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

1579views Computer Vision» more CVPR 2006»

CSIFT: A SIFT Descriptor with Color Invariant Characteristics

15 years 1 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	1579	CSIFT: A SIFT Descriptor with Color Invariant Characteristics	claim
2	609	SVM-KNN: Discriminative Nearest Neighbor Classification for Visual Category Recognition	claim
3	546	Diffusion Distance for Histogram Comparison	claim
4	532	Efficient Maximally Stable Extremal Region (MSER) Tracking	claim
5	480	A Closed Form Solution to Natural Image Matting	claim
6	468	A Comparison and Evaluation of Multi-View Stereo Reconstruction Algorithms	claim
7	422	Robust Fragments-based Tracking using the Integral Histogram	claim
8	414	Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories	claim
9	388	Multiview Geometry for Texture Mapping 2D Images Onto 3D Range Data	claim
10	380	Conditional Random People: Tracking Humans with CRFs and Grid Filters	claim
11	350	Image-Segmentation Evaluation From the Perspective of Salient Object Extraction	claim
12	328	3D People Tracking with Gaussian Process Dynamical Models	claim
13	328	Fast Human Detection Using a Cascade of Histograms of Oriented Gradients	claim
14	325	Robust Visual Tracking Using Case-Based Reasoning with Confidence	claim
15	325	Depth from Familiar Objects: A Hierarchical Model for 3D Scenes	claim
16	321	Accurate Tracking of Monotonically Advancing Fronts	claim
17	320	An Adaptive Appearance Model Approach for Model-based Articulated Object Tracking	claim
18	319	Specular Flow and the Recovery of Surface Structure	claim
19	313	Bilayer Segmentation of Live Video	claim
20	305	Control Theory and Fast Marching Techniques for Brain Connectivity Mapping	claim
21	305	On Manifold Structure of Cardiac MRI Data: Application to Segmentation	claim
22	298	Multi-Target Tracking - Linking Identities using Bayesian Network Inference	claim
23	298	Real Time Localization and 3D Reconstruction	claim
24	297	Non-Rigid Metric Shape and Motion Recovery from Uncalibrated Images Using Priors	claim
25	297	Automatic Discovery of Action Taxonomies from Multiple Views	claim
26	296	Counting Crowded Moving Objects	claim
27	295	Locally Linear Models on Face Appearance Manifolds with Application to Dual-Subspace Based Classification	claim
28	294	Clustering Appearance for Scene Analysis	claim
29	293	Body Localization in Still Images Using Hierarchical Models and Hybrid Search	claim
30	293	Tracking of Multiple, Partially Occluded Humans based on Static Body Part Detection	claim
31	290	RANSAC for (Quasi-)Degenerate data (QDEGSAC)	claim
32	287	Hierarchical Statistical Learning of Generic Parts of Object Structure	claim
33	287	An Integrated Model of Top-Down and Bottom-Up Attention for Optimizing Detection Speed	claim
34	284	Semi-Supervised Classification Using Linear Neighborhood Propagation	claim
35	284	3D Face Recognition Using 3D Alignment for PCA	claim
36	282	Vessel Crawlers: 3D Physically-based Deformable Organisms for Vasculature Segmentation and Analysis
37	282	Perceptually-Inspired and Edge-Directed Color Image Super-Resolution	claim
38	276	Vertical Parallax from Moving Shadows	claim
39	274	Hierarchical Procrustes Matching for Shape Retrieval	claim
40	268	A Framework for Feature Selection for Background Subtraction	claim
41	268	Training Deformable Models for Localization	claim
42	264	Shape Guided Object Segmentation	claim
43	263	Recognition of Composite Human Activities through Context-Free Grammar Based Representation	claim
44	262	Shape Topics: A Compact Representation and New Algorithms for 3D Partial Shape Retrieval	claim
45	261	Dynamic Appearance Modeling for Human Tracking	claim
46	261	A Multi-Channel Algorithm for Edge Detection Under Varying Lighting	claim
47	260	Image Denoising Via Learned Dictionaries and Sparse representation	claim
48	258	A Generalized EM Approach for 3D Model Based Face Recognition under Occlusions	claim
49	257	Unsupervised Learning of Categories from Sets of Partially Matching Image Features	claim
50	257	Automatic Landmark Tracking and its Application to the Optimization of Brain Conformal Mapping	claim
51	256	3D Facial Expression Recognition Based on Primitive Surface Feature Distribution	claim
52	256	Fast Compact City Modeling for Navigation Pre-Visualization	claim
53	255	Fusion of Detection and Matching Based Approaches for Laser Based Multiple People Tracking	claim
54	255	3-D Shape Reconstruction of Retinal Fundus	claim
55	253	Scale Variant Image Pyramids	claim
56	252	3D Reconstruction of Background and Objects Moving on Ground Plane Viewed from a Moving Camera	claim
57	250	Unsupervised Bayesian Detection of Independent Motion in Crowds	claim
58	247	Fully Automatic Registration of 3D Point Clouds	claim
59	247	Extracting Subimages of an Unknown Category from a Set of Images	claim
60	246	Using Bilinear Models for View-invariant Action and Identity Recognition	claim
61	246	Inferring Facial Action Units with Causal Relations	claim
62	245	AdaBoost.MRF: Boosted Markov Random Forests and Application to Multilevel Activity Recognition	claim
63	244	Three-Dimensional Volume Reconstruction Based on Trajectory Fusion from Confocal Laser Scanning Microscope Images	claim
64	244	Recognize High Resolution Faces: From Macrocosm to Microcosm	claim
65	242	Learning Joint Top-Down and Bottom-up Processes for 3D Visual Inference	claim
66	241	A Projective Invariant for Textures	claim
67	240	A Dynamic Bayesian Network Model for Autonomous 3D Reconstruction from a Single Indoor Image	claim
68	240	Hidden Conditional Random Fields for Gesture Recognition	claim
69	239	Joint Boosting Feature Selection for Robust Face Recognition	claim
70	238	Learning Distance Metrics with Contextual Constraints for Image Retrieval	claim
71	238	Dynamics Based Robust Motion Segmentation	claim
72	237	Gesture Recognition using Hidden Markov Models from Fragmented Observations	claim
73	236	Shape Representation based on Integral Kernels: Application to Image Matching and Segmentation	claim
74	236	Making a Long Video Short: Dynamic Video Synopsis	claim
75	234	Graph Partitioning by Spectral Rounding: Applications in Image Segmentation and Clustering	claim
76	232	Covariance Tracking using Model Update Based on Lie Algebra	claim
77	232	AnnoSearch: Image Auto-Annotation by Search	claim
78	230	Escaping local minima through hierarchical model selection: Automatic object discovery, segmentation, and tracking in video	claim
79	230	Surface Geometric Constraints for Stereo in Belief Propagation	claim
80	230	Homography from Coplanar Ellipses with Application to Forensic Blood Splatter Reconstruction	claim
81	230	Stereo Matching with Color-Weighted Correlation, Hierarchical Belief Propagation and Occlusion Handling	claim
82	229	Composite Templates for Cloth Modeling and Sketching	claim
83	224	Real-time Hand Pose Recognition Using Low-Resolution Depth Images	claim
84	222	Motion Patterns: High-Level Representation of Natural Video Sequences	claim
85	221	Active Graph Cuts	claim
86	219	Activity Analysis in Microtubule Videos by Mixture of Hidden Markov Models	claim
87	219	Incremental learning of object detectors using a visual shape alphabet	claim
88	219	3D Surface Matching and Recognition Using Conformal Geometry	claim
89	218	Context and Hierarchy in a Probabilistic Image Model	claim
90	218	A Generative-Discriminative Hybrid Method for Multi-View Object Detection	claim
91	218	Tracking With Sobolev Active Contours	claim
92	217	An Integrated Segmentation and Classification Approach Applied to Multiple Sclerosis Analysis	claim
93	217	Applying Ensembles of Multilinear Classifiers in the Frequency Domain	claim
94	217	Learning Exemplar-Based Categorization for the Detection of Multi-View Multi-Pose Objects	claim
95	216	Animals on the Web	claim
96	216	Discriminative Learning of Mixture of Bayesian Network Classifiers for Sequence Classification	claim
97	216	Solving Markov Random Fields using Second Order Cone Programming Relaxations	claim
98	216	Nonlinear Mean Shift for Clustering over Analytic Manifolds	claim
99	216	Reconstruction in the Round Using Photometric Normals and Silhouettes.	claim
100	215	Principled Hybrids of Generative and Discriminative Models	claim
101	215	A Visual Vocabulary for Flower Classification	claim
102	215	Probabilistic 3D Polyp Detection in CT Images: The Role of Sample Alignment	claim
103	214	A General Framework and New Alignment Criterion for Dense Optical Flow	claim
104	214	On-line Boosting and Vision	claim
105	213	A Simple Bayesian Framework for Content-Based Image Retrieval	claim
106	213	Multiclass Object Recognition with Sparse, Localized Features	claim
107	213	Measure Locally, Reason Globally: Occlusion-sensitive Articulated Pose Estimation	claim
108	211	Acceleration Strategies for Gaussian Mean-Shift Image Segmentation	claim
109	209	Modeling Age Progression in Young Faces	claim
110	209	Simultaneous Registration and Modeling of Deformable Shapes	claim
111	209	Automatic Kinematic Chain Building from Feature Trajectories of Articulated Objects	claim
112	209	Cosegmentation of Image Pairs by Histogram Matching - Incorporating a Global Constraint into MRFs	claim
113	208	Accelerated Kernel Feature Analysis	claim
114	208	Bottom-Up & Top-down Object Detection using Primal Sketch Features and Graphical Models	claim
115	208	Performance Modeling and Prediction of Face Recognition Systems	claim
116	208	Learning Semantic Patterns with Discriminant Localized Binary Projections	claim
117	208	Robust Tracking and Stereo Matching under Variable Illumination	claim
118	208	Robust multi-target tracking using spatio-temporal context	claim
119	207	Supervised Learning of Edges and Object Boundaries	claim
120	207	A Shape Representation for Planar Curves by Shape Signature Harmonic Embedding	claim
121	206	Accurate Face Alignment using Shape Constrained Markov Network	claim
122	206	Recursive estimation of generative models of video	claim
123	205	Epipolar Geometry of Central Projection Systems Using Veronese Maps	claim
124	204	The Design of High-Level Features for Photo Quality Assessment	claim
125	204	Object Pose Detection in Range Scan Data	claim
126	202	Spectral Methods for Automatic Multiscale Data Clustering	claim
127	202	Spatial Divide and Conquer with Motion Cues for Tracking through Clutter	claim
128	200	Robust AAM Fitting by Fusion of Images and Disparity Data	claim
129	199	Affine Invariance Revisited	claim
130	199	Modeling and Classifying Breast Tissue Density in Mammograms	claim
131	199	Multi-View Stereo Revisited	claim
132	199	Segmentation by Level Sets and Symmetry	claim
133	199	BoostMotion: Boosting a Discriminative Similarity Function for Motion Estimation	claim
134	199	Fast Variational Segmentation using Partial Extremal Initialization	claim
135	198	Dimensionality Reduction by Learning an Invariant Mapping	claim
136	198	Multiple Object Class Detection with a Generative Model	claim
137	197	Visible Surface Reconstruction from Normals with Discontinuity Consideration	claim
138	197	Particle Video: Long-Range Motion Estimation using Point Trajectories	claim
139	196	Correlated Label Propagation with Application to Multi-label Learning	claim
140	195	Stereo Vision in Structured Environments by Consistent Semi-Global Matching	claim
141	195	Learning Boosted Asymmetric Classifiers for Object Detection	claim
142	195	Groupwise point pattern registration using a novel CDF-based Jensen-Shannon Divergence	claim
143	194	Shape-Based Approach to Robust Image Segmentation using Kernel PCA	claim
144	194	Aligning ASL for Statistical Translation Using a Discriminative Word Model	claim
145	194	Motion Estimation from Spheres	claim
146	193	Structure and View Estimation for Tomographic Reconstruction: A Bayesian Approach	claim
147	193	Using Dependent Regions for Object Categorization in a Generative Framework	claim
148	192	3D Alignment of Face in a Single Image	claim
149	192	Classifying Human Dynamics Without Contact Forces	claim
150	192	Modeling Correspondences for Multi-Camera Tracking Using Nonlinear Manifold Learning and Target Dynamics	claim
151	192	The Function Space of an Activity	claim
152	190	A Geodesic Active Contour Framework for Finding Glass	claim
153	190	Intelligent Collaborative Tracking by Mining Auxiliary Objects	claim
154	190	Blind Haze Separation	claim
155	189	Model Order Selection and Cue Combination for Image Segmentation	claim
156	189	Color Subspaces as Photometric Invariants	claim
157	188	Hierarchical Volumetric Multi-view Stereo Reconstruction of Manifold Surfaces based on Dual Graph Embedding	claim
158	186	Graph Laplacian Kernels for Object Classification from a Single Example	claim
159	186	Impact of Dynamics on Subspace Embedding and Tracking of Sequences	claim
160	185	Differential Tracking based on Spatial-Appearance Model (SAM)	claim
161	185	Satellite Features for the Classification of Visually Similar Classes	claim
162	184	Multi-Camera Scene Flow by Tracking 3-D Points and Surfels	claim
163	184	Image-Based Multiclass Boosting and Echocardiographic View Classification	claim
164	184	Local Steerable Phase (LSP) Feature for Face Representation and Recognition	claim
165	184	Towards Multi-View Object Class Detection	claim
166	183	A Conic Section Classifier and its Application to Image Datasets	claim
167	183	Seamless Image Stitching of Scenes with Large Motions and Exposure Differences	claim
168	183	Kernel-based Template Alignment	claim
169	182	Multiple Face Model of Hybrid Fourier Feature for Large Face Image Set	claim
170	182	Single-Image Vignetting Correction	claim
171	181	Learning Object Shape: From Drawings to Images	claim
172	181	Noise Estimation from a Single Image	claim
173	181	Tracking of the Articulated Upper Body on Multi-View Stereo Image Sequences	claim
174	181	Combined Depth and Outlier Estimation in Multi-View Stereo	claim
175	181	Estimating Intrinsic Component Images using Non-Linear Regression	claim
176	180	Combining Cues: Shape from Shading and Texture	claim
177	178	Unsupervised Discovery of Action Classes	claim
178	177	Edge Suppression by Gradient Field Transformation Using Cross-Projection Tensors	claim
179	177	Shape from Shading: Recognizing the Mountains through a Global View	claim
180	176	Space-Time Video Montage	claim
181	176	Quantitative Evaluation of Near Regular Texture Synthesis Algorithms	claim
182	176	Optimal Pose for Face Recognition	claim
183	176	Stereo Matching with Symmetric Cost Functions	claim
184	176	Ultrasound-Specific Segmentation via Decorrelation and Statistical Region-Based Active Contours	claim
185	175	Automatic Cast Listing in Feature-Length Films with Anisotropic Manifold Space	claim
186	175	Scalable Monocular SLAM	claim
187	175	A Refractive Camera for Acquiring Stereo and Super-resolution Images	claim
188	175	Image Matching Using Photometric Information	claim
189	175	Scalable Recognition with a Vocabulary Tree	claim
190	174	Rank-one Projections with Adaptive Margins for Face Recognition	claim
191	174	Learning Non-Metric Partial Similarity Based on Maximal Margin Criterion	claim
192	173	The Panum Proxy Algorithm for Dense Stereo Matching over a Volume of Interest	claim
193	173	Multi-Resolution Patch Tensor for Facial Expression Hallucination	claim
194	173	Successive Convex Matching for Action Detection	claim
195	173	Deformation Modeling for Robust 3D Face Matching	claim
196	173	Real-Time Visual SLAM with Resilience to Erratic Motion	claim
197	172	Image Pre-Conditioning for Out-of-Focus Projector Blur	claim
198	172	A Design Principle for Coarse-to-Fine Classification	claim
199	172	Efficient Nonparametric Belief Propagation with Application to Articulated Body Tracking	claim
200	171	An Intensity-augmented Ordinal Measure for Visual Correspondence	claim
201	170	Reconstructing Occluded Surfaces Using Synthetic Apertures: Stereo, Focus and Robust Measures	claim
202	170	Lensless Imaging with a Controllable Aperture	claim
203	169	Structure from Motion with Known Camera Positions	claim
204	169	Incorporating the Boltzmann Prior in Object Detection Using SVM	claim
205	169	Augmenting Shape with Appearance in Vehicle Category Recognition	claim
206	169	Perception Strategies in Hierarchical Vision Systems	claim
207	169	Meta-Evaluation of Image Segmentation Using Machine Learning	claim
208	169	Human Carrying Status in Visual Surveillance	claim
209	168	Are two rotational flows sufficient to calibrate a smooth non-parametric sensor?	claim
210	168	Putting Objects in Perspective	claim
211	168	The Registration Problem Revisited: Optimal Solutions From Points, Lines and Planes	claim
212	168	The Layout Consistent Random Field for Recognizing and Segmenting Partially Occluded Objects	claim
213	168	Selecting Principal Components in a Two-Stage LDA Algorithm	claim
214	168	Region-based Image Annotation using Asymmetrical Support Vector Machine-based Multiple-Instance Learning	claim
215	165	Piecewise Image Registration in the Presence of Multiple Large Motions	claim
216	165	Searching Off-line Arabic Documents	claim
217	165	Element-Free Elastic Models for Volume Fitting and Capture	claim
218	165	An Efficiency Criterion for 2D Shape Model Selection.	claim
219	164	Mesostructure from Specularity	claim
220	164	Measurement integration under inconsistency for robust tracking	claim
221	164	Contour-Based Structure from Reflection	claim
222	164	Image Completion Using Global Optimization	claim
223	164	Instant 3Descatter	claim
224	164	Identifying Color in Motion in Video Sensors	claim
225	163	A New Formulation for Shape from Shading for Non-Lambertian Surfaces	claim
226	163	Improving Recognition of Novel Input with Similarity	claim
227	163	Transformation invariant component analysis for binary images	claim
228	163	Video Completion by Motion Field Transfer	claim
229	162	Robust People Tracking with Global Trajectory Optimization	claim
230	161	Off-road Path Following using Region Classification and Geometric Projection Constraints	claim
231	161	Equivalence of Non-Iterative Algorithms for Simultaneous Low Rank Approximations of Matrices	claim
232	161	Local Features, All Grown Up	claim
233	161	Reciprocal Image Features for Uncalibrated Helmholtz Stereopsis	claim
234	160	A Planar Light Probe	claim
235	160	Efficient Optimal Kernel Placement for Reliable Visual Tracking	claim
236	160	Reconstruction with Interval Constraints Propagation	claim
237	160	Pursuing Informative Projection on Grassmann Manifold	claim
238	160	New Method of Probability Density Estimation with Application to Mutual Information Based Image Registration	claim
239	159	Statistical Analysis of Local 3D Structure in 2D Images	claim
240	157	Improving Border Localization of Multi-Baseline Stereo Using Border-Cut	claim
241	155	Kernel Uncorrelated and Orthogonal Discriminant Analysis: A Unified Approach	claim
242	155	When Fisher meets Fukunaga-Koontz: A New Look at Linear Discriminants	claim
243	152	Uncertainty Models in Quasiconvex Optimization for Geometric Reconstruction	claim
244	152	Wire Structure Pattern Extraction and Tracking From X-Ray Images of Composite Mechanisms	claim
245	151	Recursive Recovery of Position and Orientation from Stereo Image Sequences without Three-Dimensional Structures	claim
246	150	Using Multiple Segmentations to Discover Objects and their Extent in Image Collections	claim
247	149	Picture Collage	claim
248	148	Multi-Resolution Spin-Images	claim
249	147	Image Denoising with Shrinkage and Redundant Representations	claim
250	147	Using Stationary-Dynamic Camera Assemblies for Wide-area Video Surveillance and Selective Attention	claim
251	145	A Modular Approach to the Analysis and Evaluation of Particle Filters for Figure Tracking	claim
252	144	Learning Patch Dependencies for Improved Pose Mismatched Face Verification	claim
253	144	Multi-Aspect Detection of Articulated Objects	claim
254	143	The Bottleneck Geodesic: Computing Pixel Affinity	claim
255	143	Landmark-Based Geodesic Computation for Heuristically Driven Path Planning	claim
256	141	Shape from Dynamic Texture for Planes	claim
257	140	Weakly Supervised Top-down Image Segmentation	claim
258	139	Coupled Bayesian Framework for Dual Energy Image Registration	claim
259	139	Toward Robust Distance Metric Analysis for Similarity Estimation	claim
260	139	Discriminative Object Class Models of Appearance and Shape by Correlatons	claim
261	138	Tunable Kernels for Tracking	claim
262	137	Using Language to Drive the Perceptual Grouping of Local Image Features	claim
263	136	Nonparametric Priors on the Space of Joint Intensity Distributions for Non-Rigid Multi-Modal Image Registration	claim
264	132	Joint Recognition of Complex Events and Track Matching	claim
265	130	Separation of Highlight Reflections on Textured Surfaces	claim
266	129	Regression-based Hand Pose Estimation from Multiple Cameras	claim
267	122	Globally Optimal Grouping for Symmetric Boundaries	claim
268	115	Spatial Weighting for Bag-of-Features	claim

Sciweavers

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers