CVPR 2008 - PDF Preprint Papers

CVPR 2008 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-2008 Paper

click to vote

CVPR
2008
IEEE

651views Computer Vision» more CVPR 2008»

Graph cut based image segmentation with connectivity priors

2 years 3 months ago

Download www.cs.ucl.ac.uk

Graph cut is a popular technique for interactive image segmentation. However, it has certain shortcomings. In particular, graph cut has problems with segmenting thin elongated obj...

Sara Vicente, Vladimir Kolmogorov, Carsten Rother

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	651	Graph cut based image segmentation with connectivity priors	claim
2	504	Image partial blur detection and classification	claim
3	494	Image super-resolution using gradient profile prior	claim
4	489	Discriminative local binary patterns for human detection in personal album	claim
5	474	Accurate Eye Center Location and Tracking Using Isophote Curvature
6	396	Estimating age, gender, and identity using first name priors
7	367	Illumination and Camera Invariant Stereo Matching
8	339	Beyond sliding windows: Object localization by efficient subwindow search	claim
9	280	Regularizing 3D medial axis using medial scaffold transforms
10	245	Optical flow estimation using Fourier Mellin Transform	claim
11	225	An efficient algorithm for compressed MR imaging using total variation and wavelets	claim
12	194	Privacy preserving crowd monitoring: Counting people without people models or tracking	claim
13	189	A hybrid camera for motion deblurring and depth map super-resolution
14	180	Multiple-instance ranking: Learning to rank images for image retrieval	claim
15	180	Geo-spatial aerial video processing for scene understanding and object tracking	claim
16	172	Visibility in bad weather from a single image	claim
17	167	A discriminatively trained, multiscale, deformable part model	claim
18	165	Real-Time Face Pose Estimation from Single Range Images
19	160	Robust dual motion deblurring	claim
20	153	Conjugate rotation: Parameterization and estimation from an affine feature correspondence	claim
21	153	Rank-based distance metric learning: An application to image retrieval	claim
22	151	Combining appearance models and Markov Random Fields for category level object segmentation	claim
23	140	Simultaneous image transformation and sparse representation recovery	claim
24	139	General Constraints for Batch Multiple-Target Tracking Applied to Large-Scale Videomicroscopy
25	134	Real time object tracking based on dynamic feature grouping with background subtraction	claim
26	132	Learning realistic human actions from movies	claim
27	129	Automatic registration of aerial imagery with untextured 3D LiDAR models	claim
28	126	Action snippets: How many frames does human action recognition require?	claim
29	125	A Bayesian approach for image segmentation with shape priors	claim
30	125	A two-frame theory of motion, lighting and shape	claim
31	122	Automatic face naming with caption-based supervision
32	121	SMRFI: Shape matching via registration of vector-valued feature images
33	118	From appearance to context-based recognition: Dense labeling in small images
34	118	Background subtraction in highly dynamic scenes	claim
35	118	Object tracking and detection after occlusion via numerical hybrid local and global mode-seeking	claim
36	116	Simultaneous super-resolution and 3D video using graph-cuts
37	115	Discriminative learning of visual words for 3D human pose estimation	claim
38	115	Simultaneous learning of a discriminative projection and prototypes for Nearest-Neighbor classification	claim
39	114	Approximate earth mover's distance in linear time	claim
40	114	Recovering Shape Characteristics on Near-flat Specular Surfaces
41	111	Stereoscopic inpainting: Joint color and depth completion from stereo images	claim
42	111	FusionFlow: Discrete-continuous optimization for optical flow estimation	claim
43	109	Spatio-temporal Saliency detection using phase spectrum of quaternion fourier transform	claim
44	108	Local deformation models for monocular 3D shape recovery	claim
45	108	Sparse probabilistic regression for activity-independent human pose inference	claim
46	107	Generalised blurring mean-shift algorithms for nonparametric clustering	claim
47	106	Clothing cosegmentation for recognizing people
48	106	Learning human actions via information maximization
49	106	Constrained spectral clustering through affinity propagation	claim
50	105	Video segmentation: Propagation, validation and aggregation of a preceding graph	claim
51	105	Discriminative learned dictionaries for local image analysis	claim
52	104	Unsupervised estimation of segmentation quality using nonnegative factorization	claim
53	101	A hierarchical and contextual model for aerial image understanding	claim
54	101	Dense 3D motion capture from synchronized video streams	claim
55	101	Superpixel lattices	claim
56	100	Parameterized Kernel Principal Component Analysis: Theory and applications to supervised and unsupervised image alignment	claim
57	99	Small codes and large image databases for recognition	claim
58	99	Unsupervised discovery of visual object class hierarchies	claim
59	99	Dense specular shape from multiple specular flows	claim
60	99	Modulated phase-shifting for 3D scanning	claim
61	96	Constant time O(1) bilateral filtering	claim
62	96	Learning 4D action feature models for arbitrary view action recognition	claim
63	95	Semantic texton forests for image categorization and segmentation	claim
64	94	Similarity-based cross-layered hierarchical representation for object categorization	claim
65	94	Robust statistics on Riemannian manifolds via the geometric median	claim
66	94	A fast local descriptor for dense matching	claim
67	94	Recognizing human actions using multiple features
68	93	3D face tracking and expression inference from a 2D sequence using manifold learning	claim
69	93	Decomposition, discovery and detection of visual categories using topic models	claim
70	93	Context and observation driven latent variable model for human pose estimation	claim
71	93	Classification using intersection kernel support vector machines is efficient	claim
72	91	Homography based multiple camera detection and tracking of people in a dense crowd	claim
73	91	Visual tracking via incremental Log-Euclidean Riemannian subspace learning	claim
74	89	People-tracking-by-detection and people-detection-by-tracking
75	89	A deformable local image descriptor	claim
76	89	A robust descriptor based on Weber's Law	claim
77	89	Sequential particle swarm optimization for visual tracking	claim
78	88	Markerless motion capture of man-machine interaction	claim
79	88	Combining brain computer interfaces with vision for object categorization	claim
80	88	Semi-supervised boosting using visual similarity learning
81	87	Randomized trees for human pose detection	claim
82	87	Online learning of patch perspective rectification for efficient object detection	claim
83	87	Global pose estimation using non-tree models	claim
84	86	Extracting a fluid dynamic texture and the background from video	claim
85	86	Multiplicative kernels: Object detection, segmentation and pose estimation	claim
86	85	Action recognition with motion-appearance vocabulary forest	claim
87	85	Trajectory analysis and semantic region modeling using a nonparametric Bayesian model	claim
88	84	Global stereo reconstruction under second order smoothness priors	claim
89	84	Real-time pose estimation of articulated objects using low-level motion	claim
90	84	(BP)2: Beyond pairwise Belief Propagation labeling by approximating Kikuchi free energies	claim
91	84	Particle filtering for registration of 2D and 3D point sets with stochastic dynamics	claim
92	84	Action recognition by learning mid-level motion features	claim
93	83	Automatic non-rigid registration of 3D dynamic data for facial expression synthesis and transfer	claim
94	82	Semi-supervised SVM batch mode active learning for image retrieval	claim
95	82	Least squares congealing for unsupervised alignment of images	claim
96	81	Single-image vignetting correction using radial gradient symmetry	claim
97	80	Where am I: Place instance and category recognition using spatial PACT	claim
98	80	On benchmarking camera calibration and multi-view stereo for high resolution imagery	claim
99	80	Looking around the backyard helps to recognize faces and digits	claim
100	79	Recovery of relative depth from a single observation using an uncalibrated (real-aperture) camera	claim
101	79	A region based stereo matching algorithm using cooperative optimization	claim
102	79	Progressive search space reduction for human pose estimation	claim
103	79	The patch transform and its applications to image editing	claim
104	78	Robust learning of discriminative projection for multicategory classification on the Stiefel manifold	claim
105	78	Learning class-specific affinities for image labelling
106	78	Image super-resolution as sparse representation of raw image patches	claim
107	77	Closing the loop in scene interpretation	claim
108	76	Regression from patch-kernel	claim
109	76	Correspondences between parts of shapes with particle filters	claim
110	76	3D model matching with Viewpoint-Invariant Patches (VIP)	claim
111	76	Image de-fencing	claim
112	76	Transfer learning for image classification with sparse prototype representations	claim
113	76	Boosted deformable model for human body alignment	claim
114	76	Hybrid body representation for integrated pose recognition, localization and segmentation	claim
115	76	Efficient photometric stereo on glossy surfaces with wide specular lobes	claim
116	76	Layered graphical models for tracking partially-occluded objects	claim
117	76	Visual Synset: Towards a higher-level visual representation	claim
118	76	Bayesian color constancy revisited	claim
119	75	Precise detailed detection of faces and facial features	claim
120	75	Visual tracking with histograms and articulating blocks	claim
121	75	An experimental study of employing visual appearance as a phenotype	claim
122	74	Globally optimal surface segmentation using regional properties of segmented objects	claim
123	73	Efficient sequential correspondence selection by cosegmentation	claim
124	73	Real-time 3D segmentation of the left ventricle using deformable subdivision surfaces	claim
125	72	A bi-illuminant dichromatic reflection model for understanding images	claim
126	72	Kernel-based learning of cast shadows from a physical model of light sources and surfaces for low-level segmentation	claim
127	72	Exact inference in multi-label CRFs with higher order cliques	claim
128	72	Misalignment-robust face recognition	claim
129	72	In defense of Nearest-Neighbor based image classification	claim
130	72	Probabilistic image registration and anomaly detection by nonlinear warping	claim
131	71	High resolution matting via interactive trimap segmentation	claim
132	71	Modeling the structure of multivariate manifolds: Shape maps	claim
133	71	Fast and robust numerical solutions to minimal problems for cameras with radial distortion	claim
134	71	Efficient mean shift belief propagation for vision tracking	claim
135	71	Shape prior segmentation of multiple objects with graph cuts	claim
136	70	Silhouette-based camera calibration from sparse views under circular motion	claim
137	70	Finding people in archive films through tracking	claim
138	70	Tensor reduction error analysis - Applications to video compression and classification	claim
139	70	Using contours to detect and localize junctions in natural images	claim
140	69	Dimensionality reduction by unsupervised regression	claim
141	69	An LED-only BRDF measurement device	claim
142	69	Robust tensor factorization using R1 norm	claim
143	69	Recursive photometric stereo when multiple shadows and highlights are present	claim
144	69	Sketching in the air: A vision-based system for 3D object design	claim
145	68	Probabilistic graph and hypergraph matching	claim
146	68	A three-point minimal solution for panoramic stitching with lens distortion	claim
147	67	Image decomposition into structure and texture subcomponents with multifrequency modulation constraints	claim
148	67	Joint learning and dictionary construction for pattern recognition	claim
149	67	Object image retrieval by exploiting online knowledge resources	claim
150	67	Fast texture segmentation model based on the shape operator and active contour	claim
151	67	Cost-sensitive face recognition	claim
152	67	Sparsity, redundancy and optimal image support towards knowledge-based segmentation	claim
153	67	Segmentation by transduction	claim
154	66	Annotating collections of photos using hierarchical event and scene models	claim
155	66	Clustering and dimensionality reduction on Riemannian manifolds	claim
156	66	What are the high-level concepts with small semantic gaps?	claim
157	65	Optimizing discrimination-efficiency tradeoff in integrating heterogeneous local features for object detection	claim
158	65	Segmentation of multiple, partially occluded objects by grouping, merging, assigning part detection responses	claim
159	65	Unsupervised learning of probabilistic object models (POMs) for object classification, segmentation and recognition	claim
160	65	Boosting ordinal features for accurate and fast iris recognition	claim
161	65	Consistent image analogies using semi-supervised learning	claim
162	64	On controlling light transport in poor visibility environments	claim
163	64	Motion segmentation via robust subspace separation in the presence of outlying, incomplete, or corrupted trajectories	claim
164	64	Private Content Based Image Retrieval	claim
165	63	Photometric stereo with coherent outlier handling and confidence estimation	claim
166	63	A conditional random field for automatic photo editing	claim
167	63	Image/video deblurring using a hybrid camera	claim
168	63	Enforcing convexity for improved alignment with constrained local models	claim
169	63	Auto-context and its application to high-level vision tasks	claim
170	63	Learning coupled conditional random field for image decomposition with application on object categorization	claim
171	63	Scene classification with low-dimensional semantic spaces and weak supervision	claim
172	63	Intrinsic image decomposition with non-local texture cues	claim
173	63	Scale invariance without scale selection	claim
174	63	Shape priors in variational image segmentation: Convexity, Lipschitz continuity and globally optimal solutions	claim
175	63	Non-negative graph embedding	claim
176	62	Structure learning in random fields for heart motion abnormality detection	claim
177	62	Bayesian tactile face	claim
178	62	High resolution motion layer decomposition using dual-space graph cuts	claim
179	62	IM2GPS: estimating geographic information from a single image	claim
180	62	Extrinsic and depth calibration of ToF-cameras	claim
181	62	Recovering consistent video depth maps via bundle optimization	claim
182	62	High-arity interactions, polyhedral relaxations, and cutting plane algorithm for soft constraint optimisation (MAP-MRF)	claim
183	62	Towards unsupervised whole-object segmentation: Combining automated matting with boundary detection	claim
184	61	Learning-based face hallucination in DCT domain	claim
185	61	Robust 3D face recognition in uncontrolled environments	claim
186	61	Learning patch correspondences for improved viewpoint invariant face recognition	claim
187	61	A Loopy Belief Propagation approach for robust background estimation	claim
188	61	Sensor planning for automated and persistent object tracking with multiple cameras	claim
189	61	Action MACH a spatio-temporal Maximum Average Correlation Height filter for action recognition	claim
190	61	Boosting adaptive linear weak classifiers for online learning and tracking	claim
191	61	Two-Dimensional Active Learning for image classification	claim
192	61	Face tracking and recognition with visual constraints in real-world videos	claim
193	61	A factorization approach to structure from motion with shape priors	claim
194	60	Action recognition using exemplar-based embedding	claim
195	60	Classification via semi-Riemannian spaces	claim
196	60	Building reconstruction from a single DEM	claim
197	60	Semi-Supervised Discriminant Analysis using robust path-based similarity	claim
198	60	Discriminative human action segmentation and recognition using semi-Markov model	claim
199	60	Efficient object shape recovery via slicing planes	claim
200	59	ANSIG - An analytic signature for permutation-invariant two-dimensional shape representation	claim
201	59	A linear approach to motion estimation using generalized camera models	claim
202	59	3D-2D spatiotemporal registration for sports motion analysis	claim
203	59	Manifold-Manifold Distance with application to face recognition based on image set	claim
204	59	Viewpoint-independent object class detection using 3D Feature Maps	claim
205	59	Learning Bayesian Networks with qualitative constraints	claim
206	59	Fast algorithms for large scale conditional 3D prediction	claim
207	58	An integrated background model for video surveillance based on primal sketch and 3D scene geometry	claim
208	58	Discriminative modeling by Boosting on Multilevel Aggregates	claim
209	58	Loose shape model for discriminative learning of object categories	claim
210	58	Statistical analysis on Stiefel and Grassmann manifolds with applications in computer vision	claim
211	58	Face alignment via boosted ranking model	claim
212	58	Joint multi-label multi-instance learning for image classification	claim
213	58	Multi-object shape estimation and tracking from silhouette cues	claim
214	58	Detecting and matching repeated patterns for automatic geo-tagging in urban environments	claim
215	58	Fast image search for learned metrics	claim
216	58	Lost in quantization: Improving particular object retrieval in large scale image databases	claim
217	58	Coarse-to-fine low-rank structure-from-motion	claim
218	58	On errors-in-variables regression with arbitrary covariance and its application to optical flow estimation	claim
219	58	Edge descriptors for robust wide-baseline correspondence	claim
220	58	Action recognition using ballistic dynamics	claim
221	58	Discovering class specific composite features through discriminative sampling with Swendsen-Wang Cut	claim
222	58	Dimensionality reduction using covariance operator inverse regression	claim
223	57	A mobile vision system for robust multi-person tracking	claim
224	57	Global data association for multi-object tracking using network flows	claim
225	57	Edge preserving spatially varying mixtures for image segmentation	claim
226	57	Tracking distributions with an overlap prior
227	57	Stereo reconstruction with mixed pixels using adaptive over-segmentation	claim
228	57	Motion estimation for multi-camera systems using global optimization	claim
229	57	Structure-perceptron learning of a hierarchical log-linear model	claim
230	57	Large-scale manifold learning	claim
231	57	Semi-supervised learning of multi-factor models for face de-identification	claim
232	57	Learning on lie groups for invariant detection and tracking	claim
233	57	Human action recognition using Local Spatio-Temporal Discriminant Embedding	claim
234	57	Simple calibration of non-overlapping cameras with a mirror	claim
235	57	Modeling complex luminance variations for target tracking	claim
236	56	Intensity statistics-based HSI diffusion for color photo denoising	claim
237	56	Spectrally optimal factorization of incomplete matrices	claim
238	56	Dense correspondence finding for parametrization-free animation reconstruction from video	claim
239	56	Motion from blur	claim
240	56	A Parallel Decomposition Solver for SVM: Distributed dual ascend using Fenchel Duality	claim
241	56	Variable baseline/resolution stereo	claim
242	56	Detection with multi-exit asymmetric boosting	claim
243	56	A joint appearance-spatial distance for kernel-based image categorization	claim
244	55	Color constancy beyond bags of pixels	claim
245	55	Pose primitive based human action recognition in videos or still images	claim
246	55	Drift-free tracking of rigid and articulated objects	claim
247	55	Graph-shifts: Natural image labeling by dynamic hierarchical computing	claim
248	55	Coherent image annotation by learning semantic distance	claim
249	55	Selective hidden random fields: Exploiting domain-specific saliency for event classification	claim
250	55	A polynomial-time bound for matching and registration with outliers	claim
251	55	Least squares surface reconstruction from measured gradient fields	claim
252	55	Hierarchical, learning-based automatic liver segmentation	claim
253	55	Large margin pursuit for a Conic Section classifier	claim
254	55	Sequential sparsification for change detection	claim
255	54	Motion blur identification from image gradients	claim
256	54	Demosaicking recognition with applications in digital photo authentication based on a quadratic pixel correlation model	claim
257	54	Conditional density learning via regression with application to deformable shape segmentation	claim
258	54	Characterizing the shadow space of camera-light pairs	claim
259	54	Pan, zoom, scan - Time-coherent, trained automatic video cropping	claim
260	54	Local grouping for optical flow	claim
261	54	Graph commute times for image representation	claim
262	54	Context-dependent kernel design for object matching and recognition	claim
263	54	Skeletal graphs for efficient structure from motion	claim
264	54	Dynamic visual category learning	claim
265	54	Calibration of an Articulated Camera System	claim
266	53	Extracting smooth and transparent layers from a single image	claim
267	53	Latent topic random fields: Learning using a taxonomy of labels	claim
268	53	Histogram-based search: A comparative study	claim
269	53	Fuzzy chamfer distance and its probabilistic formulation for visual tracking	claim
270	53	Principled fusion of high-level model and low-level cues for motion segmentation	claim
271	53	Interactive image segmentation via minimization of quadratic energies on directed graphs	claim
272	53	Face illumination normalization on large and small scale features	claim
273	53	Pair-activity classification by bi-trajectories analysis	claim
274	53	Shading models for illumination and reflectance invariant shape detectors	claim
275	53	Adaptive and constrained algorithms for inverse compositional Active Appearance Model fitting	claim
276	53	Mining compositional features for boosting	claim
277	53	Face shape recovery from a single image using CCA mapping between tensor spaces	claim
278	52	Modeling and generating complex motion blur for real-time tracking	claim
279	52	A mixed generative-discriminative framework for pedestrian classification	claim
280	52	Correspondence-free multi-camera activity analysis and scene modeling	claim
281	52	Directions of egomotion from antipodal points	claim
282	52	The statistical modelling of fingerprint minutiae distribution with implications for fingerprint individuality studies	claim
283	52	Light-invariant fitting of active appearance models	claim
284	52	Estimating camera response functions using probabilistic intensity similarity	claim
285	52	The Logistic Random Field - A convenient graphical model for learning parameters for MRF-based labeling	claim
286	52	Directional independent component analysis with tensor representation	claim
287	52	Globally optimal bilinear programming for computer vision applications	claim
288	52	3D surface models by geometric constraints propagation	claim
289	52	Who killed the directed model?	claim
290	52	The Kneed Walker for human pose tracking	claim
291	52	Classification and evaluation of cost aggregation methods for stereo correspondence	claim
292	51	Learning for stereo vision using the structured support vector machine	claim
293	51	Recognising faces in unseen modes: A tensor based approach	claim
294	51	Symmetric multi-view stereo reconstruction from planar camera arrays	claim
295	51	Photogeometric structured light: A self-calibrating and multi-viewpoint framework for accurate 3D modeling	claim
296	51	Spectral methods for semi-supervised manifold learning	claim
297	51	Unifying discriminative visual codebook generation with classifier training for object category recognition	claim
298	51	One step beyond histograms: Image representation using Markov stationary features	claim
299	51	Minimal solutions for generic imaging models	claim
300	51	Rotation symmetry group detection via frequency analysis of frieze-expansions	claim
301	51	A Scalable graph-cut algorithm for N-D grids	claim
302	51	PSF estimation using sharp edge prediction	claim
303	51	Enforcing stochastic inverse consistency in non-rigid image registration and matching	claim
304	51	Robust null space representation and sampling for view-invariant motion trajectory analysis	claim
305	51	Coherent Laplacian 3-D protrusion segmentation	claim
306	51	Simultaneous super-resolution and feature extraction for recognition of low-resolution faces	claim
307	50	Real-time global localization with a pre-built visual landmark database	claim
308	50	Toward automatic 3D modeling of scenes using a generic camera model	claim
309	50	Building segmentation for densely built urban regions using aerial LIDAR data	claim
310	50	Accurate multi-view reconstruction using robust binocular stereo and surface meshing	claim
311	50	Fast kernel learning for spatial pyramid matching	claim
312	50	Robust unambiguous parametrization of the essential manifold	claim
313	50	Active microscopic cellular image annotation by superposable graph transduction with imbalanced labels	claim
314	50	Robust estimation of gaussian mixtures from noisy input data	claim
315	50	Object categorization using co-occurrence, location and appearance	claim
316	50	On the use of independent tasks for face recognition	claim
317	50	Vital sign estimation from passive thermal video	claim
318	50	A statistical deformation prior for non-rigid image and shape registration	claim
319	50	Information-theoretic active scene exploration	claim
320	50	The scale of a texture and its application to segmentation	claim
321	50	Radiometric calibration with illumination change for outdoor scene analysis	claim
322	50	Detection and matching of rectilinear structures	claim
323	50	A NURBS-based spectral reflectance descriptor with applications in computer vision and pattern recognition	claim
324	49	Order consistent change detection via fast statistical significance testing	claim
325	49	Evaluation of color descriptors for object and scene recognition	claim
326	49	3-D Tracking of shoes for Virtual Mirror applications	claim
327	49	A similarity measure between unordered vector sets with application to image categorization	claim
328	49	Local minima free Parameterized Appearance Models	claim
329	49	Learning subcategory relevances for category recognition	claim
330	49	Image selection for improved Multi-View Stereo	claim
331	49	An adaptive learning method for target tracking across multiple cameras	claim
332	49	Graph cut with ordering constraints on labels and its applications	claim
333	49	Adaptive parametrization of multivariate B-splines for image registration	claim
334	49	Quasi-perspective projection with applications to 3D factorization from uncalibrated image sequences	claim
335	49	Integrated feature selection and higher-order spatial feature extraction for object categorization	claim
336	49	Kernel integral images: A framework for fast non-uniform filtering	claim
337	48	A quasi-random sampling approach to image retrieval	claim
338	48	Distributed data association and filtering for multiple target tracking	claim
339	48	Adaptive region intensity based rigid ultrasound and CT image registration	claim
340	48	Utilizing semantic word similarity measures for video retrieval	claim
341	48	Adaptive and compact shape descriptor by progressive feature combination and selection with boosting	claim
342	48	Photometric stereo with non-parametric and spatially-varying reflectance	claim
343	48	Normalized tree partitioning for image segmentation	claim
344	48	Learning and using taxonomies for fast visual categorization	claim
345	48	Flat refractive geometry	claim
346	48	Enhanced biologically inspired model	claim
347	48	Epitomic location recognition	claim
348	48	3D occlusion recovery using few cameras	claim
349	48	Robust higher order potentials for enforcing label consistency	claim
350	48	Manifold learning using robust Graph Laplacian for interactive image search	claim
351	48	Matching non-rigidly deformable shapes across images: A globally optimal solution	claim
352	48	Unsupervised feature selection via distributed coding for multi-view object recognition	claim
353	48	From skeletons to bone graphs: Medial abstraction for object recognition	claim
354	47	Robust fusion of dynamic shape and normal capture for high-quality reconstruction of time-varying geometry	claim
355	47	Unified Principal Component Analysis with generalized Covariance Matrix for face recognition	claim
356	47	Context-aware clustering	claim
357	47	A recursive filter for linear systems on Riemannian manifolds	claim
358	47	Automatic symmetry plane estimation of bilateral objects in point clouds	claim
359	47	Max Margin AND/OR Graph learning for parsing the human body	claim
360	47	Computing minimal deformations: application to construction of statistical shape models	claim
361	46	Improving local learning for object categorization by exploring the effects of ranking	claim
362	46	Incremental learning of nonparametric Bayesian mixture models	claim
363	46	Learning object motion patterns for anomaly detection and improved object detection	claim
364	46	3D shape reconstruction of Mooney faces	claim
365	46	Classifiability-based Optimal Discriminatory Projection Pursuit	claim
366	46	Margin-based discriminant dimensionality reduction for visual recognition	claim
367	46	Reconstructing non-stationary articulated objects in monocular video using silhouette information	claim
368	46	View-invariant recognition of body pose from space-time templates	claim
369	46	Joint tracking of features and edges	claim
370	45	Demosaicing by smoothing along 1D features	claim
371	45	Learning a geometry integrated image appearance manifold from a small training set	claim
372	45	Semi-supervised distance metric learning for Collaborative Image Retrieval	claim
373	45	A general solution to the P4P problem for camera with unknown focal length	claim
374	45	Radiometric calibration using temporal irradiance mixtures	claim
375	45	Simultaneous clustering and tracking unknown number of objects	claim
376	45	Matching images under unstable segmentations	claim
377	45	Articulated shape matching using Laplacian eigenfunctions and unsupervised point registration	claim
378	45	Learning stick-figure models using nonparametric Bayesian priors over trees	claim
379	44	What can missing correspondences tell us about 3D structure and motion?	claim
380	44	Correlational spectral clustering	claim
381	44	Multi-label image segmentation via point-wise repetition	claim
382	44	Beyond the Lambertian assumption: A generative model for Apparent BRDF fields of faces using anti-symmetric tensor splines	claim
383	44	Retinal image registration from 2D to 3D	claim
384	44	Transductive object cutout	claim
385	44	Accurate camera calibration from multi-view stereo and bundle adjustment	claim
386	44	Human-assisted motion annotation	claim
387	44	Enforcing non-positive weights for stable support vector tracking	claim
388	44	Filtering Internet image search results towards keyword based category recognition	claim
389	44	Constrained image segmentation from hierarchical boundaries	claim
390	44	Accurate and robust registration for in-hand modeling	claim
391	43	Tracking rotating fluids in realtime using snapshots	claim
392	43	Unsupervised learning of visual taxonomies	claim
393	43	Smoothing-based Optimization	claim
394	43	A unified framework for generalized Linear Discriminant Analysis	claim
395	43	Linear motion estimation for systems of articulated planes	claim
396	43	What do color changes reveal about an outdoor scene?	claim
397	43	Object recognition and segmentation by non-rigid quasi-dense matching	claim
398	42	Fusion of time-of-flight depth and stereo for high accuracy depth maps	claim
399	42	A theoretical analysis of linear and multi-linear models of image appearance	claim
400	42	High quality mesostructure acquisition using specularities	claim
401	42	Interactive image matting for multiple layers	claim
402	42	Dense 3D reconstruction from specularity consistency	claim
403	42	3D pose refinement from reflections	claim
404	42	Unsupervised modeling of object categories using link analysis techniques	claim
405	42	Nonlinear image representation using divisive normalization	claim
406	42	Joint data alignment up to (lossy) transformations	claim
407	42	Granularity and elasticity adaptation in visual tracking	claim
408	42	Connected Segmentation Tree - A joint representation of region layout and hierarchy	claim
409	41	A rank constrained continuous formulation of multi-frame multi-target tracking problem	claim
410	41	Efficient subdivision-based image and volume warping	claim
411	41	Model-based hand tracking with texture, shading and self-occlusions	claim
412	41	Physical simulation for probabilistic motion tracking	claim
413	41	Volumetric reconstruction from multi-energy single-view radiography	claim
414	41	FuzzyMatte: A computationally efficient scheme for interactive matting	claim
415	41	Simultaneous data volume reconstruction and pose estimation from slice samples	claim
416	41	Taylor expansion based classifier adaptation: Application to person detection	claim
417	40	Recognition by association via learning per-exemplar distances	claim
418	40	Observe-and-explain: A new approach for multiple hypotheses tracking of humans and objects	claim
419	40	Learning based coarse-to-fine image registration	claim
420	40	Hallucinating 3D facial shapes	claim
421	40	Geo-located image analysis using latent representations	claim
422	40	Performance evaluation of state-of-the-art discrete symmetry detection algorithms	claim
423	40	Meshless deformable models for LV motion analysis	claim
424	40	Non-refractive modulators for encoding and capturing scene appearance and depth	claim
425	39	Probabilistic multi-tensor estimation using the Tensor Distribution Function	claim
426	39	Off-axis aperture camera: 3D shape reconstruction and image restoration	claim
427	39	Scene understanding with discriminative structured prediction	claim
428	39	Optical flow estimation with uncertainties through dynamic MRFs	claim
429	39	Increasing the density of Active Appearance Models	claim
430	39	Re-thinking non-rigid structure from motion	claim
431	39	Relaxed matching kernels for robust image comparison	claim
432	37	Sensing increased image resolution using aperture masks	claim
433	37	Visual quasi-periodicity	claim
434	37	Exploiting side information in locality preserving projection	claim
435	36	View and scale invariant action recognition using multiview shape-flow models	claim
436	36	Measuring camera translation by the dominant apical angle	claim
437	36	Globally optimal shape-based tracking in real-time	claim
438	35	Summarizing visual data using bidirectional similarity	claim
439	33	Subspace segmentation with outliers: A grassmannian approach to the maximum consensus subspace	claim
440	33	Reduce, reuse & recycle: Efficiently solving multi-label MRFs	claim
441	33	Semantic-based indexing of fetal anatomies from 3-D ultrasound data using global/semi-local context and sequential sampling	claim
442	32	Partitioning of image datasets using discriminative context information	claim
443	30	Finding trails	claim
444	28	Overcoming visual reverberations	claim

Sciweavers

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers