CVPR 2011 - PDF Preprint Papers

CVPR 2011 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-2011 Paper

click to vote

CVPR
2011
IEEE

837views Computer Vision» more CVPR 2011»

The Light-Path Less Traveled

1 years 1 months ago

Download perception.inrialpes.fr

This paper extends classical object pose and relative camera motion estimation algorithms for imaging sensors sampling the scene through light-paths. Many algorithms in multi-view...

Srikumar Ramalingam, Sofien Bouaziz, Peter Sturm, ...

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	837	The Light-Path Less Traveled	claim
2	659	Reconstructing an image from its local descriptors
3	562	Image analysis by counting on a grid	claim
4	507	What makes an image memorable?	claim
5	479	Object Recognition with Hierarchical Kernel Descriptors
6	420	Coupled Information-Theoretic Encoding for Face Photo-Sketch Recognition	claim
7	330	Intrinsic Dense 3D Surface Tracking	claim
8	321	Real-time Human Pose Recognition in Parts from Single Depth Images	claim
9	304	Is face recognition really a Compressive Sensing problem?	claim
10	297	Learning A Discriminative Dictionary for Sparse Coding via Label Consistent K-SVD	claim
11	293	Hyper-graph Matching via Reweighted Random Walks
12	266	Foreground Segmentation of Live Videos using Locally Competing 1SVMs	claim
13	260	Global Contrast based Salient Region Detection
14	256	Online Group-Structured Dictionary Learning	claim
15	238	A Probabilistic Model for Recursive Factorized Image Features	claim
16	238	Robust Sparse Coding for Face Recognition	claim
17	229	Learning structured prediction models for interactive image labeling	claim
18	228	Image Retrieval with Geometry-Preserving Visual Phrases	claim
19	226	Unbiased Look at Dataset Bias	claim
20	221	Stable Multi-Target Tracking in Real-Time Surveillance Video
21	218	Unsupervised Auxiliary Visual Words Discovery for Large-Scale Image Object Retrieval	claim
22	216	Sparsity-based Image Denoising via Dictionary Learning and Structural Clustering	claim
23	214	Iterative Quantization: A Procrustean Approach to Learning Binary Codes	claim
24	206	A generative model for 3D urban scene understanding from movable platforms
25	204	Reduced Epipolar Cost for Accelerated Incremental SfM
26	199	Dynamic Batch Mode Active Learning	claim
27	197	What Makes a Chair a Chair?	claim
28	196	Recognizing Human Actions by Attributes
29	194	Towards a practical lipreading system	claim
30	194	Learning Better Image Representations Using 'Flobject Analysis'	claim
31	186	From 3D Scene Geometry to Human Workspace	claim
32	186	Random Field Topic Model for Semantic Region Analysis in Crowded Scenes from Tracklets	claim
33	182	Sparse Image Representation with Epitomes	claim
34	181	Where's Waldo: Matching People in Images of Crowds	claim
35	181	Learning Hierarchical Poselets for Human Parsing	claim
36	175	PClines - Line Detection Using Parallel Coordinates	claim
37	173	Auto Directed Video Stabilization with Robust L1 Optimal Camera Paths	claim
38	173	Natural Image Denoising: Optimality and Inherent Bounds	claim
39	173	Inference for Order Reduction in Markov Random Fields
40	170	Extracting and Locating Temporal Motifs in Video Scenes Using a Hierarchical Non Parametric Bayesian Model	claim
41	170	Globally-Optimal Greedy Algorithms for Tracking a Variable Number of Objects	claim
42	169	Distributed Message Passing for Large Scale Graphical Models	claim
43	169	Discriminative Spatial Pyramid	claim
44	169	Using Global Bag of Features Models in Random Fields for Joint Categorization and Segmentation of Objects	claim
45	168	2D Nonrigid Partial Shape Matching Using MCMC and Contour Subdivision
46	168	Are Sparse Representations Really Relevant for Image Classification?	claim
47	168	Recognition Using Visual Phrases	claim
48	168	Multiobject Tracking as Maximum Weight Independent Set	claim
49	168	Local Isomorphism to Solve the Pre-image Problem in Kernel Methods	claim
50	167	A Multichannel Edge-Weighted Centroidal Voronoi Tessellation Algorithm for 3D Superalloy Image Segmentation
51	167	Unsupervised Local Color Correction for Coarsely Registered Images
52	167	From Partial Shape Matching through Local Deformation to Robust Global Shape Similarity for Object Detection	claim
53	164	Shape Grammar Parsing via Reinforcement Learning	claim
54	163	Detection Free Tracking: Exploiting Motion and Topology for Segmenting and Tracking under Entanglement.	claim
55	163	Accelerated Low-Rank Visual Recovery by Random Projection	claim
56	163	Fast Unsupervised Ego-Action Learning for First-person Sports Videos	claim
57	162	Multiview Registration via Graph Diffusion of Dual Quaternions	claim
58	161	Occlusion Boundary Detection and Figure/Ground Assignment from Optical Flow	claim
59	161	action recognition by dense trajectories	claim
60	159	Camera Calibration with Lens Distortion from Low-rank Textures	claim
61	159	Importance Filtering for Image Retargeting	claim
62	159	Monocular 3D Scene Understanding with Explicit Occlusion Reasoning	claim
63	158	Piecing Together the Segmentation Jigsaw using Context	claim
64	158	Multi-spectral SIFT for Scene Category Recognition	claim
65	156	Blind Deconvolution Using A Normalized Sparsity Measure	claim
66	155	Learning the Easy Things First: Self-Paced Visual Category Discovery	claim
67	154	P2C2: Programmable Pixel Compressive Camera for High Speed Imaging.	claim
68	153	Online Detection of Unusual Events in Videos via Dynamic Sparse Coding	claim
69	152	Image Ranking and Retrieval Based on Multi-Attribute Queries	claim
70	152	Probabilistic Simultaneous Pose and Non-Rigid Shape Recovery	claim
71	150	Learning Context for Collective Activity Recognition	claim
72	149	On Deep Generative Models with Applications to Recognition	claim
73	147	Energy Based Multiple Model Fitting for Non-Rigid Structure from Motion	claim
74	147	Learning Non-Local Range Markov Random Field for Image Restoration	claim
75	146	Active Learning for Piecewise Planar 3D Reconstruction
76	146	Joint Face Alignment with A Generic Deformable Face Model	claim
77	145	Making the Right Moves: Guiding Alpha-Expansion using Local Primal-Dual Gaps
78	145	RUNE-Tag: a High Accuracy Fiducial Marker with Strong Occlusion Resilience	claim
79	144	Object Segmentation by Alignment of Poselet Activations to Image Contours	claim
80	144	Sparse Reconstruction Cost for Abnormal Event Detection	claim
81	143	Learning Message-Passing Inference Machines for Structured Prediction	claim
82	143	Contour cut: identifying salient contours in images by solving a Hermitian eigenvalue problem	claim
83	142	Face Recognition with Large Pose Variation	claim
84	142	High-resolution Hyperspectral Imaging via Matrix Factorization	claim
85	142	A Segmentation-aware Object Detection Model with Occlusion Handling	claim
86	140	Finding the Weakest Link in Person Detectors
87	139	Repetition-based Dense Single-View Reconstruction	claim
88	139	A Polar Representation of Motion and Implications for Optical Flow	claim
89	138	Global Stereo Matching Leveraged by Sparse Ground Control Points	claim
90	137	Branch and Track	claim
91	136	Shape Estimation in Natural Illumination	claim
92	136	Cross-View Action Recognition via View Knowledge Transfer
93	135	High Level Describable Attributes for Predicting Aesthetics and Interestingness	claim
94	135	Adapting an Object Detector by Considering the Worst Case: a Conservative Approach	claim
95	133	Large-Scale Live Active Learning: Training Object Detectors with Crawled Data and Crowds	claim
96	133	Graph Embedding Discriminant Analysis on Grassmannian Manifolds for Improved Image Set Matching	claim
97	133	Single-Image Shadow Detection and Removal using Paired Regions	claim
98	133	Discrete-Continuous Optimization for Large-scale Structure from Motion	claim
99	133	Fast Cost-Volume Filtering for Visual Correspondence and Beyond	claim
100	132	Contour-Based Joint Clustering of Multiple Segmentations
101	131	Scale and Rotation Invariant Matching Using Linearly Augmented Trees	claim
102	130	Novel 4-D Open-Curve Active Contour and Curve Completion Approach for Automated Tree Structure Extraction	claim
103	129	Non-Rigid Structure from Motion with Complementary Rank-3 Spaces	claim
104	129	Real Time Head Pose Estimation with Random Regression Forests	claim
105	129	Nonparametric Density Estimation on A Graph: Learning Framework, Fast Approximation and Application in Image Segmentation	claim
106	128	Learning Effective Human Pose Estimation from Inaccurate Annotation	claim
107	127	Noise Suppression in Low-Light Images through Joint Denoising and Demosaicing	claim
108	127	Multiview Specular Stereo Reconstruction of Large Mirror Surfaces	claim
109	127	Visual and Semantic Similarity in ImageNet	claim
110	127	Learning and Matching Multiscale Template Descriptors for Real-Time Detection, Localization and Tracking	claim
111	127	Object Stereo - Joint Stereo Matching and Object Segmentation	claim
112	126	3D Motion Reconstruction for Real-World Camera Motion	claim
113	125	Markerless Motion Capture of Interacting Characters Using Multi-view Image Segmentation	claim
114	125	Collaborative Personalization of Image Enhancement	claim
115	124	Simulating Human Saccadic Scanpaths on Natural Images	claim
116	123	Discriminative Tag Learning on YouTube Videos with Latent Sub-tags	claim
117	123	Distributed Computer Vision Algorithms Through Distributed Averaging	claim
118	122	Scenario-Based Video Event Recognition by Constraint Flow	claim
119	121	Saliency Estimation Using a Non-Parametric Low-Level Vision Model	claim
120	121	Deformation and Illumination Invariant Feature Point Descriptor	claim
121	121	Shape from Specular Flow: Is One Flow Enough?	claim
122	120	Identifying Players in Broadcast Sports Videos using Conditional Random Fields	claim
123	120	Submodularity beyond submodular energies: coupling edges in graph cuts	claim
124	120	Object Cosegmentation	claim
125	119	Generalized Projection Based M-Estimator: Theory and Applications	claim
126	119	Sharing Features Between Objects and Their Attributes	claim
127	118	Glare Encoding of High Dynamic Range Images	claim
128	117	Topology-adaptive Multi-view Photometric Stereo	claim
129	117	A Large-scale Benchmark Dataset for Event Recognition in Surveillance Video	claim
130	116	Shared Parts for Deformable Part-based Models	claim
131	115	Scalable Multi-class Object Detection	claim
132	115	Supervised Local Subspace Learning for Continuous Head Pose Estimation	claim
133	114	Recovering Shape from a Single Image of a Mirrored Surface from Curvature Constraints	claim
134	114	Semantic structure from motion	claim
135	114	Face Recognition in Unconstrained Videos with Matched Background Similarity	claim
136	113	Proposal Generation for Object Detection using Cascaded Ranking SVMs	claim
137	112	Track to the future: Spatio-temporal video segmentation with long-range motion cues	claim
138	111	A Theory of Multi-perspective Defocusing	claim
139	111	Statistics of Real-World Hyperspectral Images	claim
140	111	A general method for the Point of Regard estimation in 3D space	claim
141	111	High-quality shape from multi-view stereo and shading under general illumination	claim
142	108	Learning to Recognize Objects in Egocentric Activities	claim
143	108	Biased Normalized Cuts	claim
144	107	Enforcing Similarity Constraints with Integer Programming for Better Scene Text Recognition	claim
145	107	Learning to Share Visual Appearance for Multiclass Object Detection	claim
146	106	Action Recognition from a Distributed Representation of Pose and Appearance	claim
147	105	High-Frequency Shape and Albedo from Shading using Natural Image Statistics	claim
148	104	Automatic Photo-to-Terrain Alignment for the Annotation of Mountain Pictures	claim
149	103	Learning Object Color Models from Multi-view Constraints	claim
150	103	Interactively Building a Discriminative Vocabulary of Nameable Attributes
151	103	A Global Sampling Method for Alpha Matting	claim
152	103	Optimal Similarity Registration of Volumetric Images	claim
153	102	A Complete Statistical Inverse Ray Tracing Approach to Multi-view Stereo	claim
154	102	Multifactor Analysis Based on Factor-Dependent Geometry	claim
155	101	Functional Categorization of Objects using Real-time Markerless Motion Capture	claim
156	101	Multi-Level Inference by Relaxed Dual Decomposition for Human Pose Segmentation	claim
157	101	Face Image Retrieval by Shape Manipulation	claim
158	100	Relative pose problem for non-overlapping surveillance cameras with known gravity vector	claim
159	100	Wavelet Belief Propagation for Large Scale Inference Problems	claim
160	100	Learning Temporally Consistent Rigidities	claim
161	99	Learning a Blind Measure of Perceptual Image Quality	claim
162	98	Illumination Estimation and Cast Shadow Detection through a Higher-order Graphical Model	claim
163	98	Combining Randomization and Discrimination for Fine-Grained Image Categorization	claim
164	97	Multicore Bundle Adjustment	claim
165	97	Hierarchical Semantic Indexing for Large Scale Image Retrieval	claim
166	97	On analyzing video with very small motions	claim
167	96	Boundary Preserving Dense Local Regions	claim
168	95	Adequate Reconstruction of Transparent Objects on a Shoestring Budget	claim
169	95	Variable Grouping for Energy Minimization	claim
170	95	An Analysis of Using High-Frequency Sinusoidal Illumination to Measure the 3D Shape of Translucent Objects	claim
171	95	Particle Filter with State Permutations for Solving Image Jigsaw Puzzles	claim
172	95	Bayesian Deblurring with Integrated Noise Estimation	claim
173	95	FlowBoost - Appearance Learning from Sparsely Annotated Video	claim
174	95	Modeling the joint density of two images under a variety of transformations	claim
175	95	From Region Similarity to Category Discovery	claim
176	94	Supervised Hierarchical Pitman-Yor Process for Natural Scene Segmentation	claim
177	94	Learning invariance through imitation	claim
178	93	Contour Based Joint Clustering of Multiple Segmentations	claim
179	92	A Two-Stage Reconstruction Approach for Seeing Through Water
180	91	Clues from the Beaten Path: Location Estimation with Bursty Sequences of Tourist Photos	claim
181	90	Feature Guided Motion Artifact Reduction with Structure-Awareness in 4D CT Images	claim
182	90	Regression-Based Label Fusion for Multi-Atlas Segmentation	claim
183	90	Modeling Human Activities as Speech	claim
184	90	A Closed Form Solution to Robust Subspace Estimation and Clustering	claim
185	89	A Hierarchical Conditional Random Field Model for Labeling and Segmenting Images of Street Scenes	claim
186	89	2.5D Building Modeling with Topology Control	claim
187	89	A Deformation and Lighting Insensitive Metric for Face Recognition	claim
188	88	Structure from motion for scenes with large duplicate structures	claim
189	87	Learning to Find Occlusion Regions	claim
190	87	Nonlinear Shape Manifolds as Shape Priors in Level Set Segmentation and Tracking	claim
191	87	Multi-label Learning with Incomplete Class Assignments	claim
192	87	Radiometric Calibration by Transform Invariant Low-rank Structure
193	87	Discriminative Image Warping with Attribute Flow	claim
194	87	Noise Resistant Graph Ranking for Improved Web Image Search	claim
195	85	Truncated Message Passing	claim
196	83	Boosted Local Structured HOG-LBP for Object Localization	claim
197	83	Tracking 3D Human Pose with Large Root Node Uncertainty	claim
198	82	A Novel Parametrization of the Perspective-Three-Point Problem for a Direct Computation of Absolute Camera Position and Orientation	claim
199	82	A fully automated greedy square jigsaw puzzle solver	claim
200	82	Mining Discriminative Co-occurrence Patterns for Visual Recognition	claim
201	82	Ordinal Hyperplanes Ranker with Cost Sensitivities for Age Estimation	claim
202	81	Entropy Rate Superpixel Segmentation	claim
203	81	Adaptive Random Forest - How many ``experts'' to ask before making a decision?	claim
204	80	Kernelized Structural SVM Learning for Supervised Object Segmentation	claim
205	80	Exploiting Phonological Constraints for Handshape Inference in ASL Video	claim
206	79	What You Saw is Not What You Get: Domain Adaptation Using Asymmetric Kernel Transforms	claim
207	78	Total Variation for Cyclic Structures	claim
208	78	A Bayesian Approach to Adaptive Video Super Resolution	claim
209	77	Blur kernel estimation using the Radon Transform	claim
210	76	Line-Based Relative Pose Estimation	claim
211	75	A Non-convex Relaxation Approach to Sparse Dictionary Learning	claim
212	75	Multi-agent event recognition in structured scenarios	claim
213	74	Comparing Data-Dependent and Data-Independent Embeddings for Classification and Ranking of Internet Images	claim
214	73	Space-Time Super-Resolution from a Single Video	claim
215	73	Probabilistic Gaze Estimation Without Active Personal Calibration	claim
216	72	Nonlocal Matting	claim
217	72	An Associate-Predict Model for Face Recognition	claim
218	69	Using Specular Highlights as Pose Invariant Features for 2D-3D Pose Estimation	claim
219	69	Scene Flow Estimation by Growing Correspondence Seeds	claim
220	68	Learning-based Hypothesis Fusion for Robust Catheter Tracking in 2D X-ray Fluoroscopy	claim
221	68	Supervised Hypergraph Labeling	claim
222	68	Novelty detection from an Ego-centric perspective	claim
223	67	Global Optimization for Optimal Generalized Procrustes Analysis	claim
224	66	Learning People Detection Models from Few Training Samples	claim
225	66	Connecting Non-Quadratic Variational Models and MRFs	claim
226	65	A Brute-Force Algorithm for Reconstructing a Scene from Two Projections	claim
227	65	Projective Alignment of Range and Parallax Data	claim
228	65	Effective 3D Object Detection and Regression Using Probabilistic Segmentation Features in CT Images	claim
229	64	How does Person Identity Recognition Help Multi-Person Tracking?	claim
230	63	Max-margin Clustering: Detecting Margins from Projections of Points on Lines	claim
231	63	Who are you with and where are you Going?	claim
232	63	Topologically-Robust 3D Shape Matching Based on Diffusion Geometry and Seed Growing	claim
233	62	Visual textures as realizations of multivariate log-Gaussian Cox processes	claim
234	62	A Generalized Probabilistic Framework for Compact Codebook Creation	claim
235	61	Total Recall II: Query Expansion Revisited	claim
236	61	Motion Denoising with Application to Time-lapse Photography	claim
237	61	Compact Hashing with Joint Optimization of Search Accuracy and Time	claim
238	60	Robust Tracking Using Local Sparse Appearance Model and K-Selection	claim
239	59	Activity Recognition using Dynamic Subspace Angles	claim
240	59	Fusion of GPS and Structure-from-Motion using Constrained Bundle Adjustments	claim
241	59	Aggregating Gradient Distributions into Intensity Orders: A Novel Local Image Descriptor	claim
242	58	Support Tucker Machines	claim
243	58	Shape Based Pedestrian Parsing	claim
244	58	Internal Statistics of a Single Natural Image	claim
245	57	Reconstruction of relief objects from line drawings	claim
246	56	Registration of Camera Captured Documents Under Non-rigid Deformation	claim
247	56	TaylorBoost: First and Second-order Boosting Algorithms with Explicit Margin Control	claim
248	53	Symmetric Piecewise Planar Object Reconstruction from a Single Image	claim
249	52	A Global Optimization Approach to Robust Multi-Model Fitting	claim
250	51	Multiscale Geometric and Spectral Analysis of Plane Arrangements	claim
251	51	Generalized Group Sparse Classifiers with Application in fMRI Brain Decoding	claim
252	51	Wide-angle Micro Sensors for Vision on a Tight Budget	claim
253	48	Tag Localization with Spatial Correlations and Joint Group Sparsity	claim
254	41	Earth MoverÂ�s Prototypes: a Convex Learning Approach for Discovering Activity Patterns in Dynamic Scenes	claim

Sciweavers

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers