CVPR 2006 - PDF Preprint Papers

CVPR 2006 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-2006 Paper

click to vote

CVPR
2006
IEEE

797views Computer Vision» more CVPR 2006»

CSIFT: A SIFT Descriptor with Color Invariant Characteristics

2 years 3 months ago

Download people.cs.ubc.ca

SIFT has been proven to be the most robust local invariant feature descriptor. SIFT is designed mainly for gray images. However, color provides valuable information in object desc...

Alaa E. Abdel-Hakim, Aly A. Farag

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	797	CSIFT: A SIFT Descriptor with Color Invariant Characteristics	claim
2	340	SVM-KNN: Discriminative Nearest Neighbor Classification for Visual Category Recognition	claim
3	299	Diffusion Distance for Histogram Comparison	claim
4	267	Efficient Maximally Stable Extremal Region (MSER) Tracking	claim
5	218	A Closed Form Solution to Natural Image Matting	claim
6	217	Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories	claim
7	154	A Comparison and Evaluation of Multi-View Stereo Reconstruction Algorithms	claim
8	148	Image-Segmentation Evaluation From the Perspective of Salient Object Extraction	claim
9	143	On Manifold Structure of Cardiac MRI Data: Application to Segmentation	claim
10	134	RANSAC for (Quasi-)Degenerate data (QDEGSAC)	claim
11	125	3D People Tracking with Gaussian Process Dynamical Models	claim
12	118	Accurate Tracking of Monotonically Advancing Fronts	claim
13	116	Perceptually-Inspired and Edge-Directed Color Image Super-Resolution	claim
14	115	Conditional Random People: Tracking Humans with CRFs and Grid Filters	claim
15	114	Vessel Crawlers: 3D Physically-based Deformable Organisms for Vasculature Segmentation and Analysis
16	112	Automatic Discovery of Action Taxonomies from Multiple Views	claim
17	111	Body Localization in Still Images Using Hierarchical Models and Hybrid Search	claim
18	108	Clustering Appearance for Scene Analysis	claim
19	103	Shape Guided Object Segmentation	claim
20	102	Dynamic Appearance Modeling for Human Tracking	claim
21	101	Hierarchical Statistical Learning of Generic Parts of Object Structure	claim
22	99	Hierarchical Procrustes Matching for Shape Retrieval	claim
23	99	Training Deformable Models for Localization	claim
24	98	Specular Flow and the Recovery of Surface Structure	claim
25	97	A Multi-Channel Algorithm for Edge Detection Under Varying Lighting	claim
26	96	Dynamics Based Robust Motion Segmentation	claim
27	96	Scale Variant Image Pyramids	claim
28	95	Robust Fragments-based Tracking using the Integral Histogram	claim
29	95	Robust Visual Tracking Using Case-Based Reasoning with Confidence	claim
30	94	Bilayer Segmentation of Live Video	claim
31	91	An Integrated Model of Top-Down and Bottom-Up Attention for Optimizing Detection Speed	claim
32	91	Homography from Coplanar Ellipses with Application to Forensic Blood Splatter Reconstruction	claim
33	90	Control Theory and Fast Marching Techniques for Brain Connectivity Mapping	claim
34	90	Vertical Parallax from Moving Shadows	claim
35	89	Multi-Target Tracking - Linking Identities using Bayesian Network Inference	claim
36	87	AnnoSearch: Image Auto-Annotation by Search	claim
37	87	Learning Distance Metrics with Contextual Constraints for Image Retrieval	claim
38	86	An Adaptive Appearance Model Approach for Model-based Articulated Object Tracking	claim
39	84	Fast Compact City Modeling for Navigation Pre-Visualization	claim
40	84	A Shape Representation for Planar Curves by Shape Signature Harmonic Embedding	claim
41	84	Tracking of Multiple, Partially Occluded Humans based on Static Body Part Detection	claim
42	84	Multiview Geometry for Texture Mapping 2D Images Onto 3D Range Data	claim
43	84	Fast Human Detection Using a Cascade of Histograms of Oriented Gradients	claim
44	81	A Framework for Feature Selection for Background Subtraction	claim
45	81	Counting Crowded Moving Objects	claim
46	76	Recognition of Composite Human Activities through Context-Free Grammar Based Representation	claim
47	76	Depth from Familiar Objects: A Hierarchical Model for 3D Scenes	claim
48	75	3D Surface Matching and Recognition Using Conformal Geometry	claim
49	75	Local Steerable Phase (LSP) Feature for Face Representation and Recognition	claim
50	74	Shape Representation based on Integral Kernels: Application to Image Matching and Segmentation	claim
51	74	Shape Topics: A Compact Representation and New Algorithms for 3D Partial Shape Retrieval	claim
52	74	Non-Rigid Metric Shape and Motion Recovery from Uncalibrated Images Using Priors	claim
53	72	A Generalized EM Approach for 3D Model Based Face Recognition under Occlusions	claim
54	72	AdaBoost.MRF: Boosted Markov Random Forests and Application to Multilevel Activity Recognition	claim
55	71	Modeling Age Progression in Young Faces	claim
56	71	Inferring Facial Action Units with Causal Relations	claim
57	70	3D Face Recognition Using 3D Alignment for PCA	claim
58	70	Locally Linear Models on Face Appearance Manifolds with Application to Dual-Subspace Based Classification	claim
59	70	Unsupervised Bayesian Detection of Independent Motion in Crowds	claim
60	69	Multi-Camera Scene Flow by Tracking 3-D Points and Surfels	claim
61	68	Stereo Matching with Color-Weighted Correlation, Hierarchical Belief Propagation and Occlusion Handling	claim
62	68	Fusion of Detection and Matching Based Approaches for Laser Based Multiple People Tracking	claim
63	67	Recognize High Resolution Faces: From Macrocosm to Microcosm	claim
64	67	Real-time Hand Pose Recognition Using Low-Resolution Depth Images	claim
65	67	Semi-Supervised Classification Using Linear Neighborhood Propagation	claim
66	67	Unsupervised Learning of Categories from Sets of Partially Matching Image Features	claim
67	65	Context and Hierarchy in a Probabilistic Image Model	claim
68	65	Covariance Tracking using Model Update Based on Lie Algebra	claim
69	65	The Function Space of an Activity	claim
70	65	Gesture Recognition using Hidden Markov Models from Fragmented Observations	claim
71	65	A Dynamic Bayesian Network Model for Autonomous 3D Reconstruction from a Single Indoor Image	claim
72	64	Fully Automatic Registration of 3D Point Clouds	claim
73	64	Multiclass Object Recognition with Sparse, Localized Features	claim
74	64	Epipolar Geometry of Central Projection Systems Using Veronese Maps	claim
75	64	Composite Templates for Cloth Modeling and Sketching	claim
76	63	Active Graph Cuts	claim
77	63	Particle Video: Long-Range Motion Estimation using Point Trajectories	claim
78	63	Towards Multi-View Object Class Detection	claim
79	63	Incremental learning of object detectors using a visual shape alphabet	claim
80	63	3D Facial Expression Recognition Based on Primitive Surface Feature Distribution	claim
81	63	Multi-Resolution Spin-Images	claim
82	63	Image Denoising Via Learned Dictionaries and Sparse representation	claim
83	62	Bottom-Up & Top-down Object Detection using Primal Sketch Features and Graphical Models	claim
84	61	3D Reconstruction of Background and Objects Moving on Ground Plane Viewed from a Moving Camera	claim
85	61	A Visual Vocabulary for Flower Classification	claim
86	61	Automatic Kinematic Chain Building from Feature Trajectories of Articulated Objects	claim
87	61	Tracking of the Articulated Upper Body on Multi-View Stereo Image Sequences	claim
88	61	Motion Estimation from Spheres	claim
89	60	Scalable Recognition with a Vocabulary Tree	claim
90	60	A General Framework and New Alignment Criterion for Dense Optical Flow	claim
91	60	Classifying Human Dynamics Without Contact Forces	claim
92	59	Motion Patterns: High-Level Representation of Natural Video Sequences	claim
93	59	Visible Surface Reconstruction from Normals with Discontinuity Consideration	claim
94	59	Animals on the Web	claim
95	59	Element-Free Elastic Models for Volume Fitting and Capture	claim
96	58	Learning Boosted Asymmetric Classifiers for Object Detection	claim
97	58	Video Completion by Motion Field Transfer	claim
98	58	Solving Markov Random Fields using Second Order Cone Programming Relaxations	claim
99	58	Tracking With Sobolev Active Contours	claim
100	58	Robust AAM Fitting by Fusion of Images and Disparity Data	claim
101	58	Recursive estimation of generative models of video	claim
102	58	Perception Strategies in Hierarchical Vision Systems	claim
103	58	A Projective Invariant for Textures	claim
104	58	Stereo Matching with Symmetric Cost Functions	claim
105	58	BoostMotion: Boosting a Discriminative Similarity Function for Motion Estimation	claim
106	57	Nonlinear Mean Shift for Clustering over Analytic Manifolds	claim
107	57	Multiple Object Class Detection with a Generative Model	claim
108	57	Spectral Methods for Automatic Multiscale Data Clustering	claim
109	57	Affine Invariance Revisited	claim
110	57	Joint Boosting Feature Selection for Robust Face Recognition	claim
111	57	Acceleration Strategies for Gaussian Mean-Shift Image Segmentation	claim
112	57	Shape from Shading: Recognizing the Mountains through a Global View	claim
113	57	Multi-View Stereo Revisited	claim
114	56	Structure and View Estimation for Tomographic Reconstruction: A Bayesian Approach	claim
115	56	Hidden Conditional Random Fields for Gesture Recognition	claim
116	56	Simultaneous Registration and Modeling of Deformable Shapes	claim
117	56	Transformation invariant component analysis for binary images	claim
118	56	Kernel-based Template Alignment	claim
119	55	Model Order Selection and Cue Combination for Image Segmentation	claim
120	55	Applying Ensembles of Multilinear Classifiers in the Frequency Domain	claim
121	55	Image-Based Multiclass Boosting and Echocardiographic View Classification	claim
122	55	Lensless Imaging with a Controllable Aperture	claim
123	55	Aligning ASL for Statistical Translation Using a Discriminative Word Model	claim
124	55	On-line Boosting and Vision	claim
125	54	Hierarchical Volumetric Multi-view Stereo Reconstruction of Manifold Surfaces based on Dual Graph Embedding	claim
126	54	Successive Convex Matching for Action Detection	claim
127	54	Accelerated Kernel Feature Analysis	claim
128	54	Discriminative Learning of Mixture of Bayesian Network Classifiers for Sequence Classification	claim
129	54	Accurate Face Alignment using Shape Constrained Markov Network	claim
130	54	Real-Time Visual SLAM with Resilience to Erratic Motion	claim
131	54	Extracting Subimages of an Unknown Category from a Set of Images	claim
132	54	Improving Recognition of Novel Input with Similarity	claim
133	53	Single-Image Vignetting Correction	claim
134	53	A Geodesic Active Contour Framework for Finding Glass	claim
135	53	Learning Semantic Patterns with Discriminant Localized Binary Projections	claim
136	53	Differential Tracking based on Spatial-Appearance Model (SAM)	claim
137	53	A Generative-Discriminative Hybrid Method for Multi-View Object Detection	claim
138	53	Supervised Learning of Edges and Object Boundaries	claim
139	52	Correlated Label Propagation with Application to Multi-label Learning	claim
140	52	The Design of High-Level Features for Photo Quality Assessment	claim
141	52	Measure Locally, Reason Globally: Occlusion-sensitive Articulated Pose Estimation	claim
142	52	Impact of Dynamics on Subspace Embedding and Tracking of Sequences	claim
143	52	Segmentation by Level Sets and Symmetry	claim
144	52	Instant 3Descatter	claim
145	52	An Integrated Segmentation and Classification Approach Applied to Multiple Sclerosis Analysis	claim
146	52	Meta-Evaluation of Image Segmentation Using Machine Learning	claim
147	52	Shape-Based Approach to Robust Image Segmentation using Kernel PCA	claim
148	52	Robust Tracking and Stereo Matching under Variable Illumination	claim
149	51	Human Carrying Status in Visual Surveillance	claim
150	51	The Registration Problem Revisited: Optimal Solutions From Points, Lines and Planes	claim
151	50	Learning Joint Top-Down and Bottom-up Processes for 3D Visual Inference	claim
152	50	Region-based Image Annotation using Asymmetrical Support Vector Machine-based Multiple-Instance Learning	claim
153	50	Reconstruction in the Round Using Photometric Normals and Silhouettes.	claim
154	50	Quantitative Evaluation of Near Regular Texture Synthesis Algorithms	claim
155	50	An Intensity-augmented Ordinal Measure for Visual Correspondence	claim
156	50	Local Features, All Grown Up	claim
157	50	Performance Modeling and Prediction of Face Recognition Systems	claim
158	50	A New Formulation for Shape from Shading for Non-Lambertian Surfaces	claim
159	50	Structure from Motion with Known Camera Positions	claim
160	50	Efficient Optimal Kernel Placement for Reliable Visual Tracking	claim
161	50	Stereo Vision in Structured Environments by Consistent Semi-Global Matching	claim
162	49	Escaping local minima through hierarchical model selection: Automatic object discovery, segmentation, and tracking in video	claim
163	49	Cosegmentation of Image Pairs by Histogram Matching - Incorporating a Global Constraint into MRFs	claim
164	49	Learning Exemplar-Based Categorization for the Detection of Multi-View Multi-Pose Objects	claim
165	49	Learning Patch Dependencies for Improved Pose Mismatched Face Verification	claim
166	49	Augmenting Shape with Appearance in Vehicle Category Recognition	claim
167	49	Graph Partitioning by Spectral Rounding: Applications in Image Segmentation and Clustering	claim
168	49	The Panum Proxy Algorithm for Dense Stereo Matching over a Volume of Interest	claim
169	49	Rank-one Projections with Adaptive Margins for Face Recognition	claim
170	49	Spatial Divide and Conquer with Motion Cues for Tracking through Clutter	claim
171	49	Using Bilinear Models for View-invariant Action and Identity Recognition	claim
172	49	Color Subspaces as Photometric Invariants	claim
173	49	A Simple Bayesian Framework for Content-Based Image Retrieval	claim
174	48	Image Completion Using Global Optimization	claim
175	48	3-D Shape Reconstruction of Retinal Fundus	claim
176	48	Principled Hybrids of Generative and Discriminative Models	claim
177	48	Deformation Modeling for Robust 3D Face Matching	claim
178	48	Optimal Pose for Face Recognition	claim
179	48	Modeling Correspondences for Multi-Camera Tracking Using Nonlinear Manifold Learning and Target Dynamics	claim
180	48	Intelligent Collaborative Tracking by Mining Auxiliary Objects	claim
181	48	Reciprocal Image Features for Uncalibrated Helmholtz Stereopsis	claim
182	48	Reconstruction with Interval Constraints Propagation	claim
183	47	Automatic Landmark Tracking and its Application to the Optimization of Brain Conformal Mapping	claim
184	47	Contour-Based Structure from Reflection	claim
185	47	Image Matching Using Photometric Information	claim
186	47	Wire Structure Pattern Extraction and Tracking From X-Ray Images of Composite Mechanisms	claim
187	47	A Conic Section Classifier and its Application to Image Datasets	claim
188	47	Piecewise Image Registration in the Presence of Multiple Large Motions	claim
189	47	Are two rotational flows sufficient to calibrate a smooth non-parametric sensor?	claim
190	47	Equivalence of Non-Iterative Algorithms for Simultaneous Low Rank Approximations of Matrices	claim
191	46	Real Time Localization and 3D Reconstruction	claim
192	46	Space-Time Video Montage	claim
193	46	Pursuing Informative Projection on Grassmann Manifold	claim
194	46	Weakly Supervised Top-down Image Segmentation	claim
195	46	Groupwise point pattern registration using a novel CDF-based Jensen-Shannon Divergence	claim
196	46	Using Dependent Regions for Object Categorization in a Generative Framework	claim
197	46	3D Alignment of Face in a Single Image	claim
198	46	When Fisher meets Fukunaga-Koontz: A New Look at Linear Discriminants	claim
199	45	Tunable Kernels for Tracking	claim
200	45	Making a Long Video Short: Dynamic Video Synopsis	claim
201	45	Modeling and Classifying Breast Tissue Density in Mammograms	claim
202	45	Graph Laplacian Kernels for Object Classification from a Single Example	claim
203	45	Improving Border Localization of Multi-Baseline Stereo Using Border-Cut	claim
204	44	Robust multi-target tracking using spatio-temporal context	claim
205	44	Three-Dimensional Volume Reconstruction Based on Trajectory Fusion from Confocal Laser Scanning Microscope Images	claim
206	44	Unsupervised Discovery of Action Classes	claim
207	44	Automatic Cast Listing in Feature-Length Films with Anisotropic Manifold Space	claim
208	44	Combining Cues: Shape from Shading and Texture	claim
209	44	Recursive Recovery of Position and Orientation from Stereo Image Sequences without Three-Dimensional Structures	claim
210	44	A Design Principle for Coarse-to-Fine Classification	claim
211	43	Surface Geometric Constraints for Stereo in Belief Propagation	claim
212	43	Edge Suppression by Gradient Field Transformation Using Cross-Projection Tensors	claim
213	43	The Layout Consistent Random Field for Recognizing and Segmenting Partially Occluded Objects	claim
214	43	Activity Analysis in Microtubule Videos by Mixture of Hidden Markov Models	claim
215	43	Searching Off-line Arabic Documents	claim
216	43	Nonparametric Priors on the Space of Joint Intensity Distributions for Non-Rigid Multi-Modal Image Registration	claim
217	43	Scalable Monocular SLAM	claim
218	43	Dimensionality Reduction by Learning an Invariant Mapping	claim
219	43	Efficient Nonparametric Belief Propagation with Application to Articulated Body Tracking	claim
220	42	Multi-Resolution Patch Tensor for Facial Expression Hallucination	claim
221	42	Fast Variational Segmentation using Partial Extremal Initialization	claim
222	42	Separation of Highlight Reflections on Textured Surfaces	claim
223	42	Noise Estimation from a Single Image	claim
224	42	Probabilistic 3D Polyp Detection in CT Images: The Role of Sample Alignment	claim
225	42	Toward Robust Distance Metric Analysis for Similarity Estimation	claim
226	42	Learning Object Shape: From Drawings to Images	claim
227	42	Uncertainty Models in Quasiconvex Optimization for Geometric Reconstruction	claim
228	41	Landmark-Based Geodesic Computation for Heuristically Driven Path Planning	claim
229	41	Kernel Uncorrelated and Orthogonal Discriminant Analysis: A Unified Approach	claim
230	41	Selecting Principal Components in a Two-Stage LDA Algorithm	claim
231	41	Using Language to Drive the Perceptual Grouping of Local Image Features	claim
232	40	Measurement integration under inconsistency for robust tracking	claim
233	40	Estimating Intrinsic Component Images using Non-Linear Regression	claim
234	40	A Modular Approach to the Analysis and Evaluation of Particle Filters for Figure Tracking	claim
235	40	Picture Collage	claim
236	40	Identifying Color in Motion in Video Sensors	claim
237	40	Image Denoising with Shrinkage and Redundant Representations	claim
238	39	Multiple Face Model of Hybrid Fourier Feature for Large Face Image Set	claim
239	39	Ultrasound-Specific Segmentation via Decorrelation and Statistical Region-Based Active Contours	claim
240	39	Learning Non-Metric Partial Similarity Based on Maximal Margin Criterion	claim
241	39	The Bottleneck Geodesic: Computing Pixel Affinity	claim
242	39	Off-road Path Following using Region Classification and Geometric Projection Constraints	claim
243	39	Image Pre-Conditioning for Out-of-Focus Projector Blur	claim
244	39	Mesostructure from Specularity	claim
245	39	Seamless Image Stitching of Scenes with Large Motions and Exposure Differences	claim
246	39	A Refractive Camera for Acquiring Stereo and Super-resolution Images	claim
247	38	Regression-based Hand Pose Estimation from Multiple Cameras	claim
248	38	Satellite Features for the Classification of Visually Similar Classes	claim
249	38	Multi-Aspect Detection of Articulated Objects	claim
250	38	Incorporating the Boltzmann Prior in Object Detection Using SVM	claim
251	38	Object Pose Detection in Range Scan Data	claim
252	38	Reconstructing Occluded Surfaces Using Synthetic Apertures: Stereo, Focus and Robust Measures	claim
253	38	A Planar Light Probe	claim
254	38	Using Stationary-Dynamic Camera Assemblies for Wide-area Video Surveillance and Selective Attention	claim
255	37	Globally Optimal Grouping for Symmetric Boundaries	claim
256	37	Robust People Tracking with Global Trajectory Optimization	claim
257	36	Joint Recognition of Complex Events and Track Matching	claim
258	36	Discriminative Object Class Models of Appearance and Shape by Correlatons	claim
259	35	Using Multiple Segmentations to Discover Objects and their Extent in Image Collections	claim
260	35	Combined Depth and Outlier Estimation in Multi-View Stereo	claim
261	34	Statistical Analysis of Local 3D Structure in 2D Images	claim
262	34	Blind Haze Separation	claim
263	33	An Efficiency Criterion for 2D Shape Model Selection.	claim
264	33	Coupled Bayesian Framework for Dual Energy Image Registration	claim
265	33	Putting Objects in Perspective	claim
266	31	New Method of Probability Density Estimation with Application to Mutual Information Based Image Registration	claim
267	31	Shape from Dynamic Texture for Planes	claim
268	24	Spatial Weighting for Bag-of-Features	claim

Sciweavers

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers