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

664views Computer Vision» more CVPR 2003»

Motion Segmentation with Accurate Boundaries - A Tensor Voting Approach

2 years 3 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	664	Motion Segmentation with Accurate Boundaries - A Tensor Voting Approach	claim
2	488	Learning a discriminative classifier using shape context distances	claim
3	210	Object Recognition Based on Photometric Alignment Using RANSAC	claim
4	170	Shape Context and Chamfer Matching in Cluttered Scenes	claim
5	153	An Efficient Solution to the Five-Point Relative Pose Problem	claim
6	121	Practical Super-Resolution from Dynamic Video Sequences	claim
7	112	Generalized Principal Component Analysis (GPCA)	claim
8	111	Simultaneous Structure and Texture Image Inpainting	claim
9	107	Shape-From-Silhouette of Articulated Objects and its Use for Human Body Kinematics Estimation and Motion Capture	claim
10	107	Object Class Recognition by Unsupervised Scale-Invariant Learning	claim
11	106	Learning epipolar geometry from image sequences	claim
12	103	Shape-Time Photography	claim
13	101	Multi-modal image registration by minimizing Kullback-Leibler distance between expected and observed joint class histograms	claim
14	101	Evaluation of Local Models of Dynamic Backgrounds	claim
15	99	Perception-based 3D Triangle Mesh Segmentation Using Fast Marching Watersheds	claim
16	98	Mean-shift Blob Tracking through Scale Space	claim
17	95	A Perspective on Distortions	claim
18	92	Direct 3D-Rotation Estimation from Spherical Images via a Generalized Shift Theorem	claim
19	90	Kullback-Leibler Boosting	claim
20	89	Bootstrapping SVM Active Learning by Incorporating Unlabelled Images for Image Retrieval	claim
21	87	Visual Hull Alignment and Refinement Across Time: A 3D Reconstruction Algorithm Combining Shape-From-Silhouette with Stereo	claim
22	84	Dynamic Depth Recovery from Unsynchronized Video Streams	claim
23	84	On Region Merging: The Statistical Soundness of Fast Sorting, with Applications	claim
24	82	Face Relighting with Radiance Environment Maps	claim
25	79	Robust Data Clustering	claim
26	78	Polydioptric Camera Design and 3D Motion Estimation	claim
27	77	Appearance Management and Cue Fusion for 3D Model-Based Tracking	claim
28	76	Learning Affinity Functions for Image Segmentation: Combining Patch-based and Gradient-based Approaches	claim
29	76	Man-Made Structure Detection in Natural Images using a Causal Multiscale Random Field	claim
30	75	3D Surface Modeling from Range Curves	claim
31	74	A Novel Model for Orientation Field of Fingerprints	claim
32	73	Nearest Neighbor Search for Relevance Feedback	claim
33	73	A Sparse Texture Representation Using Affine-Invariant Regions	claim
34	73	Hybrid Evolutionary Ridge Regression Approach for High-Accurate Corner Extraction	claim
35	72	Variational Inference for Visual Tracking	claim
36	72	Face Recognition Under Variable Lighting using Harmonic Image Exemplars	claim
37	72	Discovering Clusters in Motion Time-Series Data	claim
38	72	Video-Rate Stereo Depth Measurement on Programmable Hardware	claim
39	72	The Optimal Distance Measure for Object Detection	claim
40	71	3D Shape from Anisotropic Diffusion	claim
41	70	Extracting Dense Features for Visual Correspondence with Graph Cuts	claim
42	70	Toward a Stratification of Helmholtz Stereopsis	claim
43	70	Object Removal by Exemplar-Based Inpainting	claim
44	70	Face Recognition in Hyperspectral Images	claim
45	69	Eye Gaze Tracking Using an Active Stereo Head	claim
46	68	Flux Driven Fly Throughs	claim
47	68	Shedding Light on the Weather	claim
48	68	View Invariants for Human Action Recognition	claim
49	67	Kinematic Jump Processes For Monocular 3D Human Tracking	claim
50	67	Automated Feature-Based Range Registration of Urban Scenes of Large Scale	claim
51	67	Activity Recognition Using the Dynamics of the Configuration of Interacting Objects	claim
52	67	Video-Based Face Recognition Using Probabilistic Appearance Manifolds	claim
53	67	A performance evaluation of local descriptors	claim
54	66	Image Hallucination with Primal Sketch Priors	claim
55	66	Illumination Normalization with Time-dependent Intrinsic Images for Video Surveillance	claim
56	65	Curvature Correction of the Hamilton-Jacobi Skeleton	claim
57	65	Learning Bayesian Network Classifiers for Facial Expression Recognition using both Labeled and Unlabeled Data	claim
58	65	A Road Sign Recognition System Based on Dynamic Visual Model	claim
59	65	Surface Reconstruction via Helmholtz Reciprocity with a Single Image Pair	claim
60	64	Establishment Shot Detection Using Qualitative Motion	claim
61	64	Transforming Camera Geometry to A Virtual Downward-Looking Camera: Robust Ego-Motion Estimation and Ground-Layer Detection	claim
62	63	Wide-baseline Multiple-view Correspondences	claim
63	63	Surfaces with Occlusions from Layered Stereo	claim
64	63	Video-Based Face Recognition Using Adaptive Hidden Markov Models	claim
65	63	An Efficient Approach to Learning Inhomogeneous Gibbs Model	claim
66	63	Using Many Cameras as One	claim
67	62	Joint 3D-Reconstruction and Background Separation in Multiple Views using Graph Cuts	claim
68	62	PAMPAS: Real-Valued Graphical Models for Computer Vision	claim
69	62	3D Object Modeling and Recognition Using Affine-Invariant Patches and Multi-View Spatial Constraints	claim
70	61	Motion Deblurring Using Hybrid Imaging	claim
71	61	A Critical Configuration for Reconstruction from Rectilinear Motion	claim
72	61	Bayesian Human Segmentation in Crowded Situations	claim
73	60	A 2D Moving Grid Geometric Deformable Model	claim
74	59	Probabilistic Spatial Context Models for Scene Content Understanding	claim
75	59	Learning Dynamics for Exemplar-based Gesture Recognition	claim
76	58	Document Image Enhancement Using Directional Wavelet	claim
77	58	Occupant Classification System for Automotive Airbag Suppression	claim
78	58	Seeing Beyond Occlusions (and other marvels of a finite lens aperture)	claim
79	58	Simultaneous Feature Selection and Classifier Training via Linear Programming: A Case Study for Face Expression Recognition	claim
80	58	Deformable Object Tracking Using the Boundary Element Method	claim
81	57	Texture Classification: Are Filter Banks Necessary?	claim
82	57	Constrained Subspace Modelling	claim
83	57	Motion From 3D Line Correspondences: Linear and Non-Linear Solutions	claim
84	57	Statistics of Shape via Principal Geodesic Analysis on Lie Groups	claim
85	57	Recognizing Expression Variant Faces from a Single Sample Image per Class	claim
86	57	High-Accuracy Stereo Depth Maps Using Structured Light	claim
87	56	Vector-Valued Image Regularization with PDE's : A Common Framework for Different Applications	claim
88	56	Object Segmentation in Videos from Moving Camera with MRFs on Color and Motion Features	claim
89	56	Flux Invariants for Shape	claim
90	56	Using Multiple Cues for Hand Tracking and Model Refinement	claim
91	56	Fast Variable Window for Stereo Correspondence using Integral Images	claim
92	56	Robust Crease Detection in Fingerprint Images	claim
93	56	Finding and Tracking People from the Bottom Up	claim
94	55	Degeneracies, Dependencies and their Implications in Multi-body and Multi-Sequence Factorizations	claim
95	55	Representation and Detection of Deformable Shapes	claim
96	55	Shape and Materials by Example: A Photometric Stereo Approach	claim
97	55	Robust Data Association For Online Applications	claim
98	55	Simultaneous Estimation of Left Ventricular Motion and Material Properties with Maximum a Posteriori Strategy	claim
99	55	Recognising and Monitoring High-Level Behaviours in Complex Spatial Environments	claim
100	54	3D Model Retrieval With Morphing-Based Geometric and Topological Feature Maps	claim
101	54	Classification Based on Symmetric Maximized Minimal Distance in Subspace (SMMS)	claim
102	54	Implicit Meshes for Modeling and Reconstruction	claim
103	54	Continuous Tracking Within and Across Camera Streams	claim
104	53	Object Segmentation Using Graph Cuts Based Active Contours	claim
105	53	Spacetime Stereo: Shape Recovery for Dynamic Scenes	claim
106	53	Joint Manifold Distance: a new approach to appearance based clustering	claim
107	53	Local Appearance-Based Models using High-Order Statistics of Image Features	claim
108	52	A Bayesian Framework for Fusing Multiple Word Knowledge Models in Videotext Recognition	claim
109	52	Estimating 3D Hand Pose from a Cluttered Image	claim
110	52	Shadow Elimination and Occluder Light Suppression for Multi-Projector Displays	claim
111	52	Markerless Kinematic Model and Motion Capture from Volume Sequences	claim
112	52	A Bayesian Approach to Image-Based Visual Hull Reconstruction	claim
113	52	Multi-view Stereo Beyond Lambert	claim
114	52	The Viewing Graph	claim
115	52	Word Image Matching Using Dynamic Time Warping	claim
116	51	The Effects of Segmentation and Feature Choice in a Translation Model of Object Recognition	claim
117	51	Estimating the photorealism of images: Distinguishing paintings from photographs	claim
118	51	Editable Dynamic Textures	claim
119	51	Probabilistic Tracking in Joint Feature-Spatial Spaces	claim
120	51	Clustering Appearances of Objects Under Varying Illumination Conditions	claim
121	51	Qualitative Image Based Localization in Indoors Environments	claim
122	50	Nonparametric Belief Propagation	claim
123	50	Stereo Matching with Reflections and Translucency	claim
124	50	Kernel Principal Angles for Classification Machines with Applications to Image Sequence Interpretation	claim
125	50	Switching Observation Models for Contour Tracking in Clutter	claim
126	50	Multi-Resolution Real-Time Stereo on Commodity Graphics Hardware	claim
127	50	Image Repairing: Robust Image Synthesis by Adaptive ND Tensor Voting	claim
128	50	Expectation Grammars: Leveraging High-Level Expectations for Activity Recognition	claim
129	50	Active Unsupervised Texture Segmentation on a Diffusion Based Feature Space	claim
130	49	Video Segmentation Based on Graphical Models	claim
131	49	A Variational Framework for Image Segmentation Combining Motion Estimation and Shape Regularization	claim
132	49	Example-Based Style Synthesis	claim
133	49	Independent Component Analysis in a Facial Local Residue Space	claim
134	48	Feature Selection by Maximum Marginal Diversity: optimality and implications for visual recognition	claim
135	48	Tracking Appearances with Occlusions	claim
136	48	Bayesian Tangent Shape Model: Estimating Shape and Pose Parameters via Bayesian Inference	claim
137	48	Subset Selection for Efficient SVM Tracking	claim
138	48	Visual Landmarks Detection and Recognition for Mobile Robot Navigation	claim
139	48	What is the Space of Camera Response Functions?	claim
140	48	Many-to-Many Graph Matching via Metric Embedding	claim
141	48	Recognizing Objects in Adversarial Clutter: Breaking a Visual CAPTCHA	claim
142	47	Optimal Segmentation of Dynamic Scenes from Two Perspective Views	claim
143	47	Shape-based Recognition Of Wiry Objects	claim
144	47	Multi-scale Phase-based Local Features	claim
145	47	Practical Non-parametric Density Estimation on a Transformation Group for Vision	claim
146	47	Adaptive View-Based Appearance Models	claim
147	47	Scene Detection In Hollywood Movies and TV Shows	claim
148	46	Computing Layered Surface Representations: An Algorithm for Detecting and Separating Transparent Overlays	claim
149	46	Spacetime Stereo: A Unifying Framework for Depth from Triangulation	claim
150	46	Methods and Geometry for Plane-Based Self-Calibration	claim
151	46	3D Modeling Using a Statistical Sensor Model and Stochastic Search	claim
152	45	Fusing Online and Offline Information for Stable 3D Tracking in Real-Time	claim
153	45	Learning Object Intrinsic Structure for Robust Visual Tracking	claim
154	45	Learning Appearance and Transparency Manifolds of Occluded Objects in Layers	claim
155	45	Constructing 3D City Models by Merging Ground-Based and Airborne Views	claim
156	45	Deformable Pedal Curves with Application to Face Contour Extraction	claim
157	44	Object-Specific Figure-Ground Segregation	claim
158	44	Structure From Motion for Scenes Without Features	claim
159	44	Face Alignment Using Statistical Models and Wavelet Features	claim
160	43	A Hybrid Approach for Computing Visual Hulls of Complex Objects	claim
161	42	Illumination Chromaticity Estimation using Inverse-Intensity Chromaticity Space	claim
162	42	Resolution vs. tracking error: zoom as a gain controller	claim
163	42	Analyzing Appearance and Contour Based Methods for Object Categorization	claim
164	42	Graph-Theoretic Approach to Clustering and Segmentation	claim
165	41	Constraint on Five Points in Two Images	claim
166	41	Automatic Relighting of Overlapping Textures of a 3D Model	claim
167	41	Low-Dimensional Representations of Shaded Surfaces under Varying Illumination	claim
168	40	Adaptive Pattern Discovery for Interactive Multimedia Retrieval	claim
169	39	Multilinear Subspace Analysis of Image Ensembles	claim
170	38	Optimal Linear Representations of Images for Object Recognition	claim
171	38	Directional Histogram Model for Three-Dimensional Shape Similarity	claim
172	36	Pose reconstruction with an uncalibrated Computed Tomography imaging device	claim
173	35	ROD-TV: Reconstruction on Demand by Tensor Voting	claim

Sciweavers

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers