CVPR 2007 - PDF Preprint Papers

CVPR 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition

3D Immersive Browsing | Click Here

Teaser Browsing | Click Here

Queue Browsing | Click Here

Title Browsing | Click Here

Wall of Fame | Most Viewed CVPR-2007 Paper

click to vote

CVPR
2007
IEEE

277views Computer Vision» more CVPR 2007»

Towards Fog-Free In-Vehicle Vision Systems through Contrast Restoration

2 years 3 months ago

Download perso.lcpc.fr

In foggy weather, the contrast of images grabbed by in-vehicle cameras in the visible light range is drastically degraded, which makes the current applications very sensitive to we...

Nicolas Hautière, Jean-Philippe Tarel and Didier ...

posted by jptarel

Read More »

Disclaimer and Copyright Notice

Sciweavers respects the rights of all copyright holders and in this regard, authors are only allowed to share a link to their preprint paper on their own website. Every contribution is associated with a desciptive image. It is the sole responsibility of the authors to ensure that their posted image is not copyright infringing. This service is compliant with IEEE copyright.

Id	Views	Title	Status
1	277	Towards Fog-Free In-Vehicle Vision Systems through Contrast Restoration
2	270	Shadow Removal in Front Projection Environments Using Object Tracking	claim
3	179	Partially Occluded Object-Specific Segmentation in View-Based Recognition
4	165	Removal of Image Artifacts Due to Sensor Dust
5	147	Mumford-Shah Meets Stereo: Integration of Weak Depth Hypotheses	claim
6	143	Quasi-Dense Wide Baseline Matching Using Match Propagation	claim
7	132	Multi-label image segmentation via max-sum solver	claim
8	124	Detecting Pedestrians by Learning Shapelet Features	claim
9	124	Principal Curvature-Based Region Detector for Object Recognition	claim
10	121	Detector adaptation by maximising agreement between independent data sources	claim
11	121	Nonlinear Dynamical Shape Priors for Level Set Segmentation	claim
12	120	Dynamic 3D Scene Analysis from a Moving Vehicle	claim
13	116	Delaunay Deformable Models: Topology-Adaptive Meshes Based on the Restricted Delaunay Triangulation	claim
14	115	A Fast 3D Correspondence Method for Statistical Shape Modeling	claim
15	114	Accurate Object Detection with Deformable Shape Models Learnt from Images	claim
16	114	Beyond bottom-up: Incorporating task-dependent influences into a computational model of spatial attention	claim
17	113	Autocalibration and Uncalibrated Reconstruction of Shape from Defocus	claim
18	111	Joint Priors for Variational Shape and Appearance Modeling	claim
19	111	Detection and segmentation of moving objects in highly dynamic scenes	claim
20	110	On Constant Focal Length Self-Calibration From Multiple Views	claim
21	109	Learning Local Image Descriptors	claim
22	107	Topology matching for 3D video compression
23	107	The Hyperbolic Geometry of Illumination-Induced Chromaticity Changes	claim
24	106	Light Fall-off Stereo	claim
25	105	An MRF and Gaussian Curvature Based Shape Representation for Shape Matching	claim
26	104	Evaluation of Cost Functions for Stereo Matching	claim
27	104	Multi-Use Light Engine - Fast Projection	claim
28	104	Groupwise Shape Registration on Raw Edge Sequence via A Spatio-Temporal Generative Model	claim
29	104	Generative Graphical Models for Maneuvering Object Tracking and Dynamics Analysis	claim
30	103	Learning to Detect A Salient Object	claim
31	102	Scene Segmentation and Categorization Using NCuts	claim
32	101	A Nonparametric Treatment for Location/Segmentation Based Visual Tracking	claim
33	101	Objects in Action: An Approach for Combining Action Understanding and Object Perception	claim
34	101	Gradient Intensity: A New Mutual Information-Based Registration Method	claim
35	101	Matching Local Self-Similarities across Images and Videos	claim
36	101	Kernel Sharing With Joint Boosting For Multi-Class Concept Detection	claim
37	101	Robust Local Features and their Application in Self-Calibration and Object Recognition on Embedded Systems
38	100	A Bayesian algorithm for tracking multiple moving objects in outdoor surveillance video	claim
39	100	Multiple View Image Reconstruction: A Harmonic Approach	claim
40	99	Implicit Active Contours Driven by Local Binary Fitting Energy	claim
41	99	Monocular and Stereo Methods for AAM Learning from Video	claim
42	99	Face Re-Lighting from a Single Image under Harsh Lighting Conditions	claim
43	98	High-dimensional statistical distance for region-of-interest tracking: Application to combining a soft geometric constraint with
44	97	Concurrent Multiple Instance Learning for Image Categorization	claim
45	97	A Human Action Recognition System for Embedded Computer Vision Application	claim
46	97	Spatio-Temporal Markov Random Field for Video Denoising	claim
47	97	Fast Keypoint Recognition in Ten Lines of Code	claim
48	94	Single View Human Action Recognition using Key Pose Matching and Viterbi Path Searching	claim
49	94	Graph Cut Based Optimization for MRFs with Truncated Convex Priors	claim
50	94	A Surface-Growing Approach to Multi-View Stereo Reconstruction	claim
51	94	Efficient Belief Propagation for Vision Using Linear Constraint Nodes	claim
52	94	Virtual Training for Multi-View Object Class Recognition	claim
53	93	Tracking Large Variable Numbers of Objects in Clutter	claim
54	92	Simultaneous Detection and Segmentation of Pedestrians using Top-down and Bottom-up Processing	claim
55	92	Belief Propagation in a 3D Spatio-temporal MRF for Moving Object Detection	claim
56	92	Projective Factorization of Multiple Rigid-Body Motions	claim
57	90	Free-Form Nonrigid Image Registration Using Generalized Elastic Nets	claim
58	90	What makes a good model of natural images?	claim
59	89	Generic Face Alignment using Boosted Appearance Model	claim
60	88	A Lagrangian Particle Dynamics Approach for Crowd Flow Segmentation and Stability Analysis	claim
61	88	A Closed-form Solution to 3D Reconstruction of Piecewise Planar Objects from Single Images	claim
62	85	Image Segmentation by Probabilistic Bottom-Up Aggregation and Cue Integration	claim
63	85	Segmenting Motions of Different Types by Unsupervised Manifold Clustering	claim
64	85	A Topic-Motion Model for Unsupervised Video Object Discovery	claim
65	83	Discovery of Collocation Patterns: from Visual Words to Visual Phrases	claim
66	83	Real-Time Projector Tracking on Complex Geometry Using Ordinary Imagery	claim
67	83	Scaled Motion Dynamics for Markerless Motion Capture	claim
68	83	Large scale vision-based navigation without an accurate global reconstruction	claim
69	83	Change Detection in a 3-d World	claim
70	82	Using Group Prior to Identify People in Consumer Images
71	82	Hierarchical Learning of Curves Application to Guidewire Localization in Fluoroscopy	claim
72	82	Nonnegative Tucker Decomposition	claim
73	81	Toward Flexible 3D Modeling using a Catadioptric Camera	claim
74	81	Learning Gaussian Conditional Random Fields for Low-Level Vision	claim
75	81	Discriminative Learning of Dynamical Systems for Motion Tracking	claim
76	81	Multi-Layer Background Subtraction Based on Color and Texture	claim
77	80	Marker-less Deformable Mesh Tracking for Human Shape and Motion Capture	claim
78	80	3D Probabilistic Feature Point Model for Object Detection and Recognition	claim
79	80	PrivacyCam: a Privacy Preserving Camera Using uCLinux on the Blackfin DSP	claim
80	79	Simultaneous Depth Reconstruction and Restoration of Noisy Stereo Images Using Non-local Pixel Distribution
81	79	3D LayoutCRF for Multi-View Object Class Recognition and Segmentation	claim
82	79	A Minutiae-based Fingerprint Individuality Model	claim
83	79	Unsupervised Learning of Hierarchical Semantics of Objects (hSOs)	claim
84	79	Joint Real-time Object Detection and Pose Estimation Using Probabilistic Boosting Network	claim
85	79	Probabilistic visibility for multi-view stereo	claim
86	79	Multi-Object Tracking Using Color, Texture and Motion	claim
87	79	A Multi-Resolution Dynamic Model for Face Aging Simulation	claim
88	78	Optimized Color Sampling for Robust Matting	claim
89	78	Adaptive Patch Features for Object Class Recognition with Learned Hierarchical Models	claim
90	78	A Topological Approach to Hierarchical Segmentation using Mean Shift	claim
91	77	Robust Click-Point Linking: Matching Visually Dissimilar Local Regions	claim
92	76	Epitomic Representation of Human Activities	claim
93	76	Learning Color Names from Real-World Images	claim
94	76	Multiview normal field integration using level set methods	claim
95	76	Fast Human Pose Estimation using Appearance and Motion via Multi-Dimensional Boosting Regression	claim
96	75	Metropolis-Hasting techniques for finite-element-based registration	claim
97	75	Automatic Face Recognition from Skeletal Remains	claim
98	75	Incorporating On-demand Stereo for Real Time Recognition	claim
99	74	Global Optimization for Shape Fitting	claim
100	74	Latent-Dynamic Discriminative Models for Continuous Gesture Recognition	claim
101	74	Single Image Motion Deblurring Using Transparency	claim
102	73	P3 & Beyond: Solving Energies with Higher Order Cliques	claim
103	73	Resolving Objects at Higher Resolution from a Single Motion-blurred Image	claim
104	73	A Linear Programming Approach for Multiple Object Tracking	claim
105	72	A Probabilistic Model for Object Recognition, Segmentation, and Non-Rigid Correspondence	claim
106	72	Utilizing Variational Optimization to Learn Markov Random Fields	claim
107	71	P3 & Beyond: Solving Energies with Higher Order Cliques	claim
108	71	Estimating Scale of a Scene from a Single Image Based on Defocus Blur and Scene Geometry	claim
109	71	Real-time Automatic Deceit Detection from Involuntary Facial Expressions	claim
110	71	Constrained Optimization for Retinal Curvature Estimation Using an Affine Camera	claim
111	71	Visual Curvature	claim
112	70	Combining Region and Edge Cues for Image Segmentation in a Probabilistic Gaussian Mixture Framework	claim
113	70	Biased Manifold Embedding: A Framework for Person-Independent Head Pose Estimation	claim
114	70	Toward A Discriminative Codebook: Codeword Selection across Multi-resolution	claim
115	69	Shape Variation-Based Frieze Pattern for Robust Gait Recognition	claim
116	69	Bilattice-based Logical Reasoning for Human Detection	claim
117	69	Beyond Local Appearance: Category Recognition from Pairwise Interactions of Simple Features	claim
118	69	3D Pose Estimation Based on Multiple Monocular Cues	claim
119	69	Visual Odometry System Using Multiple Stereo Cameras and Inertial Measurement Unit	claim
120	68	Robust Estimation of Texture Flow via Dense Feature Sampling	claim
121	68	Contextual Identity Recognition in Personal Photo Albums	claim
122	68	Robust Change-Detection by Normalised Gradient-Correlation	claim
123	68	Optimizing Distribution-based Matching by Random Subsampling	claim
124	68	Accurate, Dense, and Robust Multi-View Stereopsis	claim
125	67	Feature Extraction by Maximizing the Average Neighborhood Margin	claim
126	67	Face Recognition Using Kernel Ridge Regression	claim
127	67	Real-Time License Plate Recognition on an Embedded DSP-Platform	claim
128	67	Layered Graph Match with Graph Editing	claim
129	67	Cordless portable multi-view fringe projection system for 3D reconstruction	claim
130	66	Robust 3D Face Recognition Using Learned Visual Codebook	claim
131	66	Robust Face Alignment for Illumination and Pose Invariant Face Recognition	claim
132	66	Improving Part based Object Detection by Unsupervised, Online Boosting	claim
133	66	Leveraging temporal, contextual and ordering constraints for recognizing complex activities in video	claim
134	66	Integration of Motion Cues in Optical and Sonar Videos for 3-D Positioning	claim
135	66	Image Hallucination Using Neighbor Embedding over Visual Primitive Manifolds	claim
136	65	Skin Detail Analysis for Face Recognition	claim
137	65	OPTIMOL: automatic Online Picture collecTion via Incremental MOdel Learning	claim
138	65	Euclidean Path Modeling from Ground and Aerial Views	claim
139	65	Learning Conditional Random Fields for Stereo	claim
140	65	Fast 3D Scanning with Automatic Motion Compensation	claim
141	65	Detailed Human Shape and Pose from Images	claim
142	65	Closed-Loop Tracking and Change Detection in Multi-Activity Sequences	claim
143	65	Efficient Sampling of Disparity Space for Fast And Accurate Matching	claim
144	65	A Novel Approach to Improve Biometric Recognition Using Rank Level Fusion	claim
145	65	A linear estimation method for 3D pose and facial animation tracking	claim
146	64	EDA Approach for Model Based Localization and Recognition of Vehicles	claim
147	64	On-line Simultaneous Learning and Tracking of Visual Feature Graphs	claim
148	64	Texture-Preserving Shadow Removal in Color Images Containing Curved Surfaces	claim
149	64	Thermal Imaging of the Superficial Temporal Artery: An Arterial Pulse Recovery Model	claim
150	64	Differential Camera Tracking through Linearizing the Local Appearance Manifold	claim
151	64	Non-intrusive Iris Image Capturing System Using Light Stripe Projection and Pan-Tilt-Zoom Camera	claim
152	64	Connecting the Out-of-Sample and Pre-Image Problems in Kernel Methods	claim
153	63	Robust Occlusion Handling in Object Tracking	claim
154	63	Enhanced Level Building Algorithm for the Movement Epenthesis Problem in Sign Language Recognition	claim
155	63	Deformable Surface Tracking Ambiguities	claim
156	63	An Active Illumination and Appearance (AIA) Model for Face Alignment	claim
157	63	Multimodal Tracking for Smart Videoconferencing and Video Surveillance	claim
158	63	Physics-Based Person Tracking Using Simplified Lower-Body Dynamics	claim
159	63	Model-Guided Segmentation of 3D Neuroradiological Image Using Statistical Surface Wavelet Model	claim
160	63	Consistent Temporal Variations in Many Outdoor Scenes	claim
161	63	3D Face Recognition Founded on the Structural Diversity of Human Faces	claim
162	62	Composite Models of Objects and Scenes for Category Recognition	claim
163	62	Object retrieval with large vocabularies and fast spatial matching	claim
164	62	Robust Metric Reconstruction from Challenging Video Sequences	claim
165	62	Soft Edge Smoothness Prior for Alpha Channel Super Resolution	claim
166	62	Learning and Matching Line Aspects for Articulated Objects	claim
167	62	Discriminative Cluster Refinement: Improving Object Category Recognition Given Limited Training Data	claim
168	62	Bridging the Gap between Detection and Tracking for 3D Monocular Video-Based Motion Capture	claim
169	61	Map-Enhanced UAV Image Sequence Registration and Synchronization of Multiple Image Sequences	claim
170	61	Polarization and Phase-Shifting for 3D Scanning of Translucent Objects	claim
171	61	Illumination Multiplexing within Fundamental Limits	claim
172	61	Fast Terrain Classification Using Variable-Length Representation for Autonomous Navigation	claim
173	61	Capturing People in Surveillance Video	claim
174	60	Dense mirroring surface recovery from 1D homographies and sparse correspondences	claim
175	60	High-Speed Measurement of BRDF using an Ellipsoidal Mirror and a Projector	claim
176	60	Active Aperture Control and Sensor Modulation for Flexible Imaging	claim
177	60	ShadowCuts: Photometric Stereo with Shadows	claim
178	60	The Effect of Pixel-Level Fusion on Object Tracking in Multi-Sensor Surveillance Video	claim
179	60	Combining local and global motion models for feature point tracking	claim
180	60	Recognizing Groceries in situ Using in vitro Training Data	claim
181	60	Flexible Object Models for Category-Level 3D Object Recognition	claim
182	59	A contextual dissimilarity measure for accurate and efficient image search	claim
183	59	Human Detection via Classification on Riemannian Manifolds	claim
184	59	An end-to-end eChronicling System for Mobile Human Surveillance	claim
185	59	A Robust Warping Method for Fingerprint Matching	claim
186	59	A Benchmark for the Comparison of 3-D Motion Segmentation Algorithms	claim
187	59	Hierarchical Recognition of Human Activities Interacting with Objects	claim
188	58	Image representations beyond histograms of gradients: The role of Gestalt descriptors	claim
189	58	Discriminant Mutual Subspace Learning for Indoor and Outdoor Face Recognition	claim
190	58	Shape Statistics for Image Segmentation with Prior	claim
191	58	The effective resolution of correlation filters applied to natural scenes	claim
192	58	Multi-scale Structural Saliency for Signature Detection	claim
193	58	Topology Preserving Log-Unbiased Nonlinear Image Registration: Theory and Implementation	claim
194	57	Using Segmentation to Verify Object Hypotheses	claim
195	57	The Hierarchical Isometric Self-Organizing Map for Manifold Representation	claim
196	57	Online Detection of Fire in Video	claim
197	57	Sensor noise modeling using the Skellam distribution: Application to the color edge detection	claim
198	57	A Binning Scheme for Fast Hard Drive Based Image Search	claim
199	57	Two thresholds are better than one	claim
200	56	Eigenboosting: Combining Discriminative and Generative Information	claim
201	56	Online Learning Asymmetric Boosted Classifiers for Object Detection	claim
202	56	Recognizing Human Activities from Silhouettes: Motion Subspace and Factorial Discriminative Graphical Model	claim
203	56	Integrating Global and Local Structures: A Least Squares Framework for Dimensionality Reduction	claim
204	56	A Graph Cut Approach to Image Segmentation in Tensor Space	claim
205	56	Discriminant Additive Tangent Spaces for Object Recognition	claim
206	56	Multimodal Mean Adaptive Backgrounding for Embedded Real-Time Video Surveillance	claim
207	56	Learning Motion Categories using both Semantic and Structural Information	claim
208	56	On-the-fly Object Modeling while Tracking	claim
209	56	Optimal Dimensionality Discriminant Analysis and Its Application to Image Recognition	claim
210	56	Learning Features for Tracking	claim
211	56	Topology-preserving Geometric Deformable Model on Adaptive Quadtree Grid	claim
212	56	Modelling Objects using Distribution and Topology of Multiscale Region Pairs	claim
213	56	Thermal-Visible Video Fusion for Moving Target Tracking and Pedestrian Classification	claim
214	55	Semi-supervised Hierarchical Models for 3D Human Pose Reconstruction	claim
215	55	An Embodied User Interface for Increasing Physical Activities in Game	claim
216	55	Adaptive Distance Metric Learning for Clustering	claim
217	55	Segmenting Images on the Tensor Manifold	claim
218	55	Approximate Nearest Subspace Search with Applications to Pattern Recognition	claim
219	55	Face Recognition in Video: Adaptive Fusion of Multiple Matchers	claim
220	55	Simultaneous Object Detection and Segmentation by Boosting Local Shape Feature based Classifier	claim
221	55	Seamless Mosaicing of Image-Based Texture Maps	claim
222	55	Tracking as Repeated Figure/Ground Segmentation	claim
223	54	Real-Time Plane-Sweeping Stereo with Multiple Sweeping Directions	claim
224	54	Trace Ratio vs. Ratio Trace for Dimensionality Reduction	claim
225	54	Accurate Dynamic Sketching of Faces from Video	claim
226	54	Surveillance in Virtual Reality: System Design and Multi-Camera Control	claim
227	54	Segmental Hidden Markov Models for View-based Sport Video Analysis	claim
228	54	Multi-modal Clustering for Multimedia Collections	claim
229	54	Inferring 3D Volumetric Shape of Both Moving Objects and Static Background Observed by a Moving Camera	claim
230	54	Photometric Self-Calibration of a Projector-Camera System	claim
231	54	Tree-based Classifiers for Bilayer Video Segmentation	claim
232	54	Learning Visual Representations using Images with Captions	claim
233	54	An Adaptive Focal Connectivity Algorithm for Multifocus Fusion	claim
234	54	Isotropy, Reciprocity and the Generalized Bas-Relief Ambiguity	claim
235	54	Using Geometry Invariants for Camera Response Function Estimation	claim
236	53	Element Rearrangement for Tensor-Based Subspace Learning	claim
237	53	Hierarchical Structuring of Data on Manifolds	claim
238	53	Local Ensemble Kernel Learning for Object Category Recognition	claim
239	53	High Distortion and Non-Structural Image Matching via Feature Co-occurrence	claim
240	53	Visual Event Recognition in News Video using Kernel Methods with Multi-Level Temporal Alignment	claim
241	53	Sparse Kernels for Bayes Optimal Discriminant Analysis	claim
242	53	City-Scale Location Recognition	claim
243	53	Progressive Finite Newton Approach To Real-time Nonrigid Surface Detection	claim
244	53	Keypoint Descriptors for Matching Across Multiple Image Modalities and Non-linear Intensity Variations	claim
245	53	A Variational Approach to the Evolution of Radial Basis Functions for Image Segmentation	claim
246	53	Searching Video for Complex Activities with Finite State Models	claim
247	53	Learning a Spatially Smooth Subspace for Face Recognition	claim
248	53	Patch-based Image Correlation with Rapid Filtering	claim
249	53	Compositional Boosting for Computing Hierarchical Image Structures	claim
250	53	Face Recognition using Discriminatively Trained Orthogonal Rank One Tensor Projections	claim
251	53	Kernel Fukunaga-Koontz Transform Subspaces For Enhanced Face Recognition	claim
252	53	Object Tracking by Asymmetric Kernel Mean Shift with Automatic Scale and Orientation Selection	claim
253	53	Image Matching via Saliency Region Correspondences	claim
254	53	Quality-Driven Face Occlusion Detection and Recovery	claim
255	52	Automatic Person Detection and Tracking using Fuzzy Controlled Active Cameras	claim
256	52	A Real-Time ProCam System for Interaction with Chinese Ink-and-Wash Cartoons	claim
257	52	A Quasi-Minimal Model for Paper-Like Surfaces	claim
258	52	Image-Based Localization Using Hybrid Feature Correspondences	claim
259	52	Spectral Matting	claim
260	52	Multi-class object tracking algorithm that handles fragmentation and grouping	claim
261	52	Facial Expression Biometrics Using Tracker Displacement Features	claim
262	52	Learning the Compositional Nature of Visual Objects	claim
263	52	Regression tracking with data relevance determination	claim
264	52	Complex Salient Regions for Computer Vision Problems	claim
265	52	Joint Object Segmentation and Behavior Classification in Image Sequences	claim
266	52	Online Spatial-temporal Data Fusion for Robust Adaptive Tracking	claim
267	51	Fisher Kernels on Visual Vocabularies for Image Categorization	claim
268	51	Learning Dynamic Event Descriptions in Image Sequences	claim
269	51	Mapping Natural Image Patches by Explicit and Implicit Manifolds	claim
270	51	Multiple Class Segmentation Using A Unified Framework over Mean-Shift Patches	claim
271	51	Optimal Step Nonrigid ICP Algorithms for Surface Registration	claim
272	51	Saliency Detection: A Spectral Residual Approach	claim
273	51	Recognizing objects by piecing together the Segmentation Puzzle	claim
274	51	Region Classification with Markov Field Aspect Models	claim
275	51	A Hierarchical Model of Shape and Appearance for Human Action Classification	claim
276	50	Filtered Component Analysis to Increase Robustness to Local Minima in Appearance Models	claim
277	50	Image Classification with Segmentation Graph Kernels	claim
278	50	On Stabilisation of Parametric Active Contours	claim
279	50	Probabilistic Reverse Annotation for Large Scale Image Retrieval	claim
280	50	Imaging the Finger Force Direction	claim
281	50	Automatic Removal of Chromatic Aberration from a Single Image	claim
282	50	Solving Large Scale Binary Quadratic Problems: Spectral Methods vs. Semidefinite Programming	claim
283	50	Two-View Motion Segmentation from Linear Programming Relaxation	claim
284	50	Dimensionality Reduction and Clustering on Statistical Manifolds	claim
285	50	Statistical Shape Analysis of Multi-Object Complexes	claim
286	50	Variable Bandwidth Image Denoising Using Image-based Noise Models	claim
287	49	Trajectory Series Analysis based Event Rule Induction for Visual Surveillance	claim
288	49	Conformal Embedding Analysis with Local Graph Modeling on the Unit Hypersphere	claim
289	49	Improved Video Registration using Non-Distinctive Local Image Features	claim
290	49	Spatial selection for attentional visual tracking	claim
291	49	Algorithms for Batch Matrix Factorization with Application to Structure-from-Motion	claim
292	49	Scene-space Feature Detectors	claim
293	49	A Component-Based Approach to Hand Verification	claim
294	49	Active Visual Object Reconstruction using D-, E-, and T-Optimal Next Best Views	claim
295	49	Object Classification in Visual Surveillance Using Adaboost	claim
296	49	Real-Time Image Matching Based on Multiple View Kernel Projection	claim
297	49	Iterative MAP and ML Estimations for Image Segmentation	claim
298	49	Towards Automatic Photometric Correction of Casually Illuminated Documents	claim
299	49	Detecting Specular Surfaces on Natural Images	claim
300	49	Projector-Camera Guided Fast Environment Restoration of a Biofeedback System for Rehabilitation	claim
301	49	A minimal solution to the autocalibration of radial distortion	claim
302	49	Linear and Quadratic Subsets for Template-Based Tracking	claim
303	48	Discontinuity Preserving Filtering over Analytic Manifolds	claim
304	48	Combining Static Classifiers and Class Syntax Models for Logical Entity Recognition in Scanned Historical Documents	claim
305	48	An Exemplar Model for Learning Object Classes	claim
306	48	Variational Distance-Dependent Image Restoration	claim
307	48	Multimodal workbench for automatic surveillance applications	claim
308	48	Multi-modal Person Identification in a Smart Environment	claim
309	48	Shape from Planar Curves: A Linear Escape from Flatland	claim
310	48	Multimodal Surveillance: an Introduction	claim
311	48	Detecting Object Boundaries Using Low-, Mid-, and High-level Information	claim
312	48	LDV Sensing and Processing for Remote Hearing in a Multimodal Surveillance System	claim
313	47	Layered Depth Panoramas	claim
314	47	Audio-Visual Speech Fusion Using Coupled Hidden Markov Models	claim
315	47	Regularized Mixed Dimensionality and Density Learning in Computer Vision	claim
316	47	Focal Pre-Correction of Projected Image for Deblurring Screen Image	claim
317	47	Unsupervised Activity Perception by Hierarchical Bayesian Models	claim
318	47	Design and Deployment of Visible-Thermal Biometric Surveillance Systems	claim
319	47	Cast Shadow Removal Combining Local and Global Features	claim
320	47	Tracking-as-Recognition for Articulated Full-Body Human Motion Analysis	claim
321	47	Microphone Arrays as Generalized Cameras for Integrated Audio Visual Processing	claim
322	47	Kinematics from Lines in a Single Rolling Shutter Image	claim
323	47	Modeling Appearances with Low-Rank SVM	claim
324	47	Unsupervised Learning of Image Transformations	claim
325	47	Moving Forward in Structure From Motion	claim
326	47	Automated Individualization of Deformable Eye Region Model and Its Application to Eye Motion Analysis	claim
327	47	Multiphase Segmentation of Deformation using Logarithmic Priors	claim
328	47	A Unified Probabilistic Framework for Facial Activity Modeling and Understanding	claim
329	47	Simultaneous Covariance Driven Correspondence (CDC) and Transformation Estimation in the Expectation Maximization Framework	claim
330	46	Autocalibration via Rank-Constrained Estimation of the Absolute Quadric	claim
331	46	Multiple Target Tracking Using Spatio-Temporal Markov Chain Monte Carlo Data Association	claim
332	46	Discriminant Interest Points are Stable	claim
333	46	Accurate Object Localization with Shape Masks	claim
334	46	Geometric Modeling and Calibration of Planar Multi-Projector Displays Using Rational Bezier Patches	claim
335	46	A boosting regression approach to medical anatomy detection	claim
336	46	Real-time Planar Surface Segmentation in Disparity Space	claim
337	46	Revocable Fingerprint Biotokens: Accuracy and Security Analysis	claim
338	46	Part-based Face Recognition Using Near Infrared Images	claim
339	46	Hierarchical Matching of Deformable Shapes	claim
340	46	A Face Annotation Framework with Partial Clustering and Interactive Labeling	claim
341	46	Color Constancy using Natural Image Statistics	claim
342	46	3D Occlusion Inference from Silhouette Cues	claim
343	45	Content-Based Image Annotation Refinement	claim
344	45	Hybrid learning of large jigsaws	claim
345	45	Spatial-Depth Super Resolution for Range Images	claim
346	45	Multi-scale Features for Detection and Segmentation of Rocks in Mars Images	claim
347	45	Offline Signature Verification Using Online Handwriting Registration	claim
348	45	A Probabilistic Intensity Similarity Measure based on Noise Distributions	claim
349	45	Projector Calibration using Arbitrary Planes and Calibrated Camera	claim
350	45	On Constructing Facial Similarity Maps	claim
351	45	Riemannian Analysis of Probability Density Functions with Applications in Vision	claim
352	45	A Bio-inspired Learning Approach for the Classification of Risk Zones in a Smart Space	claim
353	45	Semantic Hierarchies for Visual Object Recognition	claim
354	45	Maximally Stable Colour Regions for Recognition and Matching	claim
355	45	Transfer Learning in Sign language	claim
356	45	OpenVL: Towards A Novel Software Architecture for Computer Vision	claim
357	45	Tracking in Low Frame Rate Video: A Cascade Particle Filter with Discriminative Observers of Different Lifespans	claim
358	45	Incremental Linear Discriminant Analysis Using Sufficient Spanning Set Approximations	claim
359	44	Pedestrian Detection in Infrared Images based on Local Shape Features	claim
360	44	On the Direct Estimation of the Fundamental Matrix	claim
361	44	Kernel-Based 3D Tracking	claim
362	44	Capturing long-range correlations with patch models	claim
363	44	Local Structure Detection with Orientation-invariant Radial Configuration	claim
364	44	Boosting Coded Dynamic Features for Facial Action Units and Facial Expression Recognition	claim
365	44	Robust Real-Time Visual SLAM Using Scale Prediction and Exemplar Based Feature Description	claim
366	44	Shape from Shading Under Various Imaging Conditions	claim
367	44	Simultaneous Matting and Compositing	claim
368	44	Towards Scalable Representations of Object Categories: Learning a Hierarchy of Parts	claim
369	44	Statistics of Infrared Images	claim
370	44	Realizing Super-Resolution with Superimposed Projection	claim
371	44	Fast, Approximately Optimal Solutions for Single and Dynamic MRFs	claim
372	44	Pyramid Match Hashing: Sub-Linear Time Indexing Over Partial Correspondences	claim
373	44	Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition	claim
374	44	Optimizing Binary MRFs via Extended Roof Duality	claim
375	44	Pose and Illumination Invariant Face Recognition in Video	claim
376	44	Fiber Tract Clustering on Manifolds With Dual Rooted-Graphs	claim
377	44	Modulation Domain Template Tracking	claim
378	44	Efficiently Determining Silhouette Consistency	claim
379	44	Inferring Temporal Order of Images From 3D Structure	claim
380	43	Recognizing Night Walkers Based on One Pseudoshape Representation of Gait	claim
381	43	Handwritten Carbon Form Preprocessing Based on Markov Random Field	claim
382	43	Learning Kernel Expansions for Image Classification	claim
383	43	Feasibility Boundary in Dense and Semi-Dense Stereo Matching	claim
384	43	Learning Visual Similarity Measures for Comparing Never Seen Objects	claim
385	43	Using Stereo Matching for 2-D Face Recognition Across Pose	claim
386	43	Artificial Complex Cells via the Tropical Semiring	claim
387	43	Efficient MRF Deformation Model for Non-Rigid Image Matching	claim
388	43	Learning GMRF Structures for Spatial Priors	claim
389	43	On the Blind Classification of Time Series	claim
390	43	Parameter Sensitive Detectors	claim
391	43	Precise Registration of 3D Models To Images by Swarming Particles	claim
392	43	Harmony in Motion	claim
393	43	Radiometric Calibration from Noise Distributions	claim
394	43	From Videos to Verbs: Mining Videos for Activities using a Cascade of Dynamical Systems	claim
395	43	Joint Optimization of Cascaded Classifiers for Computer Aided Detection	claim
396	43	Estimating Cluster Overlap on Manifolds and its Application to Neuropsychiatric Disorders	claim
397	42	Stereo Matching on Objects with Fractional Boundary	claim
398	42	In Situ Evaluation of Tracking Algorithms Using Time Reversed Chains	claim
399	42	Secure Biometric Templates from Fingerprint-Face Features	claim
400	42	Virtual Recovery of the Deteriorated Art Object based on AR Technology	claim
401	42	Real-time Gesture Recognition with Minimal Training Requirements and On-line Learning	claim
402	42	Classifying Video with Kernel Dynamic Textures	claim
403	42	Stereo Matching via Disparity Estimation and Surface Modeling	claim
404	42	Kernel-based Tracking from a Probabilistic Viewpoint	claim
405	42	A practical algorithm for L triangulation with outliers	claim
406	42	Linear Laplacian Discrimination for Feature Extraction	claim
407	42	An Efficient Minimal Solution for Infinitesimal Camera Motion	claim
408	42	Multiple Instance Learning of Pulmonary Embolism Detection with Geodesic Distance along Vascular Structure	claim
409	42	Wide-Area Egomotion Estimation from Known 3D Structure	claim
410	42	Practical Online Active Learning for Classification	claim
411	41	Target Tracking with Online Feature Selection in FLIR Imagery	claim
412	41	Improved Legibility of Text for Multiprojector Tiled Displays	claim
413	41	Trajectory Association across Non-overlapping Moving Cameras in Planar Scenes	claim
414	41	Spatio-temporal Shape and Flow Correlation for Action Recognition	claim
415	41	Feature Mining for Image Classification	claim
416	41	Tensor Canonical Correlation Analysis for Action Classification	claim
417	41	Variational Bayes Based Approach to Robust Subspace Learning	claim
418	41	Semantic Hierarchies for Recognizing Objects and Parts	claim
419	41	Improving Variance Estimation in Biometric Systems	claim
420	41	On the Spacetime Geometry of Galilean Cameras	claim
421	40	Analysis of Light Transport based on the Separation of Direct and Indirect Components	claim
422	40	ROI-SEG: Unsupervised Color Segmentation by Combining Differently Focused Sub Results	claim
423	40	Efficient Indexing For Articulation Invariant Shape Matching And Retrieval	claim
424	40	A Benchmarking Dataset for Performance Evaluation of Automatic Surface Reconstruction Algorithms	claim
425	40	Speckle Tracking in 3D Echocardiography with Motion Coherence	claim
426	40	Unsupervised Segmentation of Objects using Efficient Learning	claim
427	40	Multi-Modal Biometrics Involving the Human Ear	claim
428	40	Reducing correspondence ambiguity in loosely labeled training data	claim
429	40	Learning Object Material Categories via Pairwise Discriminant Analysis	claim
430	39	Towards Robust Pedestrian Detection in Crowded Image Sequences	claim
431	39	A Comparison of PMD-Cameras and Stereo-Vision for the Task of Surface Reconstruction using Patchlets	claim
432	39	Moving Object Detection on a Runway Prior to Landing Using an Onboard Infrared Camera	claim
433	39	Shape Representation and Registration using Vector Distance Functions	claim
434	39	Viewpoint-Coded Structured Light	claim
435	38	Unsupervised Clustering using Multi-Resolution Perceptual Grouping	claim
436	38	Symmetric Objects are Hardly Ambiguous	claim
437	38	A Graph Reduction Method for 2D Snake Problems	claim
438	38	A Multi-Scale Tikhonov Regularization Scheme for Implicit Surface Modelling	claim
439	38	Sensor Fusion and Environmental Modelling for Multimodal Sentient Computing	claim
440	38	Diverse Active Ranking for Multimedia Search	claim
441	38	Inter-Reflection Compensation for Immersive Projection Display	claim
442	38	Inferring Grammar-based Structure Models from 3D Microscopy Data	claim
443	37	Opti-Acoustic Stereo Imaging, System Calibration and 3-D Reconstruction	claim
444	37	Matrix-Structural Learning (MSL) of Cascaded Classifier from Enormous Training Set	claim
445	37	Displaying a Moving Image By Multiple Steerable Projectors	claim
446	37	DigiTable: an interactive multiuser table for collocated and remote collaboration enabling remote gesture visualization	claim
447	37	Progressive Learning for Interactive Surveillance Scenes Retrieval	claim
448	37	Local Shape Registration Using Boundary-Constrained Match of Skeletons	claim
449	36	Minimal Solutions for Panoramic Stitching	claim
450	35	Learning Generative Models via Discriminative Approaches	claim
451	35	Sensor and Data Systems, Audio-Assisted Cameras and Acoustic Doppler Sensors	claim
452	34	Influence of numerical conditioning on the accuracy of relative orientation	claim
453	34	Resolving the Generalized Bas-Relief Ambiguity by Entropy Minimization	claim
454	34	Flash Cut: Foreground Extraction with Flash and No-flash Image Pairs	claim
455	32	Detector Ensemble	claim
456	32	Motion and Appearance Contexts for Tracking and Re-Acquiring Targets in Aerial Videos	claim
457	32	On the Performance Prediction and Validation for Multisensor Fusion	claim
458	32	Automatic texture mapping on real 3D model	claim
459	30	Flexible Pixel Compositor for Plug-and-Play Multi-Projector Displays	claim

Sciweavers

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers