ranking.
Ask the locals: Multi-way local pooling for image recognition.
Efficient learning of sparse, distributed, convolutional feature representations for object recognition.
Integrating local classifiers through nonlinear dynamics on label graphs with an application to image segmentation.
N-best maximal decoders for part models.
Generalized ordering constraints for multilabel optimization.
Probabilistic image segmentation with closedness constraints.
Regression from local features for viewpoint and pose estimation.
A "string of feature graphs" model for recognition of complex activities in natural videos.
Shared shape spaces.
BiCoS: A Bi-level co-segmentation method for image classification.
Isotonic CCA for sequence alignment and activity recognition.
ORB: An efficient alternative to SIFT or SURF.
HMDB: A large video database for human motion recognition.
BRISK: Binary Robust invariant scalable keypoints.
Markov Random Field-based fitting of a subdivision-based geometric atlas.
An automatic assembly and completion framework for fragmented skulls.
Multiclass recognition and part localization with humans in the loop.
Robust topological features for deformation invariant image matching.
Digital anti-aging in face images.
The generalized trace-norm and its application to structure-from-motion problems.
Pose, illumination and expression invariant pairwise face-similarity measure via Doppelgänger list comparison.
In defense of soft-assignment coding.
Dynamic fluid surface acquisition using a camera array.
Globally optimal solution to multi-object tracking with merged measurements.
Dynamic subspace-based coordinated multicamera tracking.
Optimal estimation of vanishing points in a Manhattan world.
Multiview structure from motion in trajectory space.
Multi-task low-rank affinity pursuit for image segmentation.
The power of comparative reasoning.
Density-aware person detection and tracking in crowds.
Video parsing for abnormality detection.
Learning cross-modality similarity for multinomial data.
Efficient similarity search for covariance matrices via the Jensen-Bregman LogDet Divergence.
Optical flow estimation using learned sparse model.
Parallelizable inpainting and refinement of diffeomorphisms using Beltrami holomorphic flow.
Maximizing all margins: Pushing face recognition with Kernel Plurality.
Low order dynamics embedding for high dimensional time series.
Probabilistic 3D object recognition with both positive and negative evidences.
Double window optimisation for constant time visual SLAM.
Unsupervised learning of a scene-specific coarse gaze estimator.
Image based detection of geometric changes in urban environments.
Tight convex relaxations for vector-valued labeling problems.
DTAM: Dense tracking and mapping in real-time.
Efficient Orthogonal Matching Pursuit using sparse random projections for scene and video classification.
Point-based calibration using a parametric representation of the general imaging model.
A FACS valid 3D dynamic action unit database with applications to 3D dynamic morphable facial modeling.
Kinecting the dots: Particle based scene flow from depth sensors.
Evaluation of image features using a photorealistic virtual world.
Semi-supervised learning and optimization for hypergraph matching.
Unsupervised and semi-supervised learning via ℓ1-norm graph.
A robust pipeline for rapid feature-based pre-alignment of dense range scans.
Tabula rasa: Model transfer for object category detection.
On the repeatability of the local reference frame for partial shape matching.
A convex framework for image segmentation with moment constraints.
Manhattan scene understanding using monocular, stereo, and 3D features.
Latent structured models for human pose estimation.
Center-surround divergence of feature statistics for salient object detection.
Content-based photo quality assessment.
Delta-Dual Hierarchical Dirichlet Processes: A pragmatic abnormal behaviour detector.
Structured class-labels in random forests for semantic image labelling.
Color photometric stereo for multicolored surfaces.
Generalized background subtraction based on hybrid inference by belief propagation and Bayesian filtering.
iGroup: Weakly supervised image and video grouping.
High quality image reconstruction from RAW and JPEG image pair.
Correspondence free registration through a point-to-model distance minimization.
Object detection and segmentation from joint embedding of parts and pixels.
Geometrically consistent elastic matching of 3D shapes: A linear programming solution.
Dense disparity maps from sparse disparity measurements.
HEAT: Iterative relevance feedback with one million images.
Image segmentation by figure-ground composition into maximal cliques.
A dimensionality result for multiple homography matrices.
Convex multi-region probabilistic segmentation with shape prior in the isometric log-ratio transformation space.
Full DOF tracking of a hand interacting with an object by modeling occlusions and physical constraints.
Realtime multibody visual SLAM with a smoothly moving monocular camera.
Discriminative learning of relaxed hierarchy for large-scale visual recognition.
Physically-based motion models for 3D tracking: A convex formulation.
Handling label noise in video classification via multiple instance learning.
Text-based image retrieval using progressive multi-instance learning.
Linear dependency modeling for feature fusion.
Automated corpus callosum extraction via Laplace-Beltrami nodal parcellation and intrinsic geodesic curvature flows on surfaces.
Detailed reconstruction of 3D plant root shape.
Adaptive deconvolutional networks for mid and high level feature learning.
Building a better probabilistic model of images by factorization.
Discriminative figure-centric models for joint action localization and recognition.
Key-segments for video object segmentation.
Material-specific user colour profiles from imaging spectroscopy data.
Localized principal component analysis based curve evolution: A divide and conquer approach.
Active geodesics: Region-based active contour segmentation with a global edge-based constraint.
Basis constrained 3D scene flow on a dynamic proxy.
Random ensemble metrics for object recognition.
Home 3D body scans from noisy image and range data.
Discriminative multi-manifold analysis for face recognition from a single training sample per person.
Contour Code: Robust and efficient multispectral palmprint encoding for human recognition.
Source constrained clustering.
Fourier Active Appearance Models.
Dense one-shot 3D reconstruction by detecting continuous regions with parallel line projection.
Similarity invariant classification of events by KL divergence minimization.
Unstructured light scanning to overcome interreflections.
Multiscale, curvature-based shape representation for surfaces.
Segmentation as selective search for object recognition.
Level-set person segmentation and tracking with multi-region appearance models and top-down shape information.
Multiclass transfer learning from unconstrained priors.
Aerial 3D reconstruction with line-constrained dynamic programming.
Robust and efficient parametric face alignment.
Linear time offline tracking and lower envelope algorithms.
Strong supervision from weak annotation: Interactive training of deformable part models.
The NBNN kernel.
Geometrically consistent stereo seam carving.
Image representation by active curves.
Learning specific-class segmentation from diverse data.
A graph-matching kernel for object categorization.
Assessing the aesthetic quality of photographs using generic image descriptors.
A selective spatio-temporal interest point detector for human action recognition in complex scenes.
Blurring-invariant Riemannian metrics for comparing signals and images.
Diagonal preconditioning for first order primal-dual algorithms in convex optimization.
Modeling image similarity by Gaussian mixture models and the Signature Quadratic Form Distance.
Face reconstruction in the wild.
Spatio-temporal clustering of probabilistic region trajectories.
Towards accurate and efficient representation of image irradiance of convex-Lambertian objects under unknown near lighting.
The medial feature detector: Stable regions from image boundaries.
Feature seeding for action recognition.
Linear stereo matching.
Incremental on-line semi-supervised learning for segmenting the left ventricle of the heart from ultrasound data.
Variational recursive joint estimation of dense scene structure and camera motion from monocular high speed traffic sequences.
Stereo time-of-flight.
Exploring regularized feature selection for person specific face verification.
Decision tree fields.
Active clustering of document fragments using information derived from both images and catalogs.
Speeded-up, relaxed spatial matching.
Face recognition via local sparse coding.
Compact correlation coding for visual object categorization.
Complementary hashing for approximate nearest neighbor search.
High quality depth map upsampling for 3D-TOF cameras.
Latent Low-Rank Representation for subspace segmentation and feature extraction.
Coherency Sensitive Hashing.
Scale space for central catadioptric systems: Towards a generic camera feature extractor.
Gradient-based learning of higher-order image features.
Object segmentation in video: A hierarchical variational approach for turning point trajectories into dense regions.
Scan rectification for structured light range sensors with rolling shutters.
A revisit to cost aggregation in stereo matching: How far can we reduce its computational redundancy?
Unsupervised metric learning for face identification in TV video.
Learning occlusion with likelihoods for visual tracking.
Describing people: A poselet-based approach to attribute classification.
Who Blocks Who: Simultaneous clothing segmentation for grouping images.
Locally rigid globally non-rigid surface registration.
Learning component-level sparse representation using histogram information for image classification.
Scale and object aware image retargeting for thumbnail browsing.
Spectral learning of latent semantics for action recognition.
Shape-constrained Gaussian process regression for facial-point-based head-pose normalization.
Modeling spatial layout with fisher vectors for image categorization.
Exemplar extraction using spatio-temporal hierarchical agglomerative clustering for face recognition in video.
Learning parameterized histogram kernels on the simplex manifold for image and action classification.
Spatial pyramid co-occurrence for image classification.
End-to-end scene text recognition.
Recognising spontaneous facial micro-expressions.
Discriminative high order SVD: Adaptive tensor subspace selection for image classification, clustering, and retrieval.
Multi-class semi-supervised SVMs with Positiveness Exclusive Regularization.
The truth about cats and dogs.
Action recognition in videos acquired by a moving camera using motion decomposition of Lagrangian particle trajectories.
Decoupling photometry and geometry in dense variational camera calibration.
Actively selecting annotations among objects and attributes.
Annotator rationales for visual recognition.
Superpixels via pseudo-Boolean optimization.
Efficient parallel message computation for MAP inference.
Extracting foreground masks towards object recognition.
An adaptive coupled-layer visual model for robust visual tracking.
Fast template matching in non-linear tone-mapped images.
Unwrapping low-rank textures on generalized cylindrical surfaces.
Single-shot high dynamic range imaging with conventional camera hardware.
Human action recognition by learning bases of action attributes and parts.
Superpixel tracking.
Pushing the limits of digital imaging using structured illumination.
Scene recognition and weakly supervised object localization with deformable part-based models.
RECON: Scale-adaptive robust estimation via Residual Consensus.
3D scene flow estimation with a rigid motion prior.
Video Primal Sketch: A generic middle-level representation of video.
Viewpoint-aware object detection and pose estimation.
Introducing total curvature for image processing.
Centralized sparse representation for image restoration.
Panoramic stereo video textures.
Outdoor human motion capture using inverse kinematics and von mises-fisher sampling.
Gerard Pons-Moll Andreas Baak Juergen Gall Laura Leal-Taixé Meinard Müller Hans-Peter Seidel Bodo Rosenhahn
Data-driven crowd analysis in videos.
A joint learning framework for attribute models and object descriptions.
Dynamic texture classification using dynamic fractal analysis.
Stereo reconstruction using high order likelihood.
Simultaneous localization, mapping and deblurring.
Tracking by Sampling Trackers.
A geometric solver for calibrated stereo egomotion.
Refractive shape from light field distortion.
Cluster-based color space optimizations.
Gaussian process regression flow for analysis of motion trajectories.
Graph mode-based contextual kernels for robust SVM tracking.
StereoCut: Consistent interactive object selection in stereo image pairs.
Spatiotemporal oriented energies for spacetime stereo.
Discovering favorite views of popular places with iconoid shift.
Variational stereo in dynamic illumination.
Modeling temporal coherence for optical flow.
Shading-based dynamic shape refinement from multi-view video under general illumination.
Blurred target tracking by Blur-driven Tracker.
A data-driven approach for real-time full body pose reconstruction from a depth camera.
Predicting occupation via human clothing and contexts.
What an image reveals about material reflectance.
Building large urban environments from unstructured point data.
Face recognition based on non-corresponding region matching.
Learning a category independent object detection cascade.
Dynamic and hierarchical multi-structure geometric model fitting.
Human activity prediction: Early recognition of ongoing activities from streaming videos.
Salient object detection by composition.
A graph cut algorithm for higher-order Markov Random Fields.
Positive definite dictionary learning for region covariances.
Action recognition using rank-1 approximation of Joint Self-Similarity Volume.
Domain adaptation for object recognition: An unsupervised approach.
Semantic contours from inverse detectors.
From contours to 3D object detection and pose estimation.
Optimizing polynomial solvers for minimal geometry problems.
Robust object pose estimation via statistical manifold modeling.
Learning equivariant structured output SVM regressors.
Fast articulated motion tracking using a sums of Gaussians body model.
Exploiting the Manhattan-world assumption for extrinsic self-calibration of multi-modal sensor networks.
Fully automatic pose-invariant face recognition via 3D pose normalization.
Tasting families of features for image classification.
Trajectory reconstruction from non-overlapping surveillance cameras with relative depth ordering constraints.
Fusing generic objectness and visual saliency for salient object detection.
Learning a mixture of sparse distance metrics for classification and dimensionality reduction.
What characterizes a shadow boundary under the sun and sky?
Recursive MDL via graph cuts: Application to segmentation.
2D-3D fusion for layer decomposition of urban facades.
From images to scenes: Compressing an image cluster into a single scene model for place recognition.
Slow feature analysis and decorrelation filtering for separating correlated sources.
Multimodal templates for real-time detection of texture-less objects in heavily cluttered scenes.
Stefan Hinterstoisser Stefan Holzer Cedric Cagniart Slobodan Ilic Kurt Konolige Nassir Navab Vincent Lepetit
Simultaneous correspondence and non-rigid 3D reconstruction of the coronary tree from single X-ray images.
Efficient algorithm for low-rank matrix factorization with missing components and performance comparison of latest algorithms.
Multi-label visual classification with label exclusive context.
Simultaneous multi-body stereo and segmentation.
Informative feature selection for object recognition via Sparse PCA.
Active scene recognition with vision and language.
Kernel non-rigid structure from motion.
Unsupervised metric learning by Self-Smoothing Operator.
A chains model for localizing participants of group activities in videos.
Learning spatiotemporal graphs of human activities.
Close the loop: Joint blind image restoration and recognition with sparse representation prior.
Discovering object instances from scenes of Daily Living.
A linear subspace learning approach via sparse coding.
Probabilistic group-level motion analysis and scenario recognition.
Means in spaces of tree-like shapes.
Accurate 3D pose estimation from a single depth image.
Articulated part-based model for joint object detection and pose estimation.
Robust unsupervised motion pattern inference from video and applications.
Sparse dictionary-based representation and recognition of action attributes.
Inferring social relations from visual concepts.
Multiplexed illumination for scene recovery in the presence of global illumination.
Temporally coded flash illumination for motion deblurring.
Multiview 3D warps.
Fast image-based localization using direct 2D-to-3D matching.
Non-stationary correction of optical aberrations.
Correlative multi-label multi-instance image annotation.
Weakly supervised semantic segmentation with a multi-image model.
Self-calibrating depth from refraction.
Treat samples differently: Object tracking with semi-supervised online CovBoost.
Multi-hypothesis motion planning for visual object tracking.
Large-scale image annotation using visual synset.
Local Intensity Order Pattern for feature description.
Multi-observation visual recognition via joint dynamic sparse representation.
Robust consistent correspondence between 3D non-rigid shapes based on "Dual Shape-DNA".
Pose estimation from reflections for specular surface recovery.
Dynamic Manifold Warping for view invariant action recognition.
Conditional Random Fields for multi-camera object detection.
Sparse multi-task regression and feature selection to identify brain imaging predictors for memory performance.
Dyadic transfer learning for cross-domain image classification.
Fisher Discrimination Dictionary Learning for sparse representation.
Multi-view repetitive structure detection.
Automatic construction of an action video shot database using web videos.
Recognizing jumbled images: The role of local and global information in image classification.
Extracting adaptive contextual cues from unlabeled regions.
Relative attributes.
Handling outliers in non-blind image deconvolution.
Parsing video events with goal inference and intent prediction.
From learning models of natural image patches to whole image restoration.
Sparse representation or collaborative representation: Which helps face recognition?
Fast removal of non-uniform camera shake.
Optimal landmark detection using shape models and branch and bound.
Structure-sensitive superpixels via geodesic distance.
Imaging via three-dimensional compressive sampling (3DCS).
Automated articulated structure and 3D shape recovery from point correspondences.
Diffusion runs low on persistence fast.
Efficient regression of general-activity human poses from depth images.
Understanding egocentric activities.
An adversarial optimization approach to efficient outlier removal.
Sorted Random Projections for robust texture classification.
A Direct Least-Squares (DLS) method for PnP.
Smooth object retrieval using a bag of boundaries.
Segmentation from a box.
Edge foci interest points.
Multi-view 3D reconstruction for scenes under the refractive plane with known vertical direction.
Weakly supervised object detector learning with model drift detection.
Understanding scenes on many levels.
Object recoloring based on intrinsic image estimation.
Viewpoint invariant 3D landmark model inference from monocular 2D images using higher-order priors.
Visual word disambiguation by semantic contexts.
Minimum near-convex decomposition for robust shape representation.
Generalized subgraph preconditioners for large-scale bundle adjustment.
Video from a single coded exposure photograph using a learned over-complete dictionary.
A 3D Laplacian-driven parametric deformable model.
Simplification of 3D morphable models.
Struck: Structured output tracking with kernels.
Generalized roof duality for pseudo-boolean optimization.
Learning nonlinear distance functions using neural network for regression with application to robust human age estimation.
Learning universal multi-view age estimator using video context.
Salient Object Detection using concavity context.
Learning to predict the perceived visual quality of photos.
A theory of Coprime Blurred Pairs.
Contextual weighting for vocabulary tree based image retrieval.
3D reconstruction of a smooth articulated trajectory from a monocular image sequence.
Perturb-and-MAP random fields: Using discrete optimization to learn and sample from energy models.
Diffuse reflectance imaging with astronomical applications.
Segmentation fusion for connectomics.
Distributed cosegmentation via submodular optimization on anisotropic diffusion.
Birdlets: Subordinate categorization using volumetric primitives and pose-normalized appearance.
Inferring human gaze from appearance via adaptive linear regression.
A new distance for scale-invariant 3D shape recognition and registration.
Tracking multiple people under global appearance constraints.
Revisiting radiometric calibration for color computer vision.
Real-time indoor scene understanding using Bayesian filtering with motion cues.
Action recognition in cluttered dynamic scenes using Pose-Specific Part Models.
Automatic salient object extraction with contextual cue.
CARD: Compact And Real-time Descriptors.
Ensemble of exemplar-SVMs for object detection and beyond.
Hough-based tracking of non-rigid objects.
Learning to cluster using high order graphical models with latent variables.
Fusing visual and range imaging for object class recognition.
Source camera identification using Auto-White Balance approximation.
A general preconditioning scheme for difference measures in deformable registration.
Unsupervised learning of event AND-OR grammar and semantics from video.
Optimal object matching via convexification and composition.
Silhouette-based object phenotype recognition using 3D shape priors.
Illumination demultiplexing from a single image.
Are spatial and global constraints really necessary for segmentation?
A nonparametric Riemannian framework on tensor field with application to foreground segmentation.