CVPR 2010 - PDF Preprint Papers

CVPR 2010 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-2010 Paper

click to vote

CVPR
2010
IEEE

1355views Computer Vision» more CVPR 2010»

Morphological Snakes

1 years 10 months ago

Download www.dia.fi.upm.es

We introduce a morphological approach to curve evolution. The differential operators used in the standard PDE snake models can be approached using morphological operations...

Luis Álvarez, Luis Baumela, Pedro Henríquez, Pab...

posted by Luis Baumela

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	1355	Morphological Snakes
2	1241	Depth from Diffusion
3	1157	New Features and Insights for Pedestrian Detection	claim
4	1117	3D Scene Priors for Road Detection
5	1005	Free-Shape Subwindow Search for Object Localization
6	921	Data Driven Mean-Shift Belief Propagation For non-Gaussian MRFs
7	916	Detecting Text in Natural Scenes with Stroke Width Transform	claim
8	851	Multi-Target Tracking of Time-varying Spatial Patterns
9	811	Harmony Potentials for Joint Classification and Segmentation
10	783	Unsupervised Detection and Segmentation of Identical Objects
11	780	Food Recognition Using Statistics of Pairwise Local Features	claim
12	729	Context-Aware Saliency Detection	claim
13	724	Live Dense Reconstruction with a Single Moving Camera	claim
14	655	AAM based Face Tracking with Temporal Matching and Face Segmentation	claim
15	651	Real Time Motion Capture using a Single Time-Of-Flight Camera	claim
16	643	Geodesic Star Convexity for Interactive Image Segmentation
17	643	RASL: Robust Alignment by Sparse and Low-rank Decomposition for Linearly Correlated Images	claim
18	615	Monocular 3D Pose Estimation and Tracking by Detection
19	612	3D Shape Scanning with a Time-of-Flight Camera	claim
20	599	Towards Weakly Supervised Semantic Segmentation by Means of Multiple Instance and Multitask Learning.
21	581	Visual Tracking Decomposition
22	579	Topic-Regression Multi-Modal Latent Dirichlet Allocation for Image Annotation	claim
23	559	Single Image Depth Estimation From Predicted Semantic Labels	claim
24	549	Unified Real-Time Tracking and Recognition with Rotation-Invariant Fast Features	claim
25	548	Multisensor-Fusion for 3D Full-Body Human Motion Capture
26	544	What's going on? Discovering Spatio-Temporal Dependencies in Dynamic Scenes
27	538	Removing Rolling Shutter Wobble	claim
28	532	Geodesic Graph Cut for Interactive Image Segmentation	claim
29	527	Online Multiple Instance Learning with No Regret	claim
30	489	Learning Full Pairwise Affinities for Spectral Segmentation
31	486	Authority-Shift Clustering: Hierarchical Clustering by Authority Seeking on Graphs
32	476	Spatialized Epitome and Its Applications
33	474	Human Identity Recognition in Aerial Images
34	471	Fast Matting Using Large Kernel Matting Laplacian Matrices	claim
35	471	Global and Efficient Self-Similarity for Object Classification and Detection	claim
36	467	Comparative object similarity for improved recognition with few or no examples	claim
37	462	Face Recognition with Learning-based Descriptor	claim
38	451	Simultaneous Foreground, Background, and Alpha Estimation for Image Matting	claim
39	450	Dense Non-rigid Surface Registration Using High-Order Graph Matching	claim
40	447	Tracking the Invisible: Learning Where the Object Might be	claim
41	446	Self-calibrating Photometric Stereo	claim
42	445	What Helps Where - And Why? Semantic Relatedness for Knowledge Transfer	claim
43	433	Visual Event Recognition in Videos by Learning from Web Data	claim
44	424	Geo-location estimation from two shadow trajectories	claim
45	423	The Role of Features, Algorithms and Data in Visual Recognition
46	418	On Detection of Multiple Object Instances using Hough Transforms	claim
47	409	Two Perceptually Motivated Strategies for Shape Classification
48	408	Dominant Orientation Templates for Real-Time Detection of Texture-Less Objects
49	401	Fast Polygonal Integration and Its Application in Extending Haar-like Features to Improve Object Detection	claim
