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

933views Computer Vision» more CVPR 2007»

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

15 years 1 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	933	Towards Fog-Free In-Vehicle Vision Systems through Contrast Restoration
2	500	Optimal Step Nonrigid ICP Algorithms for Surface Registration	claim
3	405	Shadow Removal in Front Projection Environments Using Object Tracking	claim
4	390	What makes a good model of natural images?	claim
5	379	Dynamic 3D Scene Analysis from a Moving Vehicle	claim
6	376	Learning Local Image Descriptors	claim
7	374	On the Performance Prediction and Validation for Multisensor Fusion	claim
8	353	Detecting Pedestrians by Learning Shapelet Features	claim
9	340	Learning to Detect A Salient Object	claim
10	336	Mumford-Shah Meets Stereo: Integration of Weak Depth Hypotheses	claim
11	329	Removal of Image Artifacts Due to Sensor Dust
12	328	Face Re-Lighting from a Single Image under Harsh Lighting Conditions	claim
13	325	Quasi-Dense Wide Baseline Matching Using Match Propagation	claim
14	324	Detection and segmentation of moving objects in highly dynamic scenes	claim
15	323	Detector adaptation by maximising agreement between independent data sources	claim
16	323	Partially Occluded Object-Specific Segmentation in View-Based Recognition
17	321	3D Probabilistic Feature Point Model for Object Detection and Recognition	claim
18	320	Groupwise Shape Registration on Raw Edge Sequence via A Spatio-Temporal Generative Model	claim
19	316	Light Fall-off Stereo	claim
20	308	Implicit Active Contours Driven by Local Binary Fitting Energy	claim
21	307	Learning Gaussian Conditional Random Fields for Low-Level Vision	claim
22	305	Kernel Sharing With Joint Boosting For Multi-Class Concept Detection	claim
23	301	Multi-label image segmentation via max-sum solver	claim
24	299	Delaunay Deformable Models: Topology-Adaptive Meshes Based on the Restricted Delaunay Triangulation	claim
25	298	Topology matching for 3D video compression
26	296	Beyond bottom-up: Incorporating task-dependent influences into a computational model of spatial attention	claim
27	295	Joint Priors for Variational Shape and Appearance Modeling	claim
28	295	A Bayesian algorithm for tracking multiple moving objects in outdoor surveillance video	claim
29	290	Accurate Object Detection with Deformable Shape Models Learnt from Images	claim
30	287	Robust Local Features and their Application in Self-Calibration and Object Recognition on Embedded Systems
31	287	A Human Action Recognition System for Embedded Computer Vision Application	claim
32	286	Change Detection in a 3-d World	claim
33	282	Multi-Layer Background Subtraction Based on Color and Texture	claim
34	282	Single View Human Action Recognition using Key Pose Matching and Viterbi Path Searching	claim
35	281	A Fast 3D Correspondence Method for Statistical Shape Modeling	claim
36	278	Generic Face Alignment using Boosted Appearance Model	claim
37	276	Using Group Prior to Identify People in Consumer Images
38	274	On Constant Focal Length Self-Calibration From Multiple Views	claim
39	273	Autocalibration and Uncalibrated Reconstruction of Shape from Defocus	claim
40	272	Principal Curvature-Based Region Detector for Object Recognition	claim
41	270	Single Image Motion Deblurring Using Transparency	claim
42	268	PrivacyCam: a Privacy Preserving Camera Using uCLinux on the Blackfin DSP	claim
43	265	Epitomic Representation of Human Activities	claim
44	265	Matching Local Self-Similarities across Images and Videos	claim
45	264	3D Pose Estimation Based on Multiple Monocular Cues	claim
46	264	Gradient Intensity: A New Mutual Information-Based Registration Method	claim
47	263	Automatic Face Recognition from Skeletal Remains	claim
48	263	Scene Segmentation and Categorization Using NCuts	claim
49	263	A Multi-Resolution Dynamic Model for Face Aging Simulation	claim
50	262	3D LayoutCRF for Multi-View Object Class Recognition and Segmentation	claim
51	262	An MRF and Gaussian Curvature Based Shape Representation for Shape Matching	claim
52	261	Boosting Coded Dynamic Features for Facial Action Units and Facial Expression Recognition	claim
53	260	Adaptive Distance Metric Learning for Clustering	claim
54	260	Incorporating On-demand Stereo for Real Time Recognition	claim
55	259	Improving Part based Object Detection by Unsupervised, Online Boosting	claim
56	258	Nonlinear Dynamical Shape Priors for Level Set Segmentation	claim
57	257	Adaptive Patch Features for Object Class Recognition with Learned Hierarchical Models	claim
58	255	Belief Propagation in a 3D Spatio-temporal MRF for Moving Object Detection	claim
59	254	Human Detection via Classification on Riemannian Manifolds	claim
60	254	Multiple Target Tracking Using Spatio-Temporal Markov Chain Monte Carlo Data Association	claim
61	252	Global Optimization for Shape Fitting	claim
62	251	Discriminative Cluster Refinement: Improving Object Category Recognition Given Limited Training Data	claim
63	251	Concurrent Multiple Instance Learning for Image Categorization	claim
64	251	Simultaneous Detection and Segmentation of Pedestrians using Top-down and Bottom-up Processing	claim
65	251	Robust Face Alignment for Illumination and Pose Invariant Face Recognition	claim
66	246	Capturing People in Surveillance Video	claim
67	246	Fast Human Pose Estimation using Appearance and Motion via Multi-Dimensional Boosting Regression	claim
68	246	High-dimensional statistical distance for region-of-interest tracking: Application to combining a soft geometric constraint with
69	245	Optimized Color Sampling for Robust Matting	claim
70	244	A Closed-form Solution to 3D Reconstruction of Piecewise Planar Objects from Single Images	claim
71	243	Cordless portable multi-view fringe projection system for 3D reconstruction	claim
72	243	Kernel Fukunaga-Koontz Transform Subspaces For Enhanced Face Recognition	claim
73	241	Multiview normal field integration using level set methods	claim
74	241	Multi-Object Tracking Using Color, Texture and Motion	claim
75	240	Objects in Action: An Approach for Combining Action Understanding and Object Perception	claim
76	238	Virtual Training for Multi-View Object Class Recognition	claim
77	236	Flexible Object Models for Category-Level 3D Object Recognition	claim
78	235	A Surface-Growing Approach to Multi-View Stereo Reconstruction	claim
79	234	Estimating Scale of a Scene from a Single Image Based on Defocus Blur and Scene Geometry	claim
80	234	Simultaneous Depth Reconstruction and Restoration of Noisy Stereo Images Using Non-local Pixel Distribution
81	233	Free-Form Nonrigid Image Registration Using Generalized Elastic Nets	claim
82	232	Biased Manifold Embedding: A Framework for Person-Independent Head Pose Estimation	claim
83	232	Composite Models of Objects and Scenes for Category Recognition	claim
84	232	Spatio-Temporal Markov Random Field for Video Denoising	claim
85	232	Surveillance in Virtual Reality: System Design and Multi-Camera Control	claim
86	231	Toward Flexible 3D Modeling using a Catadioptric Camera	claim
87	229	Segmenting Motions of Different Types by Unsupervised Manifold Clustering	claim
88	229	Latent-Dynamic Discriminative Models for Continuous Gesture Recognition	claim
89	228	Discovery of Collocation Patterns: from Visual Words to Visual Phrases	claim
90	228	Fisher Kernels on Visual Vocabularies for Image Categorization	claim
91	227	Evaluation of Cost Functions for Stereo Matching	claim
92	225	Patch-based Image Correlation with Rapid Filtering	claim
93	225	Learning a Spatially Smooth Subspace for Face Recognition	claim
94	224	Color Constancy using Natural Image Statistics	claim
95	224	Tracking Large Variable Numbers of Objects in Clutter	claim
96	223	Marker-less Deformable Mesh Tracking for Human Shape and Motion Capture	claim
97	222	Monocular and Stereo Methods for AAM Learning from Video	claim
98	222	Beyond Local Appearance: Category Recognition from Pairwise Interactions of Simple Features	claim
99	222	The Hyperbolic Geometry of Illumination-Induced Chromaticity Changes	claim
100	222	A Nonparametric Treatment for Location/Segmentation Based Visual Tracking	claim
101	221	Utilizing Variational Optimization to Learn Markov Random Fields	claim
102	221	Shape Variation-Based Frieze Pattern for Robust Gait Recognition	claim
103	221	Inferring 3D Volumetric Shape of Both Moving Objects and Static Background Observed by a Moving Camera	claim
104	220	Joint Real-time Object Detection and Pose Estimation Using Probabilistic Boosting Network	claim
105	220	Multi-Use Light Engine - Fast Projection	claim
106	220	Accurate Dynamic Sketching of Faces from Video	claim
107	219	Robust 3D Face Recognition Using Learned Visual Codebook	claim
108	219	Unsupervised Learning of Hierarchical Semantics of Objects (hSOs)	claim
109	218	Multiple View Image Reconstruction: A Harmonic Approach	claim
110	218	Model-Guided Segmentation of 3D Neuroradiological Image Using Statistical Surface Wavelet Model	claim
111	217	Efficient Belief Propagation for Vision Using Linear Constraint Nodes	claim
112	217	Image Segmentation by Probabilistic Bottom-Up Aggregation and Cue Integration	claim
113	216	Tracking as Repeated Figure/Ground Segmentation	claim
114	215	Large scale vision-based navigation without an accurate global reconstruction	claim
115	214	Image representations beyond histograms of gradients: The role of Gestalt descriptors	claim
116	214	Bilattice-based Logical Reasoning for Human Detection	claim
117	213	Multi-scale Structural Saliency for Signature Detection	claim
118	213	Tracking-as-Recognition for Articulated Full-Body Human Motion Analysis	claim
119	213	Discriminative Learning of Dynamical Systems for Motion Tracking	claim
120	213	Accurate, Dense, and Robust Multi-View Stereopsis	claim
121	213	Generative Graphical Models for Maneuvering Object Tracking and Dynamics Analysis	claim
122	212	The Hierarchical Isometric Self-Organizing Map for Manifold Representation	claim
123	212	Enhanced Level Building Algorithm for the Movement Epenthesis Problem in Sign Language Recognition	claim
124	212	ShadowCuts: Photometric Stereo with Shadows	claim
125	212	Automatic Person Detection and Tracking using Fuzzy Controlled Active Cameras	claim
126	211	Constrained Optimization for Retinal Curvature Estimation Using an Affine Camera	claim
127	211	Seamless Mosaicing of Image-Based Texture Maps	claim
128	211	Skin Detail Analysis for Face Recognition	claim
129	211	A Minutiae-based Fingerprint Individuality Model	claim
130	210	Statistical Shape Analysis of Multi-Object Complexes	claim
131	210	Nonnegative Tucker Decomposition	claim
132	210	Combining Region and Edge Cues for Image Segmentation in a Probabilistic Gaussian Mixture Framework	claim
133	210	Fast Keypoint Recognition in Ten Lines of Code	claim
134	210	Closed-Loop Tracking and Change Detection in Multi-Activity Sequences	claim
135	210	3D Face Recognition Founded on the Structural Diversity of Human Faces	claim
136	209	OPTIMOL: automatic Online Picture collecTion via Incremental MOdel Learning	claim
137	209	A Topic-Motion Model for Unsupervised Video Object Discovery	claim
138	209	Learning Conditional Random Fields for Stereo	claim
139	209	Visual Odometry System Using Multiple Stereo Cameras and Inertial Measurement Unit	claim
140	209	A linear estimation method for 3D pose and facial animation tracking	claim
141	207	Learning Motion Categories using both Semantic and Structural Information	claim
142	206	Image Hallucination Using Neighbor Embedding over Visual Primitive Manifolds	claim
143	206	A Novel Approach to Improve Biometric Recognition Using Rank Level Fusion	claim
144	205	Recognizing Human Activities from Silhouettes: Motion Subspace and Factorial Discriminative Graphical Model	claim
145	205	Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition	claim
146	205	Layered Graph Match with Graph Editing	claim
147	205	Dense mirroring surface recovery from 1D homographies and sparse correspondences	claim
148	204	Graph Cut Based Optimization for MRFs with Truncated Convex Priors	claim
149	204	The Effect of Pixel-Level Fusion on Object Tracking in Multi-Sensor Surveillance Video	claim
150	202	Learning Features for Tracking	claim
151	202	Precise Registration of 3D Models To Images by Swarming Particles	claim
152	202	Robust Metric Reconstruction from Challenging Video Sequences	claim
153	202	Multimodal Tracking for Smart Videoconferencing and Video Surveillance	claim
154	202	Detailed Human Shape and Pose from Images	claim
155	202	Connecting the Out-of-Sample and Pre-Image Problems in Kernel Methods	claim
156	201	A Benchmarking Dataset for Performance Evaluation of Automatic Surface Reconstruction Algorithms	claim
157	201	Face Recognition in Video: Adaptive Fusion of Multiple Matchers	claim
158	201	Kernel-Based 3D Tracking	claim
159	201	Real-Time License Plate Recognition on an Embedded DSP-Platform	claim
160	201	Robust Click-Point Linking: Matching Visually Dissimilar Local Regions	claim
161	200	Face Recognition Using Kernel Ridge Regression	claim
162	199	Thermal-Visible Video Fusion for Moving Target Tracking and Pedestrian Classification	claim
163	199	Joint Object Segmentation and Behavior Classification in Image Sequences	claim
164	199	Hierarchical Structuring of Data on Manifolds	claim
165	198	Searching Video for Complex Activities with Finite State Models	claim
166	198	Tensor Canonical Correlation Analysis for Action Classification	claim
167	198	Projective Factorization of Multiple Rigid-Body Motions	claim
168	197	Joint Optimization of Cascaded Classifiers for Computer Aided Detection	claim
169	197	Scaled Motion Dynamics for Markerless Motion Capture	claim
170	197	Hierarchical Learning of Curves Application to Guidewire Localization in Fluoroscopy	claim
171	196	A Topological Approach to Hierarchical Segmentation using Mean Shift	claim
172	196	An Embodied User Interface for Increasing Physical Activities in Game	claim
173	195	Leveraging temporal, contextual and ordering constraints for recognizing complex activities in video	claim
174	195	Resolving Objects at Higher Resolution from a Single Motion-blurred Image	claim
175	195	Optimizing Distribution-based Matching by Random Subsampling	claim
176	195	Bridging the Gap between Detection and Tracking for 3D Monocular Video-Based Motion Capture	claim
177	194	Capturing long-range correlations with patch models	claim
178	194	Feature Extraction by Maximizing the Average Neighborhood Margin	claim
179	194	Differential Camera Tracking through Linearizing the Local Appearance Manifold	claim
180	194	Automated Individualization of Deformable Eye Region Model and Its Application to Eye Motion Analysis	claim
181	193	Shape Representation and Registration using Vector Distance Functions	claim
182	193	Active Visual Object Reconstruction using D-, E-, and T-Optimal Next Best Views	claim
183	192	On-line Simultaneous Learning and Tracking of Visual Feature Graphs	claim
184	192	Shape Statistics for Image Segmentation with Prior	claim
185	192	Discriminant Mutual Subspace Learning for Indoor and Outdoor Face Recognition	claim
186	192	Multi-class object tracking algorithm that handles fragmentation and grouping	claim
187	191	Fast 3D Scanning with Automatic Motion Compensation	claim
188	191	Object Tracking by Asymmetric Kernel Mean Shift with Automatic Scale and Orientation Selection	claim
189	190	Modelling Objects using Distribution and Topology of Multiscale Region Pairs	claim
190	190	Learning Color Names from Real-World Images	claim
191	190	Pedestrian Detection in Infrared Images based on Local Shape Features	claim
192	190	Map-Enhanced UAV Image Sequence Registration and Synchronization of Multiple Image Sequences	claim
193	189	Real-Time Projector Tracking on Complex Geometry Using Ordinary Imagery	claim
194	189	Robust Occlusion Handling in Object Tracking	claim
195	188	An Adaptive Focal Connectivity Algorithm for Multifocus Fusion	claim
196	188	Audio-Visual Speech Fusion Using Coupled Hidden Markov Models	claim
197	188	Consistent Temporal Variations in Many Outdoor Scenes	claim
198	188	P3 & Beyond: Solving Energies with Higher Order Cliques	claim
199	187	Combining Static Classifiers and Class Syntax Models for Logical Entity Recognition in Scanned Historical Documents	claim
200	187	Unsupervised Activity Perception by Hierarchical Bayesian Models	claim
201	187	Compositional Boosting for Computing Hierarchical Image Structures	claim
202	187	Efficient Sampling of Disparity Space for Fast And Accurate Matching	claim
203	186	Combining local and global motion models for feature point tracking	claim
204	186	Active Aperture Control and Sensor Modulation for Flexible Imaging	claim
205	185	Mapping Natural Image Patches by Explicit and Implicit Manifolds	claim
206	185	City-Scale Location Recognition	claim
207	185	A contextual dissimilarity measure for accurate and efficient image search	claim
208	185	Detecting Specular Surfaces on Natural Images	claim
209	184	Contextual Identity Recognition in Personal Photo Albums	claim
210	184	Object retrieval with large vocabularies and fast spatial matching	claim
211	184	Learning the Compositional Nature of Visual Objects	claim
212	184	OpenVL: Towards A Novel Software Architecture for Computer Vision	claim
213	184	Filtered Component Analysis to Increase Robustness to Local Minima in Appearance Models	claim
214	184	A Lagrangian Particle Dynamics Approach for Crowd Flow Segmentation and Stability Analysis	claim
215	184	Image Matching via Saliency Region Correspondences	claim
216	184	Integration of Motion Cues in Optical and Sonar Videos for 3-D Positioning	claim
217	183	Using Segmentation to Verify Object Hypotheses	claim
218	183	Progressive Finite Newton Approach To Real-time Nonrigid Surface Detection	claim
219	183	Element Rearrangement for Tensor-Based Subspace Learning	claim
220	183	Segmental Hidden Markov Models for View-based Sport Video Analysis	claim
221	183	Cast Shadow Removal Combining Local and Global Features	claim
222	183	Region Classification with Markov Field Aspect Models	claim
223	183	Local Ensemble Kernel Learning for Object Category Recognition	claim
224	183	Object Classification in Visual Surveillance Using Adaboost	claim
225	182	From Videos to Verbs: Mining Videos for Activities using a Cascade of Dynamical Systems	claim
226	182	Autocalibration via Rank-Constrained Estimation of the Absolute Quadric	claim
227	182	Metropolis-Hasting techniques for finite-element-based registration	claim
228	182	Learning and Matching Line Aspects for Articulated Objects	claim
229	182	Photometric Self-Calibration of a Projector-Camera System	claim
230	181	Opti-Acoustic Stereo Imaging, System Calibration and 3-D Reconstruction	claim
231	180	Semi-supervised Hierarchical Models for 3D Human Pose Reconstruction	claim
232	180	Approximate Nearest Subspace Search with Applications to Pattern Recognition	claim
233	180	Multiphase Segmentation of Deformation using Logarithmic Priors	claim
234	180	High-Speed Measurement of BRDF using an Ellipsoidal Mirror and a Projector	claim
235	180	Hierarchical Matching of Deformable Shapes	claim
236	179	Discriminant Additive Tangent Spaces for Object Recognition	claim
237	179	A Comparison of PMD-Cameras and Stereo-Vision for the Task of Surface Reconstruction using Patchlets	claim
238	178	3D Occlusion Inference from Silhouette Cues	claim
239	178	Real-Time Plane-Sweeping Stereo with Multiple Sweeping Directions	claim
240	178	Learning Dynamic Event Descriptions in Image Sequences	claim
241	177	A Probabilistic Model for Object Recognition, Segmentation, and Non-Rigid Correspondence	claim
242	177	Visual Event Recognition in News Video using Kernel Methods with Multi-Level Temporal Alignment	claim
243	176	Probabilistic visibility for multi-view stereo	claim
244	175	EDA Approach for Model Based Localization and Recognition of Vehicles	claim
245	175	A Graph Reduction Method for 2D Snake Problems	claim
246	174	Robust Estimation of Texture Flow via Dense Feature Sampling	claim
247	174	Image Classification with Segmentation Graph Kernels	claim
248	174	Real-time Automatic Deceit Detection from Involuntary Facial Expressions	claim
249	174	Topology Preserving Log-Unbiased Nonlinear Image Registration: Theory and Implementation	claim
250	174	Accurate Object Localization with Shape Masks	claim
251	174	Facial Expression Biometrics Using Tracker Displacement Features	claim
252	174	Diverse Active Ranking for Multimedia Search	claim
253	173	A Graph Cut Approach to Image Segmentation in Tensor Space	claim
254	173	Geometric Modeling and Calibration of Planar Multi-Projector Displays Using Rational Bezier Patches	claim
255	173	Automatic Removal of Chromatic Aberration from a Single Image	claim
256	173	A Linear Programming Approach for Multiple Object Tracking	claim
257	173	Segmenting Images on the Tensor Manifold	claim
258	172	A boosting regression approach to medical anatomy detection	claim
259	172	Trace Ratio vs. Ratio Trace for Dimensionality Reduction	claim
260	172	Trajectory Series Analysis based Event Rule Induction for Visual Surveillance	claim
261	171	Speckle Tracking in 3D Echocardiography with Motion Coherence	claim
262	171	Pyramid Match Hashing: Sub-Linear Time Indexing Over Partial Correspondences	claim
263	171	Automatic texture mapping on real 3D model	claim
264	171	Fast Terrain Classification Using Variable-Length Representation for Autonomous Navigation	claim
265	171	High Distortion and Non-Structural Image Matching via Feature Co-occurrence	claim
266	170	Sparse Kernels for Bayes Optimal Discriminant Analysis	claim
267	169	Dimensionality Reduction and Clustering on Statistical Manifolds	claim
268	169	Layered Depth Panoramas	claim
269	169	On the Direct Estimation of the Fundamental Matrix	claim
270	169	Online Detection of Fire in Video	claim
271	169	A Multi-Scale Tikhonov Regularization Scheme for Implicit Surface Modelling	claim
272	169	Conformal Embedding Analysis with Local Graph Modeling on the Unit Hypersphere	claim
273	168	Isotropy, Reciprocity and the Generalized Bas-Relief Ambiguity	claim
274	168	Soft Edge Smoothness Prior for Alpha Channel Super Resolution	claim
275	168	Discontinuity Preserving Filtering over Analytic Manifolds	claim
276	168	Texture-Preserving Shadow Removal in Color Images Containing Curved Surfaces	claim
277	168	On the Blind Classification of Time Series	claim
278	167	An Active Illumination and Appearance (AIA) Model for Face Alignment	claim
279	167	Integrating Global and Local Structures: A Least Squares Framework for Dimensionality Reduction	claim
280	167	Optimizing Binary MRFs via Extended Roof Duality	claim
281	166	Incremental Linear Discriminant Analysis Using Sufficient Spanning Set Approximations	claim
282	166	A Component-Based Approach to Hand Verification	claim
283	165	Optimal Dimensionality Discriminant Analysis and Its Application to Image Recognition	claim
284	164	Efficiently Determining Silhouette Consistency	claim
285	164	Stereo Matching via Disparity Estimation and Surface Modeling	claim
286	164	Hybrid learning of large jigsaws	claim
287	164	Real-time Gesture Recognition with Minimal Training Requirements and On-line Learning	claim
288	163	Maximally Stable Colour Regions for Recognition and Matching	claim
289	163	Modeling Appearances with Low-Rank SVM	claim
290	163	Pose and Illumination Invariant Face Recognition in Video	claim
291	163	Simultaneous Object Detection and Segmentation by Boosting Local Shape Feature based Classifier	claim
292	162	Probabilistic Reverse Annotation for Large Scale Image Retrieval	claim
293	162	Image-Based Localization Using Hybrid Feature Correspondences	claim
294	162	A Unified Probabilistic Framework for Facial Activity Modeling and Understanding	claim
295	162	Non-intrusive Iris Image Capturing System Using Light Stripe Projection and Pan-Tilt-Zoom Camera	claim
296	161	Face Recognition using Discriminatively Trained Orthogonal Rank One Tensor Projections	claim
297	161	Polarization and Phase-Shifting for 3D Scanning of Translucent Objects	claim
298	161	A Binning Scheme for Fast Hard Drive Based Image Search	claim
299	160	Thermal Imaging of the Superficial Temporal Artery: An Arterial Pulse Recovery Model	claim
300	160	Part-based Face Recognition Using Near Infrared Images	claim
301	160	Spatial-Depth Super Resolution for Range Images	claim
302	159	Online Spatial-temporal Data Fusion for Robust Adaptive Tracking	claim
303	159	Quality-Driven Face Occlusion Detection and Recovery	claim
304	159	Handwritten Carbon Form Preprocessing Based on Markov Random Field	claim
305	159	Semantic Hierarchies for Recognizing Objects and Parts	claim
306	159	Content-Based Image Annotation Refinement	claim
307	158	Shape from Shading Under Various Imaging Conditions	claim
308	158	Euclidean Path Modeling from Ground and Aerial Views	claim
309	158	The effective resolution of correlation filters applied to natural scenes	claim
310	158	Variable Bandwidth Image Denoising Using Image-based Noise Models	claim
311	157	Illumination Multiplexing within Fundamental Limits	claim
312	157	Recognizing Groceries in situ Using in vitro Training Data	claim
313	157	Secure Biometric Templates from Fingerprint-Face Features	claim
314	156	A Hierarchical Model of Shape and Appearance for Human Action Classification	claim
315	155	Tree-based Classifiers for Bilayer Video Segmentation	claim
316	155	Unsupervised Segmentation of Objects using Efficient Learning	claim
317	154	P3 & Beyond: Solving Energies with Higher Order Cliques	claim
318	154	Microphone Arrays as Generalized Cameras for Integrated Audio Visual Processing	claim
319	154	A minimal solution to the autocalibration of radial distortion	claim
320	153	Variational Distance-Dependent Image Restoration	claim
321	153	A Bio-inspired Learning Approach for the Classification of Risk Zones in a Smart Space	claim
322	153	Regression tracking with data relevance determination	claim
323	153	Improved Video Registration using Non-Distinctive Local Image Features	claim
324	153	Spatial selection for attentional visual tracking	claim
325	153	Semantic Hierarchies for Visual Object Recognition	claim
326	152	Two thresholds are better than one	claim
327	152	Robust Change-Detection by Normalised Gradient-Correlation	claim
328	151	Efficient MRF Deformation Model for Non-Rigid Image Matching	claim
329	151	Iterative MAP and ML Estimations for Image Segmentation	claim
330	151	Toward A Discriminative Codebook: Codeword Selection across Multi-resolution	claim
331	150	Kinematics from Lines in a Single Rolling Shutter Image	claim
332	150	A Robust Warping Method for Fingerprint Matching	claim
333	150	Learning Object Material Categories via Pairwise Discriminant Analysis	claim
334	150	Online Learning Asymmetric Boosted Classifiers for Object Detection	claim
335	149	Multimodal Surveillance: an Introduction	claim
336	149	Detecting Object Boundaries Using Low-, Mid-, and High-level Information	claim
337	148	Towards Scalable Representations of Object Categories: Learning a Hierarchy of Parts	claim
338	148	Learning Kernel Expansions for Image Classification	claim
339	147	Learning Visual Representations using Images with Captions	claim
340	147	Hierarchical Recognition of Human Activities Interacting with Objects	claim
341	147	Visual Curvature	claim
342	147	Solving Large Scale Binary Quadratic Problems: Spectral Methods vs. Semidefinite Programming	claim
343	146	Eigenboosting: Combining Discriminative and Generative Information	claim
344	146	ROI-SEG: Unsupervised Color Segmentation by Combining Differently Focused Sub Results	claim
345	145	A Real-Time ProCam System for Interaction with Chinese Ink-and-Wash Cartoons	claim
346	145	Tracking in Low Frame Rate Video: A Cascade Particle Filter with Discriminative Observers of Different Lifespans	claim
347	145	Estimating Cluster Overlap on Manifolds and its Application to Neuropsychiatric Disorders	claim
348	144	Practical Online Active Learning for Classification	claim
349	144	Algorithms for Batch Matrix Factorization with Application to Structure-from-Motion	claim
350	144	Fiber Tract Clustering on Manifolds With Dual Rooted-Graphs	claim
351	143	Complex Salient Regions for Computer Vision Problems	claim
352	143	Virtual Recovery of the Deteriorated Art Object based on AR Technology	claim
353	143	Recognizing objects by piecing together the Segmentation Puzzle	claim
354	142	Physics-Based Person Tracking Using Simplified Lower-Body Dynamics	claim
355	141	Two-View Motion Segmentation from Linear Programming Relaxation	claim
356	141	Multiple Class Segmentation Using A Unified Framework over Mean-Shift Patches	claim
357	141	Deformable Surface Tracking Ambiguities	claim
358	141	Linear and Quadratic Subsets for Template-Based Tracking	claim
359	141	Topology-preserving Geometric Deformable Model on Adaptive Quadtree Grid	claim
360	140	In Situ Evaluation of Tracking Algorithms Using Time Reversed Chains	claim
361	140	Recognizing Night Walkers Based on One Pseudoshape Representation of Gait	claim
362	140	A Quasi-Minimal Model for Paper-Like Surfaces	claim
363	140	Multi-modal Person Identification in a Smart Environment	claim
364	140	Sensor noise modeling using the Skellam distribution: Application to the color edge detection	claim
365	140	Variational Bayes Based Approach to Robust Subspace Learning	claim
366	140	Matrix-Structural Learning (MSL) of Cascaded Classifier from Enormous Training Set	claim
367	139	Shape from Planar Curves: A Linear Escape from Flatland	claim
368	139	On Constructing Facial Similarity Maps	claim
369	139	Multi-Modal Biometrics Involving the Human Ear	claim
370	139	Multimodal Mean Adaptive Backgrounding for Embedded Real-Time Video Surveillance	claim
371	139	Multi-modal Clustering for Multimedia Collections	claim
372	139	Transfer Learning in Sign language	claim
373	139	Improving Variance Estimation in Biometric Systems	claim
374	138	A Variational Approach to the Evolution of Radial Basis Functions for Image Segmentation	claim
375	138	Learning GMRF Structures for Spatial Priors	claim
376	138	Simultaneous Covariance Driven Correspondence (CDC) and Transformation Estimation in the Expectation Maximization Framework	claim
377	138	Design and Deployment of Visible-Thermal Biometric Surveillance Systems	claim
378	137	Analysis of Light Transport based on the Separation of Direct and Indirect Components	claim
379	137	Simultaneous Matting and Compositing	claim
380	137	Stereo Matching on Objects with Fractional Boundary	claim
381	137	Spectral Matting	claim
382	136	Imaging the Finger Force Direction	claim
383	136	A Probabilistic Intensity Similarity Measure based on Noise Distributions	claim
384	136	On-the-fly Object Modeling while Tracking	claim
385	136	Radiometric Calibration from Noise Distributions	claim
386	136	Moving Object Detection on a Runway Prior to Landing Using an Onboard Infrared Camera	claim
387	135	Multiple Instance Learning of Pulmonary Embolism Detection with Geodesic Distance along Vascular Structure	claim
388	135	Robust Real-Time Visual SLAM Using Scale Prediction and Exemplar Based Feature Description	claim
389	135	Classifying Video with Kernel Dynamic Textures	claim
390	135	A Benchmark for the Comparison of 3-D Motion Segmentation Algorithms	claim
391	135	Resolving the Generalized Bas-Relief Ambiguity by Entropy Minimization	claim
392	135	Towards Automatic Photometric Correction of Casually Illuminated Documents	claim
393	133	Towards Robust Pedestrian Detection in Crowded Image Sequences	claim
394	133	Efficient Indexing For Articulation Invariant Shape Matching And Retrieval	claim
395	133	Projector Calibration using Arbitrary Planes and Calibrated Camera	claim
396	133	Feature Mining for Image Classification	claim
397	133	DigiTable: an interactive multiuser table for collocated and remote collaboration enabling remote gesture visualization	claim
398	133	Real-Time Image Matching Based on Multiple View Kernel Projection	claim
399	132	An end-to-end eChronicling System for Mobile Human Surveillance	claim
400	132	Moving Forward in Structure From Motion	claim
401	132	Learning Generative Models via Discriminative Approaches	claim
402	131	LDV Sensing and Processing for Remote Hearing in a Multimodal Surveillance System	claim
403	130	Multimodal workbench for automatic surveillance applications	claim
404	130	On Stabilisation of Parametric Active Contours	claim
405	130	Modulation Domain Template Tracking	claim
406	129	Improved Legibility of Text for Multiprojector Tiled Displays	claim
407	129	Discriminant Interest Points are Stable	claim
408	129	Projector-Camera Guided Fast Environment Restoration of a Biofeedback System for Rehabilitation	claim
409	129	Reducing correspondence ambiguity in loosely labeled training data	claim
410	128	Saliency Detection: A Spectral Residual Approach	claim
411	128	Multi-scale Features for Detection and Segmentation of Rocks in Mars Images	claim
412	128	Local Shape Registration Using Boundary-Constrained Match of Skeletons	claim
413	127	Displaying a Moving Image By Multiple Steerable Projectors	claim
414	127	Spatio-temporal Shape and Flow Correlation for Action Recognition	claim
415	127	Regularized Mixed Dimensionality and Density Learning in Computer Vision	claim
416	127	Scene-space Feature Detectors	claim
417	127	Artificial Complex Cells via the Tropical Semiring	claim
418	127	Flash Cut: Foreground Extraction with Flash and No-flash Image Pairs	claim
419	126	Offline Signature Verification Using Online Handwriting Registration	claim
420	125	Feasibility Boundary in Dense and Semi-Dense Stereo Matching	claim
421	125	Realizing Super-Resolution with Superimposed Projection	claim
422	124	Learning Visual Similarity Measures for Comparing Never Seen Objects	claim
423	123	Using Geometry Invariants for Camera Response Function Estimation	claim
424	123	Motion and Appearance Contexts for Tracking and Re-Acquiring Targets in Aerial Videos	claim
425	123	A practical algorithm for L triangulation with outliers	claim
426	123	Minimal Solutions for Panoramic Stitching	claim
427	122	An Efficient Minimal Solution for Infinitesimal Camera Motion	claim
428	121	An Exemplar Model for Learning Object Classes	claim
429	120	Using Stereo Matching for 2-D Face Recognition Across Pose	claim
430	120	Inter-Reflection Compensation for Immersive Projection Display	claim
431	120	Local Structure Detection with Orientation-invariant Radial Configuration	claim
432	119	Focal Pre-Correction of Projected Image for Deblurring Screen Image	claim
433	119	Keypoint Descriptors for Matching Across Multiple Image Modalities and Non-linear Intensity Variations	claim
434	119	Sensor Fusion and Environmental Modelling for Multimodal Sentient Computing	claim
435	119	Real-time Planar Surface Segmentation in Disparity Space	claim
436	119	Viewpoint-Coded Structured Light	claim
437	119	Trajectory Association across Non-overlapping Moving Cameras in Planar Scenes	claim
438	118	Fast, Approximately Optimal Solutions for Single and Dynamic MRFs	claim
439	118	Revocable Fingerprint Biotokens: Accuracy and Security Analysis	claim
440	118	A Face Annotation Framework with Partial Clustering and Interactive Labeling	claim
441	118	Target Tracking with Online Feature Selection in FLIR Imagery	claim
442	117	Inferring Temporal Order of Images From 3D Structure	claim
443	117	Influence of numerical conditioning on the accuracy of relative orientation	claim
444	117	On the Spacetime Geometry of Galilean Cameras	claim
445	116	Progressive Learning for Interactive Surveillance Scenes Retrieval	claim
446	115	Unsupervised Clustering using Multi-Resolution Perceptual Grouping	claim
447	115	Symmetric Objects are Hardly Ambiguous	claim
448	115	Statistics of Infrared Images	claim
449	115	Flexible Pixel Compositor for Plug-and-Play Multi-Projector Displays	claim
450	113	Riemannian Analysis of Probability Density Functions with Applications in Vision	claim
451	111	Parameter Sensitive Detectors	claim
452	110	Unsupervised Learning of Image Transformations	claim
453	110	Linear Laplacian Discrimination for Feature Extraction	claim
454	108	Inferring Grammar-based Structure Models from 3D Microscopy Data	claim
455	108	Kernel-based Tracking from a Probabilistic Viewpoint	claim
456	107	Harmony in Motion	claim
457	106	Wide-Area Egomotion Estimation from Known 3D Structure	claim
458	106	Sensor and Data Systems, Audio-Assisted Cameras and Acoustic Doppler Sensors	claim
459	102	Detector Ensemble	claim

Sciweavers

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers