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

1094views Computer Vision» more CVPR 2008»

Image super-resolution using gradient profile prior

14 years 6 months ago

Download research.microsoft.com

In this paper, we propose an image super-resolution approach using a novel generic image prior ? gradient profile prior, which is a parametric prior describing the shape and the s...

Jian Sun, Zongben Xu, Heung-Yeung Shum

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	1094	Image super-resolution using gradient profile prior	claim
2	1042	Graph cut based image segmentation with connectivity priors	claim
3	947	Accurate Eye Center Location and Tracking Using Isophote Curvature
4	887	Image partial blur detection and classification	claim
5	880	Visibility in bad weather from a single image	claim
6	855	Beyond sliding windows: Object localization by efficient subwindow search	claim
7	815	Estimating age, gender, and identity using first name priors
8	795	Discriminative local binary patterns for human detection in personal album	claim
9	786	Privacy preserving crowd monitoring: Counting people without people models or tracking	claim
10	588	Illumination and Camera Invariant Stereo Matching
11	539	Robust dual motion deblurring	claim
12	523	Rank-based distance metric learning: An application to image retrieval	claim
13	510	A discriminatively trained, multiscale, deformable part model	claim
14	507	An efficient algorithm for compressed MR imaging using total variation and wavelets	claim
15	496	Real-Time Face Pose Estimation from Single Range Images
16	490	Optical flow estimation using Fourier Mellin Transform	claim
17	469	Regularizing 3D medial axis using medial scaffold transforms
18	424	A hybrid camera for motion deblurring and depth map super-resolution
19	411	Using contours to detect and localize junctions in natural images	claim
20	411	Classification using intersection kernel support vector machines is efficient	claim
21	398	Learning human actions via information maximization
22	396	Geo-spatial aerial video processing for scene understanding and object tracking	claim
23	388	Learning realistic human actions from movies	claim
24	385	A fast local descriptor for dense matching	claim
25	377	Combining appearance models and Markov Random Fields for category level object segmentation	claim
26	362	Automatic registration of aerial imagery with untextured 3D LiDAR models	claim
27	359	Simultaneous learning of a discriminative projection and prototypes for Nearest-Neighbor classification	claim
28	358	Multiple-instance ranking: Learning to rank images for image retrieval	claim
29	350	Simultaneous super-resolution and 3D video using graph-cuts
30	343	Discriminative learning of visual words for 3D human pose estimation	claim
31	338	From appearance to context-based recognition: Dense labeling in small images
32	338	Recovering Shape Characteristics on Near-flat Specular Surfaces
33	335	A robust descriptor based on Weber's Law	claim
34	334	Recognizing human actions using multiple features
35	334	General Constraints for Batch Multiple-Target Tracking Applied to Large-Scale Videomicroscopy
36	330	Clothing cosegmentation for recognizing people
37	329	Local deformation models for monocular 3D shape recovery	claim
38	328	Progressive search space reduction for human pose estimation	claim
39	328	Unsupervised discovery of visual object class hierarchies	claim
40	323	A hierarchical and contextual model for aerial image understanding	claim
41	322	Conjugate rotation: Parameterization and estimation from an affine feature correspondence	claim
42	319	Sparse probabilistic regression for activity-independent human pose inference	claim
43	318	Parameterized Kernel Principal Component Analysis: Theory and applications to supervised and unsupervised image alignment	claim
44	314	SMRFI: Shape matching via registration of vector-valued feature images
45	312	Object tracking and detection after occlusion via numerical hybrid local and global mode-seeking	claim
46	309	Action recognition by learning mid-level motion features	claim
47	309	Real-time pose estimation of articulated objects using low-level motion	claim
48	304	Context and observation driven latent variable model for human pose estimation	claim
49	303	Semi-supervised boosting using visual similarity learning
50	302	Sequential particle swarm optimization for visual tracking	claim
51	299	Homography based multiple camera detection and tracking of people in a dense crowd	claim
52	298	3D face tracking and expression inference from a 2D sequence using manifold learning	claim
53	297	Generalised blurring mean-shift algorithms for nonparametric clustering	claim
54	297	Spatio-temporal Saliency detection using phase spectrum of quaternion fourier transform	claim
55	294	Action snippets: How many frames does human action recognition require?	claim
56	291	A Bayesian approach for image segmentation with shape priors	claim
57	291	Approximate earth mover's distance in linear time	claim
58	291	Constant time O(1) bilateral filtering	claim
59	289	Automatic face naming with caption-based supervision
60	289	Recovery of relative depth from a single observation using an uncalibrated (real-aperture) camera	claim
61	288	Visual tracking via incremental Log-Euclidean Riemannian subspace learning	claim
62	287	Extracting a fluid dynamic texture and the background from video	claim
63	286	Simultaneous image transformation and sparse representation recovery	claim
64	286	3D model matching with Viewpoint-Invariant Patches (VIP)	claim
65	285	Particle filtering for registration of 2D and 3D point sets with stochastic dynamics	claim
66	284	Real time object tracking based on dynamic feature grouping with background subtraction	claim
67	282	Unsupervised estimation of segmentation quality using nonnegative factorization	claim
68	280	Dense 3D motion capture from synchronized video streams	claim
69	280	Background subtraction in highly dynamic scenes	claim
70	280	Stereoscopic inpainting: Joint color and depth completion from stereo images	claim
71	277	Constrained spectral clustering through affinity propagation	claim
72	276	Unsupervised learning of probabilistic object models (POMs) for object classification, segmentation and recognition	claim
73	275	IM2GPS: estimating geographic information from a single image	claim
74	271	Discriminative learned dictionaries for local image analysis	claim
75	270	Learning 4D action feature models for arbitrary view action recognition	claim
76	269	Automatic non-rigid registration of 3D dynamic data for facial expression synthesis and transfer	claim
77	267	People-tracking-by-detection and people-detection-by-tracking
78	263	Combining brain computer interfaces with vision for object categorization	claim
79	257	Shape prior segmentation of multiple objects with graph cuts	claim
80	256	Global data association for multi-object tracking using network flows	claim
81	255	Learning Bayesian Networks with qualitative constraints	claim
82	254	Semi-supervised SVM batch mode active learning for image retrieval	claim
83	253	Small codes and large image databases for recognition	claim
84	252	Efficient mean shift belief propagation for vision tracking	claim
85	251	Transfer learning for image classification with sparse prototype representations	claim
86	249	Decomposition, discovery and detection of visual categories using topic models	claim
87	247	3-D Tracking of shoes for Virtual Mirror applications	claim
88	244	Robust statistics on Riemannian manifolds via the geometric median	claim
89	244	FusionFlow: Discrete-continuous optimization for optical flow estimation	claim
90	243	Randomized trees for human pose detection	claim
91	242	A two-frame theory of motion, lighting and shape	claim
92	242	Nonlinear image representation using divisive normalization	claim
93	242	Matching non-rigidly deformable shapes across images: A globally optimal solution	claim
94	242	Viewpoint-independent object class detection using 3D Feature Maps	claim
95	241	Globally optimal surface segmentation using regional properties of segmented objects	claim
96	240	Regression from patch-kernel	claim
97	239	Trajectory analysis and semantic region modeling using a nonparametric Bayesian model	claim
98	239	Boosting ordinal features for accurate and fast iris recognition	claim
99	239	Shape priors in variational image segmentation: Convexity, Lipschitz continuity and globally optimal solutions	claim
100	239	Sketching in the air: A vision-based system for 3D object design	claim
101	238	A deformable local image descriptor	claim
102	238	Selective hidden random fields: Exploiting domain-specific saliency for event classification	claim
103	238	Face shape recovery from a single image using CCA mapping between tensor spaces	claim
104	238	Global stereo reconstruction under second order smoothness priors	claim
105	238	3D shape reconstruction of Mooney faces	claim
106	238	Manifold-Manifold Distance with application to face recognition based on image set	claim
107	238	Photometric stereo with coherent outlier handling and confidence estimation	claim
108	236	Semantic texton forests for image categorization and segmentation	claim
109	236	Human action recognition using Local Spatio-Temporal Discriminant Embedding	claim
110	236	Modeling and generating complex motion blur for real-time tracking	claim
111	236	Boosted deformable model for human body alignment	claim
112	235	Finding people in archive films through tracking	claim
113	235	Superpixel lattices	claim
114	234	A region based stereo matching algorithm using cooperative optimization	claim
115	234	Action recognition with motion-appearance vocabulary forest	claim
116	233	Adaptive and constrained algorithms for inverse compositional Active Appearance Model fitting	claim
117	233	Dense specular shape from multiple specular flows	claim
118	233	Latent topic random fields: Learning using a taxonomy of labels	claim
119	233	Image/video deblurring using a hybrid camera	claim
120	233	Loose shape model for discriminative learning of object categories	claim
121	233	Video segmentation: Propagation, validation and aggregation of a preceding graph	claim
122	232	Clustering and dimensionality reduction on Riemannian manifolds	claim
123	231	(BP)2: Beyond pairwise Belief Propagation labeling by approximating Kikuchi free energies	claim
124	230	Visual Synset: Towards a higher-level visual representation	claim
125	228	In defense of Nearest-Neighbor based image classification	claim
126	227	Markerless motion capture of man-machine interaction	claim
127	226	Learning class-specific affinities for image labelling
128	226	Coherent image annotation by learning semantic distance	claim
129	225	Face tracking and recognition with visual constraints in real-world videos	claim
130	224	A conditional random field for automatic photo editing	claim
131	224	Image super-resolution as sparse representation of raw image patches	claim
132	223	Where am I: Place instance and category recognition using spatial PACT	claim
133	223	Semi-supervised distance metric learning for Collaborative Image Retrieval	claim
134	223	Tensor reduction error analysis - Applications to video compression and classification	claim
135	223	Fast kernel learning for spatial pyramid matching	claim
136	223	A similarity measure between unordered vector sets with application to image categorization	claim
137	222	Structure-perceptron learning of a hierarchical log-linear model	claim
138	222	Tracking distributions with an overlap prior
139	221	Closing the loop in scene interpretation	claim
140	220	On controlling light transport in poor visibility environments	claim
141	220	Spectral methods for semi-supervised manifold learning	claim
142	219	Accurate multi-view reconstruction using robust binocular stereo and surface meshing	claim
143	219	Classification via semi-Riemannian spaces	claim
144	218	Action recognition using ballistic dynamics	claim
145	218	Global pose estimation using non-tree models	claim
146	217	Correspondence-free multi-camera activity analysis and scene modeling	claim
147	217	Lost in quantization: Improving particular object retrieval in large scale image databases	claim
148	216	Robust tensor factorization using R1 norm	claim
149	216	Online learning of patch perspective rectification for efficient object detection	claim
150	214	Fast image search for learned metrics	claim
151	214	On benchmarking camera calibration and multi-view stereo for high resolution imagery	claim
152	214	Extrinsic and depth calibration of ToF-cameras	claim
153	214	Adaptive region intensity based rigid ultrasound and CT image registration	claim
154	213	Physical simulation for probabilistic motion tracking	claim
155	213	Kernel-based learning of cast shadows from a physical model of light sources and surfaces for low-level segmentation	claim
156	213	Retinal image registration from 2D to 3D	claim
157	213	Joint learning and dictionary construction for pattern recognition	claim
158	212	Modulated phase-shifting for 3D scanning	claim
159	212	Action recognition using exemplar-based embedding	claim
160	212	Constrained image segmentation from hierarchical boundaries	claim
161	211	Auto-context and its application to high-level vision tasks	claim
162	211	Non-negative graph embedding	claim
163	211	Segmentation by transduction	claim
164	211	A mobile vision system for robust multi-person tracking	claim
165	211	Real-time 3D segmentation of the left ventricle using deformable subdivision surfaces	claim
166	211	Learning-based face hallucination in DCT domain	claim
167	210	Histogram-based search: A comparative study	claim
168	210	Looking around the backyard helps to recognize faces and digits	claim
169	210	Bayesian color constancy revisited	claim
170	209	Towards unsupervised whole-object segmentation: Combining automated matting with boundary detection	claim
171	209	Building segmentation for densely built urban regions using aerial LIDAR data	claim
172	208	Edge preserving spatially varying mixtures for image segmentation	claim
173	207	Statistical analysis on Stiefel and Grassmann manifolds with applications in computer vision	claim
174	207	Drift-free tracking of rigid and articulated objects	claim
175	207	Efficient photometric stereo on glossy surfaces with wide specular lobes	claim
176	207	Multiplicative kernels: Object detection, segmentation and pose estimation	claim
177	207	Private Content Based Image Retrieval	claim
178	207	Graph commute times for image representation	claim
179	207	Large-scale manifold learning	claim
180	207	Motion from blur	claim
181	207	Normalized tree partitioning for image segmentation	claim
182	206	Pose primitive based human action recognition in videos or still images	claim
183	206	Building reconstruction from a single DEM	claim
184	205	Boosting adaptive linear weak classifiers for online learning and tracking	claim
185	204	Color constancy beyond bags of pixels	claim
186	204	Correspondences between parts of shapes with particle filters	claim
187	204	Object image retrieval by exploiting online knowledge resources	claim
188	203	Least squares congealing for unsupervised alignment of images	claim
189	203	Interactive image segmentation via minimization of quadratic energies on directed graphs	claim
190	202	Visual tracking with histograms and articulating blocks	claim
191	202	Precise detailed detection of faces and facial features	claim
192	201	Local minima free Parameterized Appearance Models	claim
193	201	Adaptive parametrization of multivariate B-splines for image registration	claim
194	201	The patch transform and its applications to image editing	claim
195	201	Bayesian tactile face	claim
196	201	Beyond the Lambertian assumption: A generative model for Apparent BRDF fields of faces using anti-symmetric tensor splines	claim
197	200	Articulated shape matching using Laplacian eigenfunctions and unsupervised point registration	claim
198	200	Skeletal graphs for efficient structure from motion	claim
199	199	Utilizing semantic word similarity measures for video retrieval	claim
200	199	A Parallel Decomposition Solver for SVM: Distributed dual ascend using Fenchel Duality	claim
201	199	Accurate and robust registration for in-hand modeling	claim
202	199	3D occlusion recovery using few cameras	claim
203	199	An integrated background model for video surveillance based on primal sketch and 3D scene geometry	claim
204	199	Meshless deformable models for LV motion analysis	claim
205	198	Semi-Supervised Discriminant Analysis using robust path-based similarity	claim
206	198	Sequential sparsification for change detection	claim
207	198	A bi-illuminant dichromatic reflection model for understanding images	claim
208	198	Exact inference in multi-label CRFs with higher order cliques	claim
209	198	Robust learning of discriminative projection for multicategory classification on the Stiefel manifold	claim
210	197	On errors-in-variables regression with arbitrary covariance and its application to optical flow estimation	claim
211	196	Recognition by association via learning per-exemplar distances	claim
212	196	Efficient sequential correspondence selection by cosegmentation	claim
213	196	Multi-object shape estimation and tracking from silhouette cues	claim
214	195	A factorization approach to structure from motion with shape priors