CVPR 2004 - PDF Preprint Papers

CVPR 2004 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-2004 Paper

click to vote

CVPR
2004
IEEE

533views Computer Vision» more CVPR 2004»

An EM-Like Algorithm for Color-Histogram-Based Object Tracking

14 years 6 months ago

Download www.cse.psu.edu

Ben J. A. Kröse, Zoran Zivkovic

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	533	An EM-Like Algorithm for Color-Histogram-Based Object Tracking	claim
2	400	Effect of Colorspace Transformation, the Illuminance Component, and Color Modeling on Skin Detection	claim
3	382	Visual Odometry	claim
4	353	Bayesian Face Recognition Using Support Vector Machine and Face Clustering	claim
5	340	3D Human Pose from Silhouettes by Relevance Vector Regression	claim
6	329	Bayesian Video Matting Using Learnt Image Priors	claim
7	324	Fast, Integrated Person Tracking and Activity Recognition with Plan-View Templates from a Single Stereo Camera	claim
8	321	2D-Shape Analysis Using Conformal Mapping	claim
9	320	Scale-Invariant Shape Features for Recognition of Object Categories	claim
10	306	Fast Contour Matching Using Approximate Earth Mover's Distance	claim
11	299	Bridging the Gaps between Cameras	claim
12	296	PCA-SIFT: A More Distinctive Representation for Local Image Descriptors	claim
13	276	A Graphical Model Framework for Coupling MRFs and Deformable Models	claim
14	275	Shape Correspondence through Landmark Sliding	claim
15	270	Dual-Space Linear Discriminant Analysis for Face Recognition	claim
16	269	BoostMap: A Method for Efficient Approximate Similarity Rankings	claim
17	268	Learning Object Detection from a Small Number of Examples: The Importance of Good Features	claim
18	266	View Independent Human Body Pose Estimation from a Single Perspective Image	claim
19	257	Motion Segmentation with Missing Data Using PowerFactorization and GPCA	claim
20	256	Detection and Removal of Rain from Videos	claim
21	243	Incremental Density Approximation and Kernel-Based Bayesian Filtering for Object Tracking	claim
22	242	Studies on Silhouette Quality and Gait Recognition	claim
23	240	Detecting and Reading Text in Natural Scenes	claim
24	240	Generalized Quotient Image	claim
25	239	A Rao-Blackwellized Particle Filter for EigenTracking	claim
26	238	How Features of the Human Face Affect Recognition: A Statistical Comparison of Three Face Recognition Algorithms	claim
27	237	High-Zoom Video Hallucination by Exploiting Spatio-Temporal Regularities	claim
28	237	Feature-Centric Evaluation for Efficient Cascaded Object Detection	claim
29	236	Globally Optimal Segmentation of Interacting Surfaces with Geometric Constraints	claim
30	236	Motion Without Correspondence from Tomographic Projections by Bayesian Inversion Theory	claim
31	234	Model-Based Motion Clustering Using Boosted Mixture Modeling	claim
32	226	Motion-Based Background Subtraction Using Adaptive Kernel Density Estimation	claim
33	225	Automatic View Recognition in Echocardiogram Videos Using Parts-Based Representation	claim
34	225	Efficient Belief Propagation for Early Vision	claim
35	225	Reconstructing 3D Independent Motions Using Non-Accidentalness	claim
36	223	Is Bottom-Up Attention Useful for Object Recognition?	claim
37	219	A Discriminative Feature Space for Detecting and Recognizing Faces	claim
38	219	Alignment of Continuous Video onto 3D Point Clouds	claim
39	217	A Variational Approach to Scene Reconstruction and Image Segmentation from Motion-Blur Cues	claim
40	215	Video Data Mining Using Configurations of Viewpoint Invariant Regions	claim
41	214	Accurate Face Models from Uncalibrated and Ill-Lit Video Sequences	claim
42	214	Optimizing Motion Estimation with Linear Programming and Detail-Preserving Variational Method	claim
43	213	Wide Baseline Feature Matching Using the Cross-Epipolar Ordering Constraint	claim
44	213	Pointwise Motion Tracking in Echocardiographic Images	claim
45	212	Learning a Restricted Bayesian Network for Object Detection	claim
46	211	Atlanta World: An Expectation Maximization Framework for Simultaneous Low-Level Edge Grouping and Camera Calibration in Complex Man-Made Environments	claim
47	211	Space-Time Video Completion	claim
48	211	Face Localization via Hierarchical CONDENSATION with Fisher Boosting Feature Selection	claim
49	210	3D Facial Tracking from Corrupted Movie Sequences	claim
50	210	Thermal Face Recognition in an Operational Scenario	claim
51	210	Non-Rigid Shape and Motion Recovery: Degenerate Deformations	claim
52	209	An Unsupervised, Online Learning Framework for Moving Object Detection	claim
53	207	MetaMorphs: Deformable Shape and Texture Models	claim
54	207	Asymmetrically Boosted HMM for Speech Reading	claim
55	205	Video Repairing: Inference of Foreground and Background under Severe Occlusion	claim
56	205	Multi-Scale Visual Tracking by Sequential Belief Propagation	claim
57	204	Capturing Image Structure with Probabilistic Index Maps	claim
58	204	Learning Classifiers from Imbalanced Data Based on Biased Minimax Probability Machine	claim
59	203	Probabilistic Parameter-Free Motion Detection	claim
60	202	Motion Estimation by Swendsen-Wang Cuts	claim
61	202	A Probabilistic Framework for Combining Tracking Algorithms	claim
62	202	Bayesian Assembly of 3D Axially Symmetric Shapes from Fragments	claim
63	201	Tracking Loose-Limbed People	claim
64	199	Point Matching as a Classification Problem for Fast and Robust Object Pose Estimation	claim
65	199	Reconstructing Open Surfaces from Unorganized Data Points	claim
66	198	Multiple Bernoulli Relevance Models for Image and Video Annotation	claim
67	198	Role of Shape and Kinematics in Human Movement Analysis	claim
68	198	Hidden Semantic Concept Discovery in Region Based Image Retrieval	claim
69	197	Propagation Networks for Recognition of Partially Ordered Sequential Action	claim
70	196	An Algorithm for Multiple Object Trajectory Tracking	claim
71	196	Visual Object Categorization Using Distance-Based Discriminant Analysis	claim
72	195	Multibody Motion Segmentation Based on Simulated Annealing	claim
73	195	From Fragments to Salient Closed Boundaries: An In-Depth Study	claim
74	195	Real-Time Combined 2D+3D Active Appearance Models	claim
75	195	Recovering Shape and Reflectance Model of Non-Lambertian Objects from Multiple Views	claim
76	194	Robust Subspace Clustering by Combined Use of kNND Metric and SVD Algorithm	claim
77	194	Linear Model Hashing and Batch RANSAC for Rapid and Accurate Object Recognition	claim
78	193	Estimation, Smoothing, and Characterization of Apparent Diffusion Coefficient Profiles from High Angular Resolution DWI	claim
79	193	Visual Tracking Using Learned Linear Subspaces	claim
80	193	Restoration of Curved Document Images through 3D Shape Modeling	claim
81	192	Learning Distance Functions for Image Retrieval	claim
82	191	Making One Object Look Like Another: Controlling Appearance Using a Projector-Camera System	claim
83	189	Multigrid and Multi-Level Swendsen-Wang Cuts for Hierarchic Graph Partition	claim
84	189	Parts-Based 3D Object Classification	claim
85	188	Collaborative Tracking of Multiple Targets	claim
86	187	Robust Color Object Detection Using Spatial-Color Joint Probability Functions	claim
87	187	A New GPCA Algorithm for Clustering Subspaces by Fitting, Differentiating and Dividing Polynomials	claim
88	187	Random Sampling LDA for Face Recognition	claim
89	186	Automatic Method for Correlating Horizons across Faults in 3D Seismic Data	claim
90	183	A Probabilistic Approach to Image Orientation Detection via Confidence-Based Integration of Low-Level and Semantic Cues	claim
91	182	Value Directed Learning of Gestures and Facial Displays	claim
92	182	Tracking Multiple Humans in Crowded Environment	claim
93	181	Window-Based, Discontinuity Preserving Stereo	claim
94	181	Inferring 3D Body Pose from Silhouettes Using Activity Manifold Learning	claim
95	181	The Multibody Trifocal Tensor: Motion Segmentation from 3 Perspective Views	claim
96	180	Multiscale Conditional Random Fields for Image Labeling	claim
97	180	Radiometric Alignment of Image Sequences	claim
98	180	Extraction and Recognition of Periodically Deforming Objects by Continuous, Spatio-Temporal Shape Description	claim
99	180	Camera Calibration from a Single Night Sky Image	claim
100	179	Super-Resolution through Neighbor Embedding	claim
101	178	Radiometric Calibration of a Helmholtz Stereo Rig	claim
102	178	A Minimal Solution to the Generalised 3-Point Pose Problem	claim
103	178	Using Skew Gabor Filter in Source Signal Separation and Local Spectral Multi-Orientation Analysis	claim
104	177	Jitter Camera: High Resolution Video from a Low Resolution Detector	claim
105	177	A Flexible Projector-Camera System for Multi-Planar Displays	claim
106	177	Radiometric Calibration from a Single Image	claim
107	177	A Fast Multigrid Implicit Algorithm for the Evolution of Geodesic Active Contours	claim
108	177	Feature Selection for Classifying High-Dimensional Numerical Data	claim
109	176	Cyclic Articulated Human Motion Tracking by Sequential Ancestral Simulation	claim
110	176	Learning in Region-Based Image Retrieval with Generalized Support Vector Machines	claim
111	175	Simultaneous Calibration and Tracking with a Network of Non-Overlapping Sensors	claim
112	175	Camera Network Calibration from Dynamic Silhouettes	claim
113	174	Visual Odometry and Map Correlation	claim
114	174	A GMM Parts Based Face Representation for Improved Verification through Relevance Adaptation	claim
115	174	Elastic-String Models for Representation and Analysis of Planar Shapes	claim
116	174	Probability Models for High Dynamic Range Imaging	claim
117	174	A Discriminative Learning Framework with Pairwise Constraints for Video Object Classification	claim
118	173	Shape Representation and Classification Using the Poisson Equation	claim
119	172	Frame Synchronization and Multi-Level Subspace Analysis for Video Based Face Recognition	claim
120	172	Spatially Coherent Clustering Using Graph Cuts	claim
121	171	Modeling Complex Motion by Tracking and Editing Hidden Markov Graphs	claim
122	170	Inference of Multiple Subspaces from High-Dimensional Data and Application to Multibody Grouping	claim
123	170	Segment-Based Stereo Matching Using Graph Cuts	claim
124	170	Detecting Unusual Activity in Video	claim
125	169	Dynamic Geodesic Snakes for Visual Tracking	claim
126	169	Hybrid Textons: Modeling Surfaces with Reflectance and Geometry	claim
127	169	High-Speed Videography Using a Dense Camera Array	claim
128	169	Representation and Matching of Articulated Shapes	claim
129	168	On the Distribution of Saliency	claim
130	168	Multiple Kernel Tracking with SSD	claim
131	168	Error Analysis for a Navigation Algorithm Based on Optical-Flow and a Digital Terrain Map	claim
132	168	Difference Sphere: An Approach to Near Light Source Estimation	claim
133	168	Region-Based Progressive Stereo Matching	claim
134	167	Learning Methods for Generic Object Recognition with Invariance to Pose and Lighting	claim
135	166	3D Models Coding and Morphing for Efficient Video Compression	claim
136	166	Efficient Search of Faces from Complex Line Drawings	claim
137	166	Random Sampling Based SVM for Relevance Feedback Image Retrieval	claim
138	166	Unsupervised Learning of Image Manifolds by Semidefinite Programming	claim
139	166	Affine Image Registration Using a New Information Metric	claim
140	166	Self Shadowing and Local Illumination of Randomly Rough Surfaces	claim
141	165	Cue Integration through Discriminative Accumulation	claim
142	164	Joint Feature-Basis Subset Selection	claim
143	164	Improving Object Classification in Far-Field Video	claim
144	164	Flexible Spatial Models for Grouping Local Image Features	claim
145	163	Space-Time Isosurface Evolution for Temporally Coherent 3D Reconstruction	claim
146	162	Grouping Dominant Orientations for Ill-Structured Road Following	claim
147	162	Clear Underwater Vision	claim
148	162	Diffeomorphic Matching of Distributions: A New Approach for Unlabelled Point-Sets and Sub-Manifolds Matching	claim
149	161	Invariant Operators, Small Samples, and the Bias-Variance Dilemma	claim
150	160	Brightness Perception, Dynamic Range and Noise: A Unifying Model for Adaptive Image Sensors	claim
151	160	Multi-Classifier Framework for Atlas-Based Image Segmentation	claim
152	160	Estimating Illumination Direction from Textured Images	claim
153	160	Detection and Tracking of Objects in Underwater Video	claim
154	159	3D Head Tracking Based on Recognition and Interpolation Using a Time-of-Flight Depth Sensor	claim
155	159	A Model for Dynamic Shape and Its Applications	claim
156	159	Efficient Graphical Models for Processing Images	claim
157	158	Proposal Maps Driven MCMC for Estimating Human Body Pose in Static Images	claim
158	158	Programmable Imaging Using a Digital Micromirror Array	claim
159	158	Variational Mixture Smoothing for Non-Linear Dynamical Systems	claim
160	158	A Variational Approach to Problems in Calibration of Multiple Cameras	claim
161	157	Names and Faces in the News	claim
162	157	Probabilistic Expression Analysis on Manifolds	claim
163	157	Fast Wide Baseline Matching for Visual Navigation	claim
164	157	Sharing Features: Efficient Boosting Procedures for Multiclass Object Detection	claim
165	156	Probabilistic Identity Characterization for Face Recognition	claim
166	154	Algebraic Solution for the Visual Hull	claim
167	152	Object-Based Image Retrieval Using the Statistical Structure of Images	claim
168	152	Wavelet-Based Hierarchical Surface Approximation from Height Fields	claim
169	152	A Unified Framework for Uncertainty Propagation in Automatic Shape Tracking	claim
170	152	GCap: Graph-Based Automatic Image Captioning	claim
171	151	A Correlation-Based Model Prior for Stereo	claim
172	150	Integrating Multiple Model Views for Object Recognition	claim
173	149	Tomographic Reconstruction of Piecewise Smooth Images	claim
174	148	Bayesian Fusion of Camera Metadata Cues in Semantic Scene Classification	claim
175	148	Color Lines: Image Specific Color Representation	claim
176	148	Wide-Baseline Stereo from Multiple Views: A Probabilistic Account	claim
177	146	Segmenting, Modeling, and Matching Video Clips Containing Multiple Moving Objects	claim
178	146	Automatic Cascade Training with Perturbation Bias	claim
179	146	Searching the Web with Mobile Images for Location Recognition	claim
180	145	Multibody Factorization with Uncertainty and Missing Data Using the EM Algorithm	claim
181	145	Computing Depth under Ambient Illumination Using Multi-Shuttered Light	claim
182	145	Distortion Estimation Techniques in Solving Visual CAPTCHAs	claim
183	144	The SPS Algorithm: Patching Figural Continuity and Transparency by Split-Patch Search	claim
184	144	Spherical Harmonics vs. Haar Wavelets: Basis for Recovering Illumination from Cast Shadows	claim
185	143	Uncontrolled Modulation Imaging	claim
186	142	Local Smoothing for Manifold Learning	claim
187	142	Perceptual Organization of Radial Symmetries	claim
188	142	Covariance-Driven Mosaic Formation from Sparsely-Overlapping Image Sets with Application to Retinal Image Mosaicing	claim
189	140	Stereo Correspondence with Slanted Surfaces: Critical Implications of Horizontal Slant	claim
190	139	Efficient Tracking with the Bounded Hough Transform	claim
191	138	High Resolution Video Mosaicing with Global Alignment	claim
192	138	Robust Error Metric Analysis for Noise Estimation in Image Indexing	claim
193	137	Graphical Models for Graph Matching	claim
194	137	Separating Style and Content on a Nonlinear Manifold	claim
195	137	Lie-Algebraic Averaging for Globally Consistent Motion Estimation	claim
196	137	Shaping Receptive Fields for Affine Invariance	claim
197	136	Faster Graph-Theoretic Image Processing via Small-World and Quadtree Topologies	claim
198	135	Shedding Light on Stereoscopic Segmentation	claim
199	135	Linear Projection Methods in Face Recognition under Unconstrained Illuminations: A Comparative Study	claim
200	135	Midstream Content Access of Visual Pattern Coded Imagery	claim
201	134	Multiobjective Data Clustering	claim
202	132	Minimum Effective Dimension for Mixtures of Subspaces: A Robust GPCA Algorithm and Its Applications	claim
203	131	Grouping with Bias Revisited	claim
204	131	Scale Selection for Anisotropic Scale-Space: Application to Volumetric Tumor Characterization	claim
205	128	Using Plane + Parallax for Calibrating Dense Camera Arrays	claim
206	128	Motion Layer Extraction in the Presence of Occlusion Using Graph Cut	claim
207	126	Approximation of Canonical Sets and Their Applications to 2D View Simplification	claim
208	125	The World in an Eye	claim
209	122	Self-Normalized Linear Tests	claim
210	122	Separating Reflections from a Single Image Using Local Features	claim
211	119	Gibbs Likelihoods for Bayesian Tracking	claim
212	119	Segmentation Using Multiscale Cues	claim
213	118	Recovering Human Body Configurations: Combining Segmentation and Recognition	claim
214	114	A Unified Spatio-Temporal Articulated Model for Tracking	claim
215	113	Integrating and Employing Multiple Levels of Zoom for Activity Recognition	claim
216	113	Synchronizing Video Sequences	claim
217	112	Selecting Ghosts and Queues from a Car Trackers Output Using a Spatio-Temporal Query Language	claim
218	111	Towards Robust Structure-Based Enhancement and Horizon Picking in 3-D Seismic Data	claim
219	110	Augmenting Images of Non-Rigid Scenes Using Point and Curve Correspondences	claim
220	110	Perspective Shape-from-Shading by Fast Marching	claim
221	107	Scalable Discriminant Feature Selection for Image Retrieval and Recognition	claim

Sciweavers

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers