CVPR 2005 - PDF Preprint Papers

CVPR 2005 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-2005 Paper

136

click to vote

CVPR
2005
IEEE

2143views Computer Vision» more CVPR 2005»

Level Set Evolution Without Re-initialization: A New Variational Formulation

15 years 12 months ago

Download www.engr.uconn.edu

"In this paper, we present a new variational formulation for geometric active contours that forces the level set function to be close to a signed distance function, and theref...

Chunming Li, Chenyang Xu, Changfeng Gui, and Marti...

posted by scimaster

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	2143	Level Set Evolution Without Re-initialization: A New Variational Formulation
2	1158	Flattening Curved Documents in Images	claim
3	902	Histograms of Oriented Gradients for Human Detection	claim
4	834	Level Set Based Shape Prior Segmentation	claim
5	611	A Framework of 2D Fisher Discriminant Analysis: Application to Face Recognition with Small Number of Training Samples
6	438	Segmentation of Edge Preserving Gradient Vector Flow: An Approach Toward Automatically Initializing and Splitting of Snakes	claim
7	411	Tracking People and Recognizing Their Activities	claim
8	367	Face Recognition Based on Frontal Views Generated from Non-Frontal Images	claim
9	334	Bayesian Object Detection in Dynamic Scenes	claim
10	326	Integral Histogram: A Fast Way To Extract Histograms in Cartesian Spaces	claim
11	312	Bayesian 3D Modeling from Images Using Multiple Depth Maps	claim
12	304	Detection and Explanation of Anomalous Activities: Representing Activities as Bags of Event n-Grams	claim
13	304	Automatic 3D to 2D Registration for the Photorealistic Rendering of Urban Scenes	claim
14	302	Subspace Analysis Using Random Mixture Models	claim
15	301	Robust and Efficient Foreground Analysis for Real-Time Video Surveillance	claim
16	292	Fast Illumination-Invariant Background Subtraction Using Two Views: Error Analysis, Sensor Placement and Applications	claim
17	288	Fisher+Kernel Criterion for Discriminant Analysis	claim
18	287	Full-Frame Video Stabilization	claim
19	286	A Rational Function Lens Distortion Model for General Cameras	claim
20	285	Estimating 3D Shape and Texture Using Pixel Intensity, Edges, Specular Highlights, Texture Constraints and a Prior	claim
21	285	Applying Neighborhood Consistency for Fast Clustering and Kernel Density Estimation	claim
22	283	Particle Filtering for Geometric Active Contours with Application to Tracking Moving and Deforming Objects	claim
23	283	A Dynamic Conditional Random Field Model for Object Segmentation in Image Sequences	claim
24	276	Interactive Shape from Shading	claim
25	274	A Statistical Field Model for Pedestrian Detection	claim
26	273	Learning a Similarity Metric Discriminatively, with Application to Face Verification	claim
27	272	Multi-Image Matching Using Multi-Scale Oriented Patches	claim
28	272	Interactive Graph Cut Based Segmentation with Shape Priors	claim
29	270	Learning Feature Distance Measures for Image Correspondences	claim
30	269	Discriminative Learning of Markov Random Fields for Segmentation of 3D Scan Data	claim
31	269	A New Active Contour Method Based on Elastic Interaction	claim
32	269	Dense Photometric Stereo Using Tensorial Belief Propagation	claim
33	268	Modeling Dynamic Scenes with Active Appearance	claim
34	267	Dense Photometric Stereo Using a Mirror Sphere and Graph Cut	claim
35	265	Shape Matching and Object Recognition Using Low Distortion Correspondences	claim
36	265	Pedestrian Detection in Crowded Scenes	claim
37	263	A Nonlinear Approach for Face Sketch Synthesis and Recognition	claim
38	261	Part-Based Statistical Models for Object Classification and Detection	claim
39	260	Articulated Structure from Motion by Factorization	claim
40	257	Strike a Pose: Tracking People by Finding Stylized Poses	claim
41	255	Cloth Representation by Shape from Shading with Shading Primitives	claim
42	255	Hallucinating Faces: TensorPatch Super-Resolution and Coupled Residue Compensation	claim
43	251	An Axiomatic Approach to Corner Detection	claim
44	250	A Semi-Supervised Active Learning Framework for Image Retrieval	claim
45	250	Active Polyhedron: Surface Evolution Theory Applied to Deformable Meshes	claim
46	249	A Slit Scanning Depth of Route Panorama from Stationary Blur	claim
47	249	Database-Guided Segmentation of Anatomical Structures with Complex Appearance	claim
48	248	Robust L1 Norm Factorization in the Presence of Outliers and Missing Data by Alternative Convex Programming	claim
49	248	On the Absolute Quadratic Complex and Its Application to Autocalibration	claim
50	248	Asymmetrical Occlusion Handling Using Graph Cut for Multi-View Stereo	claim
51	248	Boosting Saliency in Color Image Features	claim
52	247	Object Recognition with Features Inspired by Visual Cortex
53	246	Wide-Baseline Stereo Matching with Line Segments	claim
54	245	Face Synthesis and Recognition from a Single Image under Arbitrary Unknown Lighting Using a Spherical Harmonic Basis Morphable Model	claim
55	244	Fields of Experts: A Framework for Learning Image Priors	claim
56	244	Space-Time Behavior Based Correlation	claim
57	244	2D Statistical Models of Facial Expressions for Realistic 3D Avatar Animation	claim
58	242	Learning to Estimate Human Pose with Data Driven Belief Propagation	claim
59	241	Complex 3D Shape Recovery Using a Dual-Space Approach	claim
60	241	Online Selecting Discriminative Tracking Features Using Particle Filter	claim
61	240	Modelling Dynamic Scenes by Registering Multi-View Image Sequences	claim
62	239	Efficient Mean-Shift Tracking via a New Similarity Measure	claim
63	238	A Non-Local Algorithm for Image Denoising	claim
64	238	Spatiograms versus Histograms for Region-Based Tracking	claim
65	238	Multiple Object Tracking with Kernel Particle Filter	claim
66	238	Multi-View Geometry for General Camera Models	claim
67	237	Joint Nonparametric Alignment for Analyzing Spatial Gene Expression Patterns in Drosophila Imaginal Discs	claim
68	237	ALIP: The Automatic Linguistic Indexing of Pictures System	claim
69	237	A Bayesian Hierarchical Model for Learning Natural Scene Categories	claim
70	236	A Bayesian Approach to Unsupervised Feature Selection and Density Estimation Using Expectation Propagation	claim
71	236	Spectral Segmentation with Multiscale Graph Decomposition	claim
72	236	Tracking Multiple Objects through Occlusions	claim
73	236	Statistical Cue Integration for Foveated Wide-Field Surveillance	claim
74	235	Tracking Multiple Mouse Contours (without Too Many Samples)	claim
75	235	Matching with PROSAC - Progressive Sample Consensus	claim
76	235	Corrected Laplacians: Closer Cuts and Segmentation with Shape Priors	claim
77	234	MER-DIMES: A Planetary Landing Application of Computer Vision	claim
78	234	Graph Embedding: A General Framework for Dimensionality Reduction	claim
79	234	3D Geometric and Optical Modeling of Warped Document Images from Scanners	claim
80	233	Cross-Generalization: Learning Novel Classes from a Single Example by Feature Replacement	claim
81	233	Efficient Image Matching with Distributions of Local Invariant Features	claim
82	233	Stereo Correspondence by Dynamic Programming on a Tree	claim
83	233	Shape Regularized Active Contour Using Iterative Global Search and Local Optimization	claim
84	232	Pose-Robust Face Recognition Using Geometry Assisted Probabilistic Modeling	claim
85	232	Discriminant Analysis with Tensor Representation	claim
86	231	Random Subspaces and Subsampling for 2-D Face Recognition	claim
87	231	Computer Vision for Music Identification	claim
88	231	WaldBoost - Learning for Time Constrained Sequential Detection	claim
89	230	Tracking Multiple Colored Blobs with a Moving Camera	claim
90	230	Robust Object Detection via Soft Cascade	claim
91	230	Bi-Layer Segmentation of Binocular Stereo Video	claim
92	230	Rank-R Approximation of Tensors: Using Image-as-Matrix Representation	claim
93	229	Fast Spatial Pattern Discovery Integrating Boosting with Constellations of Contextual Descriptors	claim
94	229	Bayesian Super-Resolution of Text in Video with a Text-Specific Bimodal Prior	claim
95	229	Correspondence Expansion for Wide Baseline Stereo	claim
96	228	Analytically Solving Radial Distortion Parameters	claim
97	228	Online Detection and Classification of Moving Objects Using Progressively Improving Detectors	claim
98	228	Full Body Tracking from Multiple Views Using Stochastic Sampling	claim
99	227	Camera Calibration and Light Source Estimation from Images with Shadows	claim
100	227	Coupled PDEs for Non-Rigid Registration and Segmentation	claim
101	226	A Hybrid Graphical Model for Robust Feature Extraction from Video	claim
102	226	Robust Face Detection with Multi-Class Boosting	claim
103	225	Integrated Learning of Saliency, Complex Features, and Object Detectors from Cluttered Scenes	claim
104	225	Digital Tapestry	claim
105	225	Semi-Supervised Adapted HMMs for Unusual Event Detection	claim
106	224	Generative versus Discriminative Methods for Object Recognition	claim
107	224	Concurrent Subspaces Analysis	claim
108	224	A Discriminative Framework for Modelling Object Classes	claim
109	223	Visual Tracking in the Presence of Motion Blur	claim
110	223	A Closed Form Solution to Direct Motion Segmentation	claim
111	223	Monocular 3-D Tracking of the Golf Swing	claim
112	222	Face Recognition with Image Sets Using Manifold Density Divergence	claim
113	222	Illumination-Invariant Tracking via Graph Cuts	claim
114	222	Accurate and Efficient Stereo Processing by Semi-Global Matching and Mutual Information	claim
115	222	Beyond Lambert: Reconstructing Specular Surfaces Using Color	claim
116	222	Representational Oriented Component Analysis (ROCA) for Face Recognition with One Sample Image per Training Class	claim
117	222	Coupled Kernel-Based Subspace Learning	claim
118	222	Machine Learning for Clinical Diagnosis from Functional Magnetic Resonance Imaging	claim
119	222	Real-Time Multiple Objects Tracking with Occlusion Handling in Dynamic Scenes	claim
120	222	Audio-Visual Affect Recognition through Multi-Stream Fused HMM for HCI	claim
121	219	Object Detection Using 2D Spatial Ordering Constraints	claim
122	219	Creating Invariance to "Nuisance Parameters" in Face Recognition	claim
123	219	Accurate Motion Layer Segmentation and Matting	claim
124	219	Symmetric Stereo Matching for Occlusion Handling	claim
125	217	Modeling and Learning Contact Dynamics in Human Motion	claim
126	217	Object Class Recognition Using Multiple Layer Boosting with Heterogeneous Features	claim
127	216	Higher Order Whitening of Natural Images	claim
128	215	Conformal Deskewing of Non-Planar Documents	claim
129	215	Damped Newton Algorithms for Matrix Factorization with Missing Data	claim
130	215	Appearance Modeling for Tracking in Multiple Non-Overlapping Cameras	claim
131	215	Estimating Disparity and Occlusions in Stereo Video Sequences	claim
132	215	A Two-Stage Level Set Evolution Scheme for Man-Made Objects Detection in Aerial Images	claim
133	214	A Sparse Object Category Model for Efficient Learning and Exhaustive Recognition	claim
134	214	A Principled Approach to Detecting Surprising Events in Video	claim
135	214	Real-Time Non-Rigid Surface Detection	claim
136	213	Multitarget Tracking with Split and Merged Measurements	claim
137	213	Local Color Transfer via Probabilistic Segmentation by Expectation-Maximization	claim
138	213	Multilinear Independent Components Analysis	claim
139	212	A Two Level Approach for Scene Recognition	claim
140	212	Diagram Structure Recognition by Bayesian Conditional Random Fields	claim
141	211	A Projector-Camera System with Real-Time Photometric Adaptation for Dynamic Environments	claim
142	211	Randomized Trees for Real-Time Keypoint Recognition	claim
143	211	A High Resolution Grammatical Model for Face Representation and Sketching	claim
144	209	A Generative Model of Human Hair for Hair Sketching	claim
145	209	Combining Object and Feature Dynamics in Probabilistic Tracking	claim
146	209	Locally Adaptive Support-Weight Approach for Visual Correspondence Search	claim
147	208	Learning to Track: Conceptual Manifold Map for Closed-Form Tracking	claim
148	207	Ensemble Tracking	claim
149	207	Beyond Pairwise Clustering	claim
150	207	Parameter Estimation for MRF Stereo	claim
151	206	Polarization Multiplexing for Bidirectional Imaging	claim
152	206	Kernel-Based Bayesian Filtering for Object Tracking	claim
153	206	Determining the Radiometric Response Function from a Single Grayscale Image	claim
154	206	Localization in Urban Environments: Monocular Vision Compared to a Differential GPS Sensor	claim
155	205	A Direct Method for Modeling Non-Rigid Motion with Thin Plate Spline	claim
156	205	Jensen-Shannon Boosting Learning for Object Recognition	claim
157	204	Evaluating Image Retrieval	claim
158	204	Dynamic Environment Exploration Using a Virtual White Cane	claim
159	203	Shape from Shading: A Well-Posed Problem?	claim
160	202	Coherent Regions for Concise and Stable Image Description	claim
161	201	Reflections on the Generalized Bas-Relief Ambiguity	claim
162	201	Geo-Consistency for Wide Multi-Camera Stereo	claim
163	201	Multimodal Face Recognition: Combination of Geometry with Physiological Information	claim
164	201	Scene-Adapted Structured Light	claim
165	201	OBJ CUT	claim
166	200	Interactive Montages of Sprites for Indexing and Summarizing Security Video	claim
167	199	Hybrid Models for Human Motion Recognition	claim
168	199	Tracking Non-Stationary Appearances and Dynamic Feature Selection	claim
169	199	Semi-Supervised Cross Feature Learning for Semantic Concept Detection in Videos	claim
170	198	Learning Appearance Manifolds from Video	claim
171	198	A Weighted Nearest Mean Classifier for Sparse Subspaces	claim
172	198	Eye Gaze Tracking under Natural Head Movements	claim
173	197	Mapping Low-Level Features to High-Level Semantic Concepts in Region-Based Image Retrieval	claim
174	196	Activity Recognition and Abnormality Detection with the Switching Hidden Semi-Markov Model	claim
175	196	A SIFT Descriptor with Global Context	claim
176	193	Optimal Point Correspondence through the Use of Rank Constraints	claim
177	193	Feature Kernel Functions: Improving SVMs Using High-Level Knowledge	claim
178	193	Segmentation of a Piece-Wise Planar Scene from Perspective Images	claim
179	192	Classification of Contour Shapes Using Class Segment Sets	claim
180	191	Facial Muscle Activations from Motion Capture	claim
181	190	Multilabel Random Walker Image Segmentation Using Prior Models	claim
182	190	Nonlinear Face Recognition Based on Maximum Average Margin Criterion	claim
183	189	Mixture Trees for Modeling and Fast Conditional Sampling with Applications in Vision and Graphics	claim
184	189	Mercer Kernels for Object Recognition with Local Features	claim
185	189	3D Reconstruction by Fitting Low-Rank Matrices with Missing Data	claim
186	189	Hand Tracking with Flocks of Features	claim
187	188	Isophote Properties as Features for Object Detection	claim
188	187	Spatial Priors for Part-Based Recognition Using Statistical Models	claim
189	187	A Cross-Validatory Statistical Approach to Scale Selection for Image Denoising by Nonlinear Diffusion	claim
190	187	Semi-Supervised Learning Based Object Detection in Aerial Imagery	claim
191	187	A Measure of Deformability of Shapes, with Applications to Human Motion Analysis	claim
192	186	Local Discriminant Embedding and Its Variants	claim
193	186	Video Epitomes	claim
194	186	Radon-Based Structure from Motion without Correspondences	claim
195	185	A Sparse Support Vector Machine Approach to Region-Based Image Categorization	claim
196	185	The Modified pbM-Estimator Method and a Runtime Analysis Technique for the RANSAC Family	claim
197	184	A Direct Method for 3D Factorization of Nonrigid Motion Observed in 2D	claim
198	184	A Tensor Decomposition for Geometric Grouping and Segmentation	claim
199	184	Detecting, Localizing and Recovering Kinematics of Textured Animals	claim
200	183	Probabilistic Modeling-Based Vessel Enhancement in Thoracic CT Scans	claim
201	183	Automatic Face Recognition for Film Character Retrieval in Feature-Length Films	claim
202	182	Unsupervised Learning of Object Features from Video Sequences	claim
203	182	Multi-Output Regularized Projection	claim
204	182	A Bayesian Mixture Model for Multi-View Face Alignment	claim
205	181	Simultaneous Modeling and Tracking (SMAT) of Feature Sets	claim
206	181	Quantitative Evaluation of a Novel Image Segmentation Algorithm	claim
207	181	Bayesian Image Segmentation Using Wavelet-Based Priors	claim
208	181	Using the Inner-Distance for Classification of Articulated Shapes	claim
209	181	Real-Time Tracking Using Level Sets	claim
210	180	Unsupervised Learning of Discriminative Edge Measures for Vehicle Matching between Non-Overlapping Cameras	claim
211	180	A Factorization-Based Approach to Articulated Motion Recovery	claim
212	179	Pruning Training Sets for Learning of Object Categories	claim
213	179	Optimal Sub-Shape Models by Minimum Description Length	claim
214	179	MosaicShape: Stochastic Region Grouping with Shape Prior	claim
215	179	Affine Object Tracking with Kernel-Based Spatial-Color Representation	claim
216	178	Hierarchical Part-Based Visual Object Categorization	claim
217	178	Nonparametric Subspace Analysis for Face Recognition	claim
218	178	Towards Complete Generic Camera Calibration	claim
219	178	Multi-View Stereo via Volumetric Graph-Cuts	claim
220	177	Appearance-Guided Particle Filtering for Articulated Hand Tracking	claim
221	177	Implicit Surfaces Make for Better Silhouettes	claim
222	177	Selection and Fusion of Color Models for Feature Detection	claim
223	177	Robust Boosting for Learning from Few Examples	claim
224	177	Decentralized Multiple Target Tracking Using Netted Collaborative Autonomous Trackers	claim
225	176	Learning Spatiotemporal T-Junctions for Occlusion Detection	claim
226	175	Identifying Semantically Equivalent Object Fragments	claim
227	175	Shock Filters Based on Implicit Cluster Separation	claim
228	175	A Unified Optimization Based Learning Method for Image Retrieval	claim
229	174	Hybrid Joint-Separable Multibody Tracking	claim
230	173	Object Class Recognition by Boosting a Part-Based Model	claim
231	173	Multiple Collaborative Kernel Tracking	claim
232	173	Finding Glass	claim
233	170	Tone Reproduction: A Perspective from Luminance-Driven Perceptual Grouping	claim
234	170	On Modelling Nonlinear Shape-and-Texture Appearance Manifolds	claim
235	170	Discriminative Training for Object Recognition Using Image Patches	claim
236	170	Energy Minimization via Graph Cuts: Settling What is Possible	claim
237	170	Vehicle Segmentation and Tracking from a Low-Angle Off-Axis Camera	claim
238	170	Pixels that Sound	claim
239	170	Detecting Doctored Images Using Camera Response Normality and Consistency	claim
240	170	Overview of the Face Recognition Grand Challenge	claim
241	170	Modelling Reflections via Multiperspective Imaging	claim
242	169	Combining Variable Selection with Dimensionality Reduction	claim
243	169	The Distinctiveness, Detectability, and Robustness of Local Image Features	claim
244	169	Ordinal Palmprint Represention for Personal Identification	claim
245	167	Two-View Geometry Estimation Unaffected by a Dominant Plane	claim
246	167	Feature Uncertainty Arising from Covariant Image Noise	claim
247	167	Learning with Constrained and Unlabelled Data	claim
248	166	Skeletal Parameter Estimation from Optical Motion Capture Data	claim
249	166	Dynamosaics: Video Mosaics with Non-Chronological Time	claim
250	165	Formulating Semantic Image Annotation as a Supervised Learning Problem	claim
251	165	Multiscale Segmentation by Combining Motion and Intensity Cues	claim
252	165	Tangent-Corrected Embedding	claim
253	164	Higher-Order Image Statistics for Unsupervised, Information-Theoretic, Adaptive, Image Filtering	claim
254	164	Indexing with Unknown Illumination and Pose	claim
255	164	A Caratheodory-Fejer Approach to Dynamic Appearance Modeling	claim
256	164	A Minimal Solution for Relative Pose with Unknown Focal Length	claim
257	163	Robust Instantaneous Rigid Motion Estimation	claim
258	163	Visibility Constrained Surface Evolution	claim
259	163	Speckle-Constrained Filtering of Ultrasound Images	claim
260	162	Camera Matchmoving in Unprepared, Unknown Environments	claim
261	162	Videoshop: A New Framework for Spatio-Temporal Video Editing in Gradient Domain	claim
262	161	Restoration and Recognition in a Loop	claim
263	161	Contrast Enhancement of Multi-Displays Using Human Contrast Sensitivity	claim
264	158	Online Modeling and Tracking of Pose-Varying Faces in Video	claim
265	158	Discriminative Density Propagation for 3D Human Motion Estimation	claim
266	157	Online Learning of Probabilistic Appearance Manifolds for Video-Based Recognition and Tracking	claim
267	152	Random Subwindows for Robust Image Classification	claim
268	152	A Flow-Based Approach to Vehicle Detection and Background Mosaicking in Airborne Video	claim
269	151	Infomax Boosting	claim
270	151	Using Particles to Track Varying Numbers of Interacting People	claim
271	148	Linear Combination Representation for Outlier Detection in Motion Tracking	claim
272	135	Recognizing Facial Expression: Machine Learning and Application to Spontaneous Behavior	claim
273	133	Why I Want a Gradient Camera	claim
274	133	Segmentation Induced by Scale Invariance	claim

Sciweavers

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers