iccv 2009 论文列表IEEE 12th International Conference on Computer Vision, ICCV 2009, Kyoto, Japan, September 27 - October 4, 2009. |
Estimating contact dynamics.
Efficient, high-quality image contour detection.
Large-scale privacy protection in Google Street View.
Andrea Frome German Cheung Ahmad Abdulkader Marco Zennaro Bo Wu Alessandro Bissacco Hartwig Adam Hartmut Neven Luc Vincent
Studying brain morphometry using conformal equivalence class.
Packing bag-of-features.
Shape analysis with multivariate tensor-based morphometry and holomorphic differentials.
Image compression with anisotropic triangulations.
Ground truth dataset and baseline evaluations for intrinsic image algorithms.
Riemannian Bayesian estimation of diffusion tensor images.
A global perspective on MAP inference for low-level vision.
Piecewise-consistent color mappings of images acquired under various conditions.
Seeing through water: Image restoration using model-based tracking.
An algebraic model for fast corner detection.
Shape guided contour grouping with particle filters.
Weighted graph characteristics from oriented line graph polynomials.
Non-local sparse models for image restoration.
The Swap and Expansion moves revisited and fused.
Detecting interpretable and accurate scale-invariant keypoints.
Deformable model fitting with a mixture of local experts.
Optimizing parametric total variation models.
A framework for visual saliency detection with applications to image thumbnailing.
Finding good composition in panoramic scenes.
Image restoration using online photo collections.
Scale invariance and noise in natural images.
Fast visibility restoration from a single color or gray level image.
GroupSAC: Efficient consensus in the presence of groupings.
Image saliency by isocentric curvedness and color.
Multimodal partial estimates fusion.
Recovering planar homographies between 2D shapes.
Multiscale symmetric part detection and grouping.
Shape-based recognition of 3D point clouds in urban environments.
What is the best multi-stage architecture for object recognition?
Actionable information in vision.
Kernelized locality-sensitive hashing for scalable image search.
Unsupervised learning of high-order structural semantics from images.
Tensor completion for estimating missing values in visual data.
Learning to predict where humans look.
Efficient multi-label ranking for multi-class learning: Application to object recognition.
SCRAMSAC: Improving RANSAC's efficiency with a spatial consistency filter.
A robust elastic and partial matching metric for face recognition.
Exploiting uncertainty in random sample consensus.
Realtime background subtraction from dynamic scenes.
A hybrid generative/discriminative classification framework based on free-energy terms.
A Riemannian analysis of 3D nose shapes for partial human biometrics.
Minimizing energy functions on 4-connected lattices using elimination.
Incremental discriminative-analysis of canonical correlations for action recognition.
Image annotation using multi-label correlated Green's function.
Hierarchical learning for tubular structure parsing in medical imaging: A study on coronary arteries using 3D CT Angiography.
Building recognition using sketch-based representations and spectral graph matching.
Untangling fibers by quotient appearance manifold mapping for grayscale shape classification.
Discriminative generalized hough transform for object dectection.
A multi-sample, multi-tree approach to bag-of-words image representation for image retrieval.
A study on automatic age estimation using a large database.
Context by region ancestry.
Hierarchical Gaussianization for image classification.
Detection of human actions from a single example.
Landmark classification in large-scale image collections.
Least-squares congealing for large numbers of images.
Time series prediction by chaotic modeling of nonlinear dynamical systems.
Selection and context for action recognition.
Weakly supervised discriminative localization and classification: a joint learning process.
The dimensionality of scene appearance.
Mode-detection via median-shift.
A novel approach to expression recognition from non-frontal face images.
Computation complexity of branch-and-bound model selection.
Radiometric compensation using stratified inverses.
Piecewise planar stereo for image-based rendering.
Modeling 3D human poses from uncalibrated monocular images.
Diagram techniques for multiple view geometry.
3D open-surface shape correspondence for statistical shape modeling: Identifying topologically consistent landmarks.
Recovering the spatial layout of cluttered rooms.
The Self-Aware Matching Measure for stereo.
Structure and kinematics triangulation with a rolling shutter stereo rig.
Multiperspective stereo matching and volumetric reconstruction.
Seeing 3D objects in a single 2D image.
Template-free monocular reconstruction of deformable surfaces.
3D reconstruction from image collections with a single known focal length.
Single view reconstruction using shape grammars for urban environments.
High-resolution shape reconstruction from multiple range images based on simultaneous estimation of surface and motion.
Dense 3D reconstruction method using a single pattern for fast moving object.
Simultaneous color consistency and depth map estimation for radiometrically varying stereo images.
Component analysis approach to estimation of tissue intensity distributions of 3D images.
Simultaneous photometric invariance and shape recovery.
Color constancy using 3D scene geometry.
Moving in stereo: Efficient structure and motion using lines.
Improving accuracy of geometric parameter estimation using projected score method.
A new minimal solution to the relative pose of a calibrated stereo camera with small field of view overlap.
Hierarchical 3D diffusion wavelet shape priors.
Complete multi-view reconstruction of dynamic scenes from probabilistic fusion of narrow and wide baseline stereo.
Factorizing Scene Albedo and Depth from a Single Foggy Image.
Attached shadow coding: Estimating surface normals from shadows under unknown reflectance and lighting conditions.
BLOGS: Balanced local and global search for non-degenerate two view epipolar geometry.
Superresolution texture maps for multiview reconstruction.
Video Scene Understanding Using Multi-scale Analysis.
Structure- and motion-adaptive regularization for high accuracy optic flow.
Video scene categorization by 3D hierarchical histogram matching.
Correlated probabilistic trajectories for pedestrian motion detection.
Efficient privacy preserving video surveillance.
Real-time visual tracking via Incremental Covariance Tensor Learning.
Illumination aware MCMC Particle Filter for long-term outdoor multi-object simultaneous tracking and classification.
A direct approach for efficiently tracking with 3D morphable models.
Large displacement optical flow computation withoutwarping.
Robust motion estimation using trajectory spectrum learning: Application to aortic and mitral valve modeling from 4D TEE.
Spatio-temporal relationship match: Video structure comparison for recognition of complex human activities.
SURF Tracking.
Reconstructing 3D motion trajectories of particle swarms by global correspondence selection.
A new multiview spacetime-consistent depth recovery framework for free viewpoint video rendering.
Optical flow estimation on coarse-to-fine region-trees using discrete optimization.
Detection driven adaptive multi-cue integration for multiple human tracking.
Tracking a large number of objects from multiple views.
Keyframe-based real-time camera tracking.
Adaptive fragments-based tracking of non-rigid objects using level sets.
An information theoretic approach for tracker performance evaluation.
Robust tracking-by-detection using a detector confidence particle filter.
Learning deformable action templates from cluttered videos.
Detection and removal of chromatic moving shadows in surveillance scenarios.
Automatic annotation of human actions in video.
Robust facial feature tracking using selected multi-resolution linear predictors.
Tracking a hand manipulating an object.
Using individuality to track individuals: Clustering individual trajectories in crowds using local appearance and frequency trait.
A robust boosting tracker with minimum error bound in a co-training framework.
LabelMe video: Building a video database with human annotations.
The Normalized Subspace Inclusion: Robust clustering of motion subspaces.
Robust visual tracking using ℓ1 minimization.
Stabilizing motion tracking using retrieved motion priors.
Domain adaptive semantic diffusion for large scale context-based video annotation.
Absolute scale in structure from motion from a single vehicle mounted camera by exploiting nonholonomic constraints.
Complex volume and pose tracking with probabilistic dynamical models and visual hull constraints.
Video stabilization using robust feature trajectories.
Tracking in unstructured crowded scenes.
Estimating human shape and pose from a single image.
Joint pose estimator and feature learning for object detection.
Poselets: Body part detectors trained using 3D human pose annotations.
Human pose estimation using consistent max-covering.
Efficient human pose estimation via parsing a tree structure based human model.
Constructing implicit 3D shape models for pose estimation.
An algebraic approach to affine registration of point sets.
Simultaneous alignment and clustering for an image ensemble.
Matching as a non-cooperative game.
Wide-baseline image matching using Line Signatures.
Deformation invariant image matching by spectrally controlled diffeomorphic alignment.
Optimal correspondences from pairwise constraints.
Subspace matching: Unique solution to point matching with geometric constraints.
Feature correspondence and deformable object matching via agglomerative correspondence clustering.
Coarse registration of 3D surface triangulations based on moment invariants with applications to object alignment and identification.
Unsupervised face alignment by robust nonrigid mapping.
Robust matching of building facades under large viewpoint changes.
Non-iterative approach for fast and accurate vanishing point detection.
Body-relative navigation guidance using uncalibrated cameras.
A hand-held photometric stereo camera for 3-D modeling.
Display-camera calibration from eye reflections.
Background Subtraction for Freely Moving Cameras.
Shadow cameras: Reciprocal views from illumination masks.
Static multi-camera factorization using rigid motion.
Plane-based calibration of central catadioptric cameras.
Jointly estimating demographics and height with a calibrated camera.
Simultaneous camera pose and correspondence estimation in cornerless images.
A branch-and-bound algorithm for globally optimal calibration of a camera-and-rotation-sensor system.
A Markov Clustering Topic Model for mining behaviour in video.
Structural SVM for visual localization and continuous state estimation.
On optimizing subspaces for face recognition.
A biased sampling strategy for object categorization.
An algorithm for minimizing the Mumford-Shah functional.
Patch-based within-object classification.
Kernel map compression using generalized radial basis functions.
Spectral error correcting output codes for efficient multiclass recognition.
Efficient indexing for large scale visual search.
Heterogeneous feature machines for visual recognition.
A near optimal acceptance-rejection algorithm for exact cross-correlation search.
Efficient subset selection via the kernelized Rényi distance.
Consensus set maximization with guaranteed global optimality for robust geometry estimation.
Is a detector only good for detection?
Which faces to tag: Adding prior constraints into active learning.
Face recognition with contiguous occlusion using markov random fields.
Evaluating information contributions of bottom-up and top-down processes.
Face alignment through subspace constrained mean-shifts.
Optimal multiple surfaces searching for video/image resizing - a graph-theoretic approach.
RankBoost with l1 regularization for facial expression recognition and intensity estimation.
Incremental action recognition using feature-tree.
Active Appearance Models with Rotation Invariant Kernels.
Learning actions from the Web.
Detecting objects in large image collections and videos by efficient subimage retrieval.
Top-down color attention for object recognition.
Bayesian selection of scaling laws for motion modeling in images.
A probabilistic framework for partial intrinsic symmetries in geometric data.
Unlabeled data improvesword prediction.
A latent model of discriminative aspect.
Feature-centric Efficient Subwindow Search.
Quantifying contextual information for object detection.
Fast realistic multi-action recognition using mined dense spatio-temporal features.
Automatic learning and extraction of multi-local features.
Active subspace learning.
A theory of active object localization.
The One-Shot similarity kernel.
Learning based digital matting.
Analysis of orientation and scale in smoothly varying textures.
Efficient segmentation using feature-based graph partitioning active contours.
Non-negative matrix factorization of partial track data for motion segmentation.
Robust image segmentation using learned priors.
Label set perturbation for MRF based neuroimaging segmentation.
Texel-based texture segmentation.
Video object segmentation by tracking regions.
FLoSS: Facility location for subspace segmentation.
Saliency driven total variation segmentation.
Robust graph-cut scene segmentation and reconstruction for free-viewpoint video of complex dynamic scenes.
Non-rigid object localization and segmentation using eigenspace representation.
Automatic ovarian follicle quantification from 3D ultrasound data using global/local context with database guided segmentation.
Non-Euclidean image-adaptive Radial Basis Functions for 3D interactive segmentation.
LIVEcut: Learning-based interactive video segmentation by evaluation of multiple propagated cues.
Scene shape priors for superpixel segmentation.
Level set segmentation with both shape and intensity priors.
Joint optimization of segmentation and appearance models.
Segmentation, ordering and multi-object tracking using graphical models.
Associative hierarchical CRFs for object class image segmentation.
Power watersheds: A new image segmentation framework extending graph cuts, random walker and optimal spanning forest.
Implicit color segmentation features for pedestrian and object detection.
Beyond connecting the dots: A polynomial-time algorithm for segmentation and boundary estimation with imprecise user input.
Robust dynamical model for simultaneous registration and segmentation in a variational framework: A Bayesian approach.
Image segmentation with simultaneous illumination and reflectance estimation: An energy minimization approach.
Gradient domain layer separation under independent motion.
Multiple view semantic segmentation for street view images.
Spectral clustering of linear subspaces for motion segmentation.
Class segmentation and object localization with superpixel neighborhoods.
Convex multi-region segmentation on manifolds.
The infinite Hidden Markov random field model.
Convex optimization for multi-class image labeling with a novel family of total variation based regularizers.
Incremental Multiple Kernel Learning for object recognition.
Beyond the Euclidean distance: Creating effective visual codebooks using the Histogram Intersection Kernel.
Learning long term face aging patterns from partially dense aging databases.
I know what you did last summer: object-level auto-annotation of holiday snaps.
Multiple kernels for object detection.
Efficient discriminative local learning for object recognition.
Robust multilinear principal component analysis.
Sparse representation of cast shadows via l1-regularized least squares.
Active skeleton for non-rigid object detection.
Higher-order gradient descent by fusion-move graph cut.
Probabilistic occlusion boundary detection on spatio-temporal lattices.
Efficient discriminative learning of parts-based models.
Bayesian Poisson regression for crowd counting.
Joint learning of visual attributes, object classes and visual saliency.
Dimensionality reduction and principal surfaces via Kernel Map Manifolds.
Kernel active contour.
Graph cuts using a Riemannian metric induced by tensor voting.
Semi-Supervised Random Forests.
Is that you? Metric learning approaches for face identification.
Local Trinary Patterns for human action recognition.
Multi-scale object detection by clustering lines.
Directional statistics BRDF model.
Active segmentation with fixation.
Fast and robust Earth Mover's Distances.
Simultaneous and orthogonal decomposition of data using Multimodal Discriminant Analysis.
Recognizing actions by shape-motion prototype trees.
Group-sensitive multiple kernel learning for object categorization.
Learning image similarity from Flickr groups using Stochastic Intersection Kernel MAchines.
Constrained clustering by spectral kernel learning.
Robust fitting of multiple structures: The statistical learning approach.
Extending continuous cuts: Anisotropic metrics and expansion moves.
Fast Ray features for learning irregular shapes.
Resilient Subclass Discriminant Analysis.
Learning pedestrian dynamics from the real world.
A shape-based object class model for knowledge transfer.
Attribute and simile classifiers for face verification.
Compact signatures for high-speed interest point description and matching.
Super-resolution from a single image.
Light field video stabilization.
Time-constrained photography.
Coded aperture pairs for depth from defocus.
Sparsity induced similarity measure for label propagation.
TagProp: Discriminative metric learning in nearest neighbor models for image auto-annotation.
Local distance functions: A taxonomy, new algorithms, and an evaluation.
Similarity metrics for categorization: From monolithic to category specific.
Globally optimal segmentation of multi-region objects.
Image segmentation with a bounding box prior.
An efficient algorithm for Co-segmentation.
You'll never walk alone: Modeling social behavior for multi-target tracking.
Image sequence geolocation with human travel priors.
Storyboard sketches for Content Based Video Retrieval.
Combining efficient object localization and image classification.
Discriminative models for multi-class object layout.
On feature combination for multiclass object classification.
Learning a dense multi-view representation for detection, viewpoint classification and synthesis of object categories.
Stereo from flickering caustics.
Landmark-based sparse color representations for color transfer.
A linear formulation of shape from specular flow.
Estimating natural illumination from a single outdoor image.
A prism-based system for multispectral video acquisition.
Modeling deformable objects from a single depth camera.
Looking around the corner using transient imaging.
Shift-map image editing.
Filter flow.
Semi-automatic stereo extraction from video footage.
Action detection in complex scenes with spatial and temporal ambiguities.
Modelling activity global temporal dependencies using Time Delayed Probabilistic Graphical Model.
Quasi-periodic event analysis for social game retrieval.
Activity recognition using the velocity histories of tracked keypoints.
Globally optimal affine epipolar geometry from apparent contours.
Is dual linear self-calibration artificially ambiguous?
Reconstructing building interiors from images.
Building Rome in a day.
Learning with dynamic group sparsity.
Finding shareable informative patterns and optimal coding matrix for multiclass boosting.
Kernel methods for weakly supervised mean shift clustering.
Max-margin additive classifiers for detection.
An HOG-LBP human detector with partial occlusion handling.
Human detection using partial least squares analysis.
Curvature regularity for region-based image segmentation and inpainting: A linear programming relaxation.
Boundary ownership by lifting to 2.1D.
Decomposing a scene into geometric and semantically consistent regions.