50	395	A Square-Root Sampling Approach to Fast Histogram-Based Search	claim
51	386	3D Shape Correspondence by Isometry-Driven Greedy Optimization	claim
52	385	Efficient Action Spotting based on a Spacetime Oriented Structure Representation
53	376	Online Visual Vocabulary Pruning Using Pairwise Constraints
54	372	Grouplet: a Structured Image Representation for Recognizing Human and Object Interactions	claim
55	371	Temporal Causality for the Analysis of Visual Events	claim
56	368	An automatic unsupervised classification of MR images in Alzheimer's disease
57	365	Surface Stereo with Soft Segmentation	claim
58	360	Monocular SLAM with Locally Planar Landmarks via Geometric Rao-Blackwellized Particle Filtering on Lie groups
59	358	Facial Point Detection using Boosted Regression and Graph Models
60	352	Non-uniform Deblurring for Shaken Images	claim
61	348	Tracking with Local Spatio-Temporal Motion Patterns in Extremely Crowded Scenes	claim
62	345	Personalization of Image Enhancement	claim
63	344	Learning Mid-Level Features For Recognition	claim
64	343	Vessel Scale Selection using MRF Optimization
65	337	Robust Classification of Objects, Faces, and Flowers Using Natural Image Statistics	claim
66	332	A probabilistic image jigsaw puzzle solver	claim
67	332	Gesture Recognition by Learning Local Motion Signatures	claim
68	331	Fast Global Optimization of Curvature	claim
69	329	Constrained Parametric Min Cuts for Automatic Object Segmentation	claim
70	327	A Constant-Space Belief Propagation Algorithm for Stereo Matching	claim
71	325	Robust video denoising using low rank matrix completion	claim
72	325	Visual Object Tracking using Adaptive Correlation Filters	claim
73	324	iCoseg: Interactive Co-segmentation with Intelligent Scribble Guidance
74	319	Exploiting Hierarchical Context on a Large Database of Object Categories	claim
75	318	Aggregating local descriptors into a compact image representation
76	316	Specular Surface Reconstruction from Sparse Reflection Correspondences	claim
77	312	Online Multiclass LPBoost
78	312	Discriminative Clustering for Image Co-segmentation	claim
79	312	Piecewise Planar and Non-Planar Stereo for Urban Scene Reconstruction	claim
80	310	Estimating demosaicing algorithms using image noise variance	claim
81	306	Non-Rigid Structure from Locally-Rigid Motion	claim
82	302	Automatic Image Annotation Using Group Sparsity	claim
83	300	A New Texture Descriptor Using Multifractal Analysis in Multi-orientation Wavelet Pyramid	claim
84	300	Layered Object Detection for Multi-Class Segmentation	claim
85	299	Efficient Histogram-Based Sliding Window	claim
86	298	Fast Approximate Energy Minimization with Label Costs	claim
87	296	Calibration-free gaze sensing using saliency maps	claim
88	296	Robust Flash Deblurring
89	295	Detecting and Sketching the Common	claim
90	293	Highly Accurate Boundary Detection and Grouping	claim
91	293	Supervised Translation-Invariant Sparse Coding	claim
92	293	Scale-Invariant heat kernel signatures for non-rigid shape recognition	claim
93	287	Quasi-Dense 3D Reconstruction using Tensor-based Multiview Stereo	claim
94	285	Relaxing the 3L algorithm for an accurate implicit polynomial fitting
95	283	Nonparametric Higher-Order Learning for Interactive Segmentation
96	282	Chaotic Invariants of Lagrangian Particle Trajectories for Anomaly Detection in Crowded Scenes
97	281	The chains model for detecting parts by their context	claim
98	281	On improving point-based 3D recognition	claim
99	281	Efficiently Selecting Regions for Scene Understanding	claim
100	279	Simultaneous Pose, Correspondence and Non-Rigid Shape	claim
101	277	Finding Nemo: Deformable Object Class Modelling using Curve Matching	claim
102	276	The Multiscale Competitive Code via Sparse Representation for Palmprint Verification	claim
103	276	Motion Detail Preserving Optical Flow Estimation	claim
104	274	Manifold Blurring Mean Shift Algorithms	claim
105	272	Dynamical Binary Latent Variable Models for 3D Human Pose Tracking	claim
106	270	SPEC Hashing: Similarity Preserving algorithm for Entropy-based Coding	claim
107	267	Efficient Additive Kernels via Explicit Feature Maps	claim
108	266	Linked Edges as Stable Region Boundaries
109	265	Interest Seam Image	claim
110	265	Parallel and Distributed Graph Cuts by Dual Decomposition	claim
111	265	Multi-View Object Class Detection With a 3D Geometric Model	claim
112	263	Fast Globally Optimal 2D Human Detection with Loopy Graph Models
113	260	Cascade Object Detection with Deformable Part Models	claim
114	258	Pareto Discriminant Analysis	claim
115	258	Building Reconstruction using Manhattan-World Grammars	claim
116	255	One-Shot Multi-Set Non-rigid Feature-Spatial Matching
117	255	A Diffusion Approach to Seeded Image Segmentation	claim
118	250	Optimizing One-Shot Recognition with Micro-Set Learning	claim
119	249	A Steiner Tree approach to efficient object detection	claim
120	249	Secrets of Optical Flow Estimation and Their Principles	claim
121	246	A Generative Perspective on MRFs in Low-Level Vision	claim
122	243	Object Recognition as Ranking Holistic Figure-Ground Hypotheses	claim
123	243	Image Webs: Computing and Exploiting Connectivity in Image Collections	claim
124	242	Convex Shape Decomposition	claim
125	241	Multilinear Pose and Body Shape Estimation of Dressed Subjects from Image Sets	claim
126	239	Locality-constrained Linear Coding for Image Classification	claim
127	237	Simultaneous Point Matching and 3D Deformable Surface Reconstruction	claim
128	236	A Globally Optimal Data-Driven Approach for Image Distortion Estimation	claim
129	236	Rapid Selection of Reliable Templates for Visual Tracking
130	233	Use Bin-Ratio Information for Category and Scene Classification	claim
131	233	A Game-Theoretic Approach to Fine Surface Registration without Initial Motion Estimation	claim
132	233	Covering Trees and Lower-bounds on Quadratic Assignment	claim
133	228	Object-to-Object Color Transfer: Optimal Flows and SMSP Transformations	claim
134	227	Asymmetric Region-to-Image Matching for Comparing Images with Generic Object Categories	claim
135	226	Moving Vistas: Exploiting Motion for Describing Scenes	claim
136	226	Optimal HDR Reconstruction with Linear Digital Cameras	claim
137	224	Boundary Learning by Optimization with Topological Constraints	claim
138	222	On-line Semi-supervised Multiple-Instance Boosting
139	219	Denoising vs. Deblurring: HDR Imaging Techniques Using Moving Cameras	claim
140	215	Ink-Bleed Reduction using Functional Minimization	claim
141	212	Efficient Piecewise Learning for Conditional Random Fields	claim
142	209	Multimodal semi-supervised learning for image classification
143	208	Dense Interest Points	claim
144	207	Improving web-image search results using query-relative classifiers
145	206	Figure-Ground Segmentation Improves Handled Object Recognition in Egocentric Video	claim
146	202	Hierarchical Convolutional Sparse Image Decomposition	claim
147	202	Parallel Graph-cuts by Adaptive Bottom-up Merging	claim
148	202	Scale-Hierarchical 3D Object Recognition in Cluttered Scenes	claim
149	201	Tiered Scene Labeling with Dynamic Programming	claim
150	201	Scene Classification and Detection with a Quasi-exhausitve Dataset	claim
151	200	Efficient Filter Flow for Space-Variant Multiframe Blind Deconvolution	claim
152	200	Local Features Are Not Lonely - Laplacian Sparse Coding for Image Classification	claim
153	199	Fast Image Alignment in the Fourier Domain	claim
154	197	Segmentation of Building Facades Using Procedural Shape Priors	claim
155	197	Modeling Mutual Context of Object and Human Pose in Human-Object Interaction Activities	claim
156	195	Surface Extraction from Binary Volumes with Higher-Order Smoothness	claim
157	195	Semantic Context Modeling with Maximal Margin Conditional Random Fields for Automatic Image Annotation	claim
158	195	Semi-supervised Hashing for Scalable Image Retrieval	claim
159	192	Cascaded Pose Regression	claim
160	191	Automatic Discovery of Meaningful Object Parts with Latent CRFs	claim
161	190	Scalable Active Matching	claim
162	190	Group MRF for fMRI Activation Detection
163	189	Recovering Fluid-type Motions Using Navier-Stokes Potential Flow
164	189	Novel Observation Model for Probabilistic Object Tracking	claim
165	187	Hybrid Multi-view Reconstruction by Jump-Diffusion	claim
166	187	Rapid Face Recognition Using Hashing	claim
167	186	Putting local features on a Manifold
168	185	Regenerative Morphing	claim
169	185	Classification and Clustering via Dictionary Learning with Structured Incoherence	claim
170	184	Efficient Extraction of Human Motion Volumes by Tracking	claim
171	183	The Cluttered Background Problem for Active Contours: A Minimum-Latency Solution	claim
172	182	Learning Shift-Invariant Sparse Representation of Actions	claim
173	181	Transform Coding for Fast Approximate Nearest Neighbor Search in High Dimensions	claim
174	180	Part and Appearance Sharing: Recursive Compositional Models for Multi-View Multi-Object Detection	claim
175	180	Admissible Linear Map Models of Linear Cameras	claim
176	178	Safety in Numbers: Learning Categories from Few Examples with Multi Model Knowledge Transfer	claim
177	177	PROST: Parallel Robust Online Simple Tracking
178	176	Real-time Tracking of Multiple Occluding Objects using Level Sets	claim
179	176	What is an object?	claim
180	175	Scalable Face Image Retrieval with Identity-Based Quantization and Multi-Reference Re-ranking	claim
181	173	Robust Order-based Methods for Feature Description	claim
182	171	3D Morphable Model Construction for Robust Ear and Face Recognition
183	170	Collect-Cut: Segmentation with Top-Down Cues Discovered in Multi-Object Images	claim
184	170	Building and Using a Semantivisual Image Hierarchy	claim
185	169	Beyond Active Noun Tagging: Modeling Contextual Interactions for Multi-Class Active Learning	claim
186	167	Using cloud shadows to infer scene structure and camera calibration
187	167	Morphable Reflectance Fields for Enhancing Face Recognition
188	167	Adaptive Generic Learning for Face Recognition from a Single Sample per Person	claim
189	166	Object-Graphs for Context-Aware Category Discovery	claim
190	165	Globally Optimal Pixel Labeling Algorithms for Tree Metrics	claim
191	165	Data Fusion through Cross-modality Metric Learning using Similarity-Sensitive Hashing	claim
192	163	Outlier Removal Using Duality	claim
193	162	Posture Invariant Surface Description and Feature Extraction	claim
194	162	Cascaded L1-norm Minimization Learning (CLML) Classifier for Human Detection	claim
195	162	Simultaneous surveillance camera calibration and foot-head homology estimation from human detections	claim
196	160	Visual Tracking via Weakly Supervised Learning from Multiple Imperfect Oracles	claim
197	160	A theory of phase-sensitive rotation invariance with spherical harmonic and moment-based representations	claim
198	159	Automatic Point-based Facial Trait Judgments Evaluation	claim
199	159	Dynamic and Scalable Large Scale Image Reconstruction	claim
200	159	Parametric Dimensionality Reduction by Unsupervised Regression	claim
201	159	Warping Background Subtraction
202	157	Multi-domain, Higher Order Level Set Scheme for 3D Image Segmentation on the GPU	claim
203	157	Dynamic Texture Recognition based on Distributions of Spacetime Oriented Structure
204	157	CRAM: Compact Representation of Actions in Movies	claim
205	155	Dynamic Surface Matching by Geodesic Mapping for 3D Animation Transfer
206	155	Breaking the interactive bottleneck in multi-class classification with active selection and binary feedback	claim
207	155	Segmenting Video Into Classes of Algorithm-Suitability	claim
208	154	Learning Appearance in Virtual Scenarios for Pedestrian Detection	claim
209	153	A Novel Markov Random Field Based Deformable Model for Face Recognition	claim
210	153	Heterogeneous Conditional Random Field: Realizing Joint Detection and Segmentation of Cell Regions in Microscopic Images	claim
211	152	Connecting Modalities: Semi-supervised Segmentation and Annotation of Images Using Unaligned Text Corpora	claim
212	151	Consensus Photometric Stereo	claim
213	151	Global Optimization for Estimating a BRDF with Multiple Specular Lobes	claim
214	150	A Spatially Varying PSF-based Prior for Alpha Matting	claim
215	149	Latent Hierarchical Structural Learning for Object Detection	claim
216	148	Multi-Class Object Localization by Combining Local Contextual Interactions	claim
217	147	Hybrid Shift Map for Video Retargeting
218	147	Learning 3D Action Models from a few 2D videos for View Invariant Action Recognition	claim
219	147	Correcting Over-Exposure in Photographs	claim
220	146	Estimating Camera Pose from a Single Urban Ground-View Omnidirectional Image and a 2D Building Outline Map	claim
221	145	Clustering Dynamic Textures with the Hierarchical EM Algorithm	claim
222	145	Disambiguating Visual Relations Using Loop Constraints	claim
223	145	Learning from Interpolated Images using Neural Networks for Digital Forensics	claim
224	144	Contour People: A Parameterized Model of 2D Articulated Human Shape	claim
225	141	Reading Between The Lines: Object Localization Using Implicit Cues from Image Tags	claim
226	141	A Framework for Ultra High Resolution 3D Imaging	claim
227	141	Generating Sharp Panoramas from Motion-blurred Videos	claim
228	140	Image Retrieval via Probabilistic Hypergraph Ranking	claim
229	140	Combining Discriminative and Generative Methods for 3D Deformable Surface and Articulated Pose Reconstruction	claim
230	139	Exploiting Simple Hierarchies for Unsupervised Human Behavior Analysis	claim
231	139	Estimation of Image Bias Field with Sparsity Constraints
232	139	Curious Snakes: a minimum-latency solution to the cluttered background problem in active contours
233	138	Multi-Target Tracking by On-Line Learned Discriminative Appearance Models	claim
234	138	Weakly-Supervised Hashing in Kernel Space	claim
235	138	Action Unit Detection with Segment-based SVMs	claim
236	137	P-N learning: Bootstrapping binary classifiers by structural constraints	claim
237	136	Model Evolution: An Incremental Approach to Non-Rigid Structure from Motion	claim
238	136	A Theory of Plenoptic Multiplexing	claim
239	135	Locally-Parametric Pictorial Structures	claim
240	135	Variational Segmentation of Volumetric Elongated Objects
241	135	Tracking People Interacting with Objects	claim
242	135	Online-Batch Strongly Convex Multi Kernel Learning	claim
243	135	Improving State-of-the-Art OCR through High-Precision Document-Specific Modeling	claim
244	134	Context-Constrained Hallucination for Image Super-Resolution	claim
245	132	Beyond Trees: MRF Inference via Outer-Planar Decomposition
246	130	Recognizing Human Actions from Still Images with Latent Poses	claim
247	130	YouTubeCat: Learning to Categorize Wild Web Videos	claim
248	130	Rectifying rolling shutter video from hand-held devices	claim
249	129	Towards Internet-scale Multi-view Stereo	claim
250	128	Tag-based Web Photo Retrieval Improved by Batch Mode Re-Tagging	claim
251	128	Coded Exposure Imaging for Projective Motion Deblurring	claim
252	127	Modeling Pixel Process with Scale Invariant Local Patterns for Background Subtraction in Complex Scenes	claim
253	127	SVM for Edge-Preserving Filtering	claim
254	126	High-Resolution Modeling of Moving and Deforming Objects Using Sparse Geometric and Dense Photometric Measurements	claim
255	126	Person Re-Identification by Symmetry-Driven Accumulation of Local Features	claim
256	125	Unsupervised Learning of Invariant Features Using Video	claim
257	124	On Growth and Formlets: Sparse Multi-Scale Coding of Planar Shape	claim
258	123	The Automatic Design of Feature Spaces for Local Image Descriptors using an Ensemble of Non-linear Feature Extractors	claim
259	123	Scene understanding by statistical modeling of motion patterns	claim
260	123	Motion Estimation with Non-Local Total Variation Regularization
261	122	Efficient Joint 2D and 3D Palmprint Matching with Alignment Refinement	claim
262	122	Sufficient Dimensionality Reduction for Visual Sequence Classification	claim
263	122	A Novel Riemannian Framework for Shape Analysis of 3D Objects	claim
264	121	Fast and Robust Object Segmentation with the Integral Linear Classifier	claim
265	121	Exploring Features in a Bayesian Framework for Material Recognition	claim
266	119	A Hough Transform-Based Voting Framework for Action Recognition	claim
267	119	Learning a Hierarchy of Discriminative Space-Time Neighborhood Features for Human Action Recognition	claim
268	118	Naming People from Dialog: Temporal Grouping and Weak Supervision	claim
269	117	Line Matching Leveraged By Point Correspondences	claim
270	115	Visual Tracking via Incremental Self-tuning Particle Filtering on the Affine Group	claim
271	115	Detecting and Parsing Architecture at City Scale from Range Data	claim
272	114	Sensor Saturation in Fourier Multiplexed Imaging	claim
273	114	Optimal Coded Sampling for Temporal Super-Resolution	claim
274	113	Spike Train Driven Dynamical Models for Human Actions
275	112	Noise-Optimal Capture for High Dynamic Range Photography
276	110	A Content-Aware Image Prior	claim
277	110	Object Detection via Boundary Structure Segmentation	claim
278	110	Unified Graph Matching in Euclidean Spaces	claim
279	109	Global and local isometry-invariant descriptor for 3D shape comparison and partial matching	claim
280	109	High performance object detection by collaborative learning of Joint Ranking of Granules features	claim
281	109	An Approach to Vectorial Total Variation based on Geometric Measure Theory	claim
282	107	Learning to Recognize Shadows in Monochromatic Natural Images	claim
283	105	Fast directional chamfer matching	claim
284	104	Anatomical Parts-Based Regression Using Non-Negative Matrix Factorization	claim
285	104	An Object-Dependent Hand Pose Prior from Sparse Training Data	claim
286	104	An Efficient Divide-and-Conquer Cascade for Nonlinear Object Detection	claim
287	104	Visual Recognition and Detection Under Bounded Computational Resources	claim
288	103	Estimating Optical Properties of Layered Surfaces Using the Spider Model	claim
289	102	Finding Dots: Segmentation as Popping out Regions from Boundaries	claim
290	101	Modeling and Estimating Persistent Motion with Geometric Flows	claim
291	101	Discrete minimum ratio curves and surfaces	claim
292	101	Increasing depth resolution of Electron Microscopy of Neural circuits using Sparse Tomographic reconstruction	claim
293	101	Multi-view structure computation without explicitly estimating motion	claim
294	101	Model Globally, Match Locally: Efficient and Robust 3D Object Recognition	claim
295	100	Direct Image Alignment of Projector-Camera Systems with Planar Surfaces	claim
296	100	ARISTA - Image Search to Annotation on Billions of Web Photos	claim
297	100	Multi-Cue Pedestrian Classification with Partial Occlusion Handling	claim
298	99	A Study on Continuous Max-Flow and Min-Cut Approaches	claim
299	99	Efficient Hierarchical Graph-Based Video Segmentation	claim
300	99	Learning Weights for Codebook in Image Classification	claim
301	98	Using Optical Defocus to Denoise	claim
302	97	Toward Coherent Object Detection And Scene Layout Understanding	claim
303	97	Total Bregman divergence and its applications to shape retrieval	claim
304	96	Face Recognition Based on Image Sets	claim
305	96	Multilinear Feature Extraction and Classification of Multi-Focal Images, With Applications in Nematode Taxonomy	claim
306	94	Large-Scale Image Retrieval with Compressed Fisher Vectors	claim
307	94	Bundled Depth-Map Merging for Multi-View Stereo	claim
308	93	Efficient computation of robust low-rank matrix approximations in the presence of missing data using the L1 norm	claim
309	93	Linear View Synthesis Using a Dimensionality Gap Light Field Prior	claim
310	93	Co-clustering of Image Segments Using Convex Optimization Applied to EM Neuronal Reconstruction	claim
311	93	Topic regression multi-modal Latent Dirichlet Allocation for image annotation	claim
312	92	Surface color estimation based on inter- and intra-pixel relationships in outdoor scenes	claim
313	92	Discriminative K-SVD for Dictionary Learning in Face Recognition	claim
314	91	Large-Scale Image Categorization with Explicit Data Embedding	claim
315	90	An Online Approach: Learning-Semantic-Scene-by-Tracking and Tracking-by-Learning-Semantic-Scene	claim
316	90	Generalized Simultaneous Registration and Segmentation	claim
317	90	Region moments: Fast invariant descriptors for detecting small image structures	claim
318	89	Super-Resolution of Range Data in Dynamic Environments Using a Gaussian Framework	claim
319	89	Image restoration and disparity estimation from an uncalibrated multi-layered image	claim
320	89	Harvesting Large-Scale Weakly-Tagged Image Databases from the Web	claim
321	89	Adaptive Linear Predictors for Real-Time Tracking	claim
322	88	Multi-Task Warped Gaussian Process for Personalized Age Estimation	claim
323	88	Anomaly detection in crowded scenes	claim
324	87	Fast Sparse Representation with Prototypes	claim
325	86	Pareto-optimal Dictionaries for Signatures	claim
326	85	Adaptive pose priors for pictorial structures	claim
327	85	Polynomial Shape from Shading	claim
328	85	Free-Form Mesh Tracking : a Patch-Based Approach	claim
329	84	"Lattice Cut" - Constructing superpixels using layer constraints	claim
330	84	Stratified Learning of Local Anatomical Context for Lung Nodules in CT Images	claim
331	84	Bayes Optimal Kernel Discriminant Analysis	claim
332	83	Visual classification with multi-task joint sparse representation	claim
333	83	Energy Minimization for Linear Envelope MRFs	claim
334	83	Many-to-one Contour Matching for Describing and Discriminating Object Shape	claim
335	83	Analyzing Spatially-varying Blur	claim
336	82	Boosting for transfer learning with multiple sources	claim
337	81	Localizing Non-Overlapping Surveillance Cameras under the L-Infinity Norm	claim
338	81	Proximate Sensing: Inferring What-Is-Where From Georeferenced Photo Collections	claim
339	81	Learning 3D Shape from a Single Facial Image via Non-linear Manifold Embedding and Alignment	claim
340	81	Exploiting Monge structures in optimum subwindow search	claim
341	81	Variational Segmentation of Elongated Volumetric Structures	claim
342	81	Far-Sighted Active Learning on a Budget for Image and Video Recognition	claim
343	81	Action Classification on Product Manifolds	claim
344	80	Motion Fields to Predict Play Evolution in Dynamic Sport Scenes	claim
345	79	Warp Propagation for Video Resizing	claim
346	78	Visual Recognition using Mappings that Replicate Margins	claim
347	78	Ray Markov Random Fields for Image-Based 3D Modeling: Model and Efficient Inference	claim
348	78	Exploiting Global Connectivity Constraints for Reconstruction of 3D Line Segments from Images	claim
349	78	Refinement of Digital Elevation Models from Shadowing Cues	claim
350	77	An Eye for an Eye: A Single Camera Gaze-Replacement Method	claim
351	77	Rectilinear parsing of architecture in urban environment	claim
352	77	Metric-Induced Optimal Embedding for Intrinsic 3D Shape Analysis	claim
353	76	Probabilistic Temporal Inference on Reconstructed 3D Scenes	claim
354	76	Probabilistic 3D Occupancy Flow with Latent Silhouette Cues	claim
355	76	Player Localization Using Multiple Static Cameras for Sports Visualization	claim
356	76	Compression of Surface Registration using Beltrami Coefficients	claim
357	75	Common visual pattern discovery via spatially coherent correspondences	claim
358	75	Cost-Sensitive Subspace Learning for Face Recognition	claim
359	75	Towards Semantic Embedding in Visual Vocabulary	claim
360	75	Robust Piecewise-Planar 3D Reconstruction and Completion from Large-Scale Unstructured Point Data	claim
361	75	On the design of robust classifiers for computer vision	claim
362	74	3D Curve Sketch: Flexible Curve-Based Stereo Reconstruction and Calibration	claim
363	74	Sparse representation using nonnegative curds and whey	claim
364	73	Multiple Object Detection by Sequential Monte Carlo and Hierarchical Detection Network	claim
365	73	Manifold blurring mean shift algorithms for manifold denoising	claim
366	73	Label propagation in video sequences	claim
367	73	Learning kernels for variants of normalized cuts: Convex relaxations and applications	claim
368	72	Taxonomic Classification for Web-based Videos	claim
369	72	Curious snakes: A minimum latency solution to the cluttered background problem in active contours	claim
370	72	Delineating trees in noisy 2D images and 3D image-stacks	claim
371	71	Discontinuous Seam-Carving for Video Retargeting	claim
372	71	Pushing the Envelope of Modern Methods for Bundle Adjustment	claim
373	71	Fast pattern matching using orthogonal Haar transform	claim
374	70	Neuron Geometry Extraction by Perceptual Grouping in ssTEM images	claim
375	70	Deconvolutional networks	claim
376	70	Modeling pixel means and covariances using factorized third-order boltzmann machines	claim
377	70	Attribute-centric recognition for cross-category generalization	claim
378	69	Unsupervised discovery of co-occurrence in sparse high dimensional data	claim
379	69	The Phase Only Transform for unsupervised surface defect detection	claim
380	68	Rapid and accurate developmental stage recognition of C. elegans from high-throughput image data	claim
381	67	Compact Projection: Simple and Efficient Near Neighbor Search with Practical Memory Requirements	claim
382	67	Lymph Node Detection in 3-D Chest CT using a Spatial Prior Probability	claim
383	67	Towards general motion-based face recognition	claim
384	67	Illumination compensation based change detection using order consistency	claim
385	66	Multi-View Scene Flow Estimation: A View Centered Variational Approach	claim
386	66	Will person detection help bag-of-features action recognition?	claim
387	66	Point-based non-rigid surface registration with accuracy estimation	claim
388	65	Nonparametric Label-to-Region by Search	claim
389	65	Performance evaluation of color correction approaches for automatic multi-view image and video stitching	claim
390	65	Simultaneous Searching of Globally Optimal Interacting Surfaces with Shape Priors
391	65	Image atlas construction via intrinsic averaging on the manifold of images	claim
392	64	Multi-structure model selection via kernel optimisation	claim
393	64	Silhouette Transformation based on Walking Speed for Gait Identification	claim
394	63	Axial light field for curved mirrors: Reflect your perspective, widen your view	claim
395	63	Analysis of Light Transport in Scattering Media	claim
396	62	Minimum length in the tangent bundle as a model for curve completion	claim
397	62	Integrated Pedestrian Classification and Orientation Estimation	claim
398	62	Robust RVM regression using sparse outlier model	claim
399	62	GPCA with denoising: A moments-based convex approach	claim
400	61	Part and appearance sharing: Recursive Compositional Models for multi-view	claim
401	61	Object Separation In X-Ray Image Sets	claim
402	61	Finding meaning on YouTube: Tag recommendation and category discovery	claim
403	61	A probabilistic framework for joint segmentation and tracking	claim
404	60	Compression of surface registrations using Beltrami coefficients	claim
405	60	Growing semantically meaningful models for visual SLAM	claim
406	60	Free-form mesh tracking: A patch-based approach	claim
407	59	Talking pictures: Temporal grouping and dialog-supervised person recognition	claim
408	58	Shape and Refractive Index Recovery from Single-View Polarisation Images	claim
409	58	Estimating satellite attitude from pushbroom sensors	claim
410	57	Group motion segmentation using a Spatio-Temporal Driving Force Model	claim
411	54	Spherical embeddings for non-Euclidean dissimilarities	claim
412	54	Natural gradients for deformable registration	claim
413	53	Shape-based similarity retrieval of Doppler images for clinical decision support	claim

Sciweavers

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers