CVPR 2003 - PDF Preprint Papers

CVPR 2003 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-2003 Paper

click to vote

CVPR
2003
IEEE

1110views Computer Vision» more CVPR 2003»

Motion Segmentation with Accurate Boundaries - A Tensor Voting Approach

15 years 2 months ago

Download www.cse.unr.edu

Producing an accurate motion flow field is very difficult at motion boundaries. We present a novel, noniterative approach for segmentation from image motion, based on two voting p...

Gérard G. Medioni, Mircea Nicolescu

claim paper

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	1110	Motion Segmentation with Accurate Boundaries - A Tensor Voting Approach	claim
2	714	Learning a discriminative classifier using shape context distances	claim
3	414	High-Accuracy Stereo Depth Maps Using Structured Light	claim
4	387	Object Recognition Based on Photometric Alignment Using RANSAC	claim
5	366	Shape Context and Chamfer Matching in Cluttered Scenes	claim
6	333	An Efficient Solution to the Five-Point Relative Pose Problem	claim
7	325	Practical Super-Resolution from Dynamic Video Sequences	claim
8	323	Shape-From-Silhouette of Articulated Objects and its Use for Human Body Kinematics Estimation and Motion Capture	claim
9	306	Simultaneous Structure and Texture Image Inpainting	claim
10	306	Object Class Recognition by Unsupervised Scale-Invariant Learning	claim
11	297	Shedding Light on the Weather	claim
12	292	3D Surface Modeling from Range Curves	claim
13	290	Activity Recognition Using the Dynamics of the Configuration of Interacting Objects	claim
14	282	Multi-modal image registration by minimizing Kullback-Leibler distance between expected and observed joint class histograms	claim
15	279	View Invariants for Human Action Recognition	claim
16	277	Direct 3D-Rotation Estimation from Spherical Images via a Generalized Shift Theorem	claim
17	276	Visual Hull Alignment and Refinement Across Time: A 3D Reconstruction Algorithm Combining Shape-From-Silhouette with Stereo	claim
18	273	Learning Affinity Functions for Image Segmentation: Combining Patch-based and Gradient-based Approaches	claim
19	270	3D Object Modeling and Recognition Using Affine-Invariant Patches and Multi-View Spatial Constraints	claim
20	268	Face Recognition Under Variable Lighting using Harmonic Image Exemplars	claim
21	264	Evaluation of Local Models of Dynamic Backgrounds	claim
22	264	Appearance Management and Cue Fusion for 3D Model-Based Tracking	claim
23	262	Video-Based Face Recognition Using Adaptive Hidden Markov Models	claim
24	262	Learning epipolar geometry from image sequences	claim
25	261	On Region Merging: The Statistical Soundness of Fast Sorting, with Applications	claim
26	255	Perception-based 3D Triangle Mesh Segmentation Using Fast Marching Watersheds	claim
27	255	Dynamic Depth Recovery from Unsynchronized Video Streams	claim
28	249	A Bayesian Framework for Fusing Multiple Word Knowledge Models in Videotext Recognition	claim
29	248	The Optimal Distance Measure for Object Detection	claim
30	245	Face Relighting with Radiance Environment Maps	claim
31	243	Continuous Tracking Within and Across Camera Streams	claim
32	241	Mean-shift Blob Tracking through Scale Space	claim
33	241	Polydioptric Camera Design and 3D Motion Estimation	claim
34	237	Joint 3D-Reconstruction and Background Separation in Multiple Views using Graph Cuts	claim
35	235	Motion Deblurring Using Hybrid Imaging	claim
36	235	Video-Based Face Recognition Using Probabilistic Appearance Manifolds	claim
37	234	Clustering Appearances of Objects Under Varying Illumination Conditions	claim
38	234	Generalized Principal Component Analysis (GPCA)	claim
39	233	Nearest Neighbor Search for Relevance Feedback	claim
40	232	Object Segmentation Using Graph Cuts Based Active Contours	claim
41	232	Surface Reconstruction via Helmholtz Reciprocity with a Single Image Pair	claim
42	230	Learning Bayesian Network Classifiers for Facial Expression Recognition using both Labeled and Unlabeled Data	claim
43	229	Man-Made Structure Detection in Natural Images using a Causal Multiscale Random Field	claim
44	228	Transforming Camera Geometry to A Virtual Downward-Looking Camera: Robust Ego-Motion Estimation and Ground-Layer Detection	claim
45	228	Shape and Materials by Example: A Photometric Stereo Approach	claim
46	225	Statistics of Shape via Principal Geodesic Analysis on Lie Groups	claim
47	223	Eye Gaze Tracking Using an Active Stereo Head	claim
48	222	A 2D Moving Grid Geometric Deformable Model	claim
49	222	Kullback-Leibler Boosting	claim
50	221	Automated Feature-Based Range Registration of Urban Scenes of Large Scale	claim
51	221	Bootstrapping SVM Active Learning by Incorporating Unlabelled Images for Image Retrieval	claim
52	220	Joint Manifold Distance: a new approach to appearance based clustering	claim
53	220	3D Model Retrieval With Morphing-Based Geometric and Topological Feature Maps	claim
54	219	Kernel Principal Angles for Classification Machines with Applications to Image Sequence Interpretation	claim
55	218	Illumination Normalization with Time-dependent Intrinsic Images for Video Surveillance	claim
56	218	Variational Inference for Visual Tracking	claim
57	218	A Perspective on Distortions	claim
58	216	PAMPAS: Real-Valued Graphical Models for Computer Vision	claim
59	215	Image Hallucination with Primal Sketch Priors	claim
60	214	Finding and Tracking People from the Bottom Up	claim
61	212	Bayesian Human Segmentation in Crowded Situations	claim
62	210	Flux Driven Fly Throughs	claim
63	210	Active Unsupervised Texture Segmentation on a Diffusion Based Feature Space	claim
64	209	A Road Sign Recognition System Based on Dynamic Visual Model	claim
65	209	Extracting Dense Features for Visual Correspondence with Graph Cuts	claim
66	208	Multi-scale Phase-based Local Features	claim
67	208	Using Multiple Cues for Hand Tracking and Model Refinement	claim
68	208	Word Image Matching Using Dynamic Time Warping	claim
69	207	Surfaces with Occlusions from Layered Stereo	claim
70	206	Robust Data Clustering	claim
71	206	Using Many Cameras as One	claim
72	204	Object Removal by Exemplar-Based Inpainting	claim
73	204	A Bayesian Approach to Image-Based Visual Hull Reconstruction	claim
74	203	3D Shape from Anisotropic Diffusion	claim
75	201	Simultaneous Feature Selection and Classifier Training via Linear Programming: A Case Study for Face Expression Recognition	claim
76	200	Analyzing Appearance and Contour Based Methods for Object Categorization	claim
77	199	Representation and Detection of Deformable Shapes	claim
78	199	A Sparse Texture Representation Using Affine-Invariant Regions	claim
79	198	What is the Space of Camera Response Functions?	claim
80	198	Simultaneous Estimation of Left Ventricular Motion and Material Properties with Maximum a Posteriori Strategy	claim
81	198	Multi-Resolution Real-Time Stereo on Commodity Graphics Hardware	claim
82	197	A Critical Configuration for Reconstruction from Rectilinear Motion	claim
83	197	Implicit Meshes for Modeling and Reconstruction	claim
84	196	Shape-Time Photography	claim
85	196	Deformable Object Tracking Using the Boundary Element Method	claim
86	196	Learning Object Intrinsic Structure for Robust Visual Tracking	claim
87	195	Qualitative Image Based Localization in Indoors Environments	claim
88	195	Face Recognition in Hyperspectral Images	claim
89	194	Adaptive View-Based Appearance Models	claim
90	194	Bayesian Tangent Shape Model: Estimating Shape and Pose Parameters via Bayesian Inference	claim
91	193	Face Alignment Using Statistical Models and Wavelet Features	claim
92	191	Object Segmentation in Videos from Moving Camera with MRFs on Color and Motion Features	claim
93	191	Document Image Enhancement Using Directional Wavelet	claim
94	191	Spacetime Stereo: Shape Recovery for Dynamic Scenes	claim
95	190	Recognising and Monitoring High-Level Behaviours in Complex Spatial Environments	claim
96	190	Graph-Theoretic Approach to Clustering and Segmentation	claim
97	189	Probabilistic Spatial Context Models for Scene Content Understanding	claim
98	188	A Novel Model for Orientation Field of Fingerprints	claim
99	188	Estimating the photorealism of images: Distinguishing paintings from photographs	claim
100	188	Fusing Online and Offline Information for Stable 3D Tracking in Real-Time	claim
101	187	Wide-baseline Multiple-view Correspondences	claim
102	187	A performance evaluation of local descriptors	claim
103	185	Learning Appearance and Transparency Manifolds of Occluded Objects in Layers	claim
104	185	Scene Detection In Hollywood Movies and TV Shows	claim
105	184	Discovering Clusters in Motion Time-Series Data	claim
106	181	Visual Landmarks Detection and Recognition for Mobile Robot Navigation	claim
107	181	Nonparametric Belief Propagation	claim
108	180	Local Appearance-Based Models using High-Order Statistics of Image Features	claim
109	180	Optimal Segmentation of Dynamic Scenes from Two Perspective Views	claim
110	179	Adaptive Pattern Discovery for Interactive Multimedia Retrieval	claim
111	178	Expectation Grammars: Leveraging High-Level Expectations for Activity Recognition	claim
112	177	Practical Non-parametric Density Estimation on a Transformation Group for Vision	claim
113	176	Video-Rate Stereo Depth Measurement on Programmable Hardware	claim
114	176	Video Segmentation Based on Graphical Models	claim
115	175	Subset Selection for Efficient SVM Tracking	claim
116	175	Learning Dynamics for Exemplar-based Gesture Recognition	claim
117	175	Independent Component Analysis in a Facial Local Residue Space	claim
118	174	Many-to-Many Graph Matching via Metric Embedding	claim
119	174	Curvature Correction of the Hamilton-Jacobi Skeleton	claim
120	173	Recognizing Objects in Adversarial Clutter: Breaking a Visual CAPTCHA	claim
121	172	Hybrid Evolutionary Ridge Regression Approach for High-Accurate Corner Extraction	claim
122	172	Toward a Stratification of Helmholtz Stereopsis	claim
123	169	Vector-Valued Image Regularization with PDE's : A Common Framework for Different Applications	claim
124	169	Stereo Matching with Reflections and Translucency	claim
125	167	Establishment Shot Detection Using Qualitative Motion	claim
126	167	Methods and Geometry for Plane-Based Self-Calibration	claim
127	167	An Efficient Approach to Learning Inhomogeneous Gibbs Model	claim
128	165	Tracking Appearances with Occlusions	claim
129	164	Motion From 3D Line Correspondences: Linear and Non-Linear Solutions	claim
130	164	Example-Based Style Synthesis	claim
131	164	3D Modeling Using a Statistical Sensor Model and Stochastic Search	claim
132	164	Structure From Motion for Scenes Without Features	claim
133	163	Editable Dynamic Textures	claim
134	162	Probabilistic Tracking in Joint Feature-Spatial Spaces	claim
135	162	Fast Variable Window for Stereo Correspondence using Integral Images	claim
136	161	Kinematic Jump Processes For Monocular 3D Human Tracking	claim
137	160	Shape-based Recognition Of Wiry Objects	claim
138	160	The Viewing Graph	claim
139	160	Low-Dimensional Representations of Shaded Surfaces under Varying Illumination	claim
140	160	Degeneracies, Dependencies and their Implications in Multi-body and Multi-Sequence Factorizations	claim
141	158	Switching Observation Models for Contour Tracking in Clutter	claim
142	158	Deformable Pedal Curves with Application to Face Contour Extraction	claim
143	156	Texture Classification: Are Filter Banks Necessary?	claim
144	155	Automatic Relighting of Overlapping Textures of a 3D Model	claim
145	155	A Variational Framework for Image Segmentation Combining Motion Estimation and Shape Regularization	claim
146	155	Illumination Chromaticity Estimation using Inverse-Intensity Chromaticity Space	claim
147	155	Constrained Subspace Modelling	claim
148	154	Shadow Elimination and Occluder Light Suppression for Multi-Projector Displays	claim
149	154	Spacetime Stereo: A Unifying Framework for Depth from Triangulation	claim
150	153	Computing Layered Surface Representations: An Algorithm for Detecting and Separating Transparent Overlays	claim
151	153	Robust Crease Detection in Fingerprint Images	claim
152	152	Flux Invariants for Shape	claim
153	152	Occupant Classification System for Automotive Airbag Suppression	claim
154	152	Constraint on Five Points in Two Images	claim
155	151	Image Repairing: Robust Image Synthesis by Adaptive ND Tensor Voting	claim
156	149	Seeing Beyond Occlusions (and other marvels of a finite lens aperture)	claim
157	149	Multi-view Stereo Beyond Lambert	claim
158	149	Robust Data Association For Online Applications	claim
159	148	A Hybrid Approach for Computing Visual Hulls of Complex Objects	claim
160	148	Directional Histogram Model for Three-Dimensional Shape Similarity	claim
161	146	Markerless Kinematic Model and Motion Capture from Volume Sequences	claim
162	146	Object-Specific Figure-Ground Segregation	claim
163	146	Classification Based on Symmetric Maximized Minimal Distance in Subspace (SMMS)	claim
164	143	Estimating 3D Hand Pose from a Cluttered Image	claim
165	142	Optimal Linear Representations of Images for Object Recognition	claim
166	142	Feature Selection by Maximum Marginal Diversity: optimality and implications for visual recognition	claim
167	139	Resolution vs. tracking error: zoom as a gain controller	claim
168	139	Constructing 3D City Models by Merging Ground-Based and Airborne Views	claim
169	135	The Effects of Segmentation and Feature Choice in a Translation Model of Object Recognition	claim
170	134	Multilinear Subspace Analysis of Image Ensembles	claim
171	133	Pose reconstruction with an uncalibrated Computed Tomography imaging device	claim
172	131	Recognizing Expression Variant Faces from a Single Sample Image per Class	claim
173	117	ROD-TV: Reconstruction on Demand by Tensor Voting	claim

Sciweavers

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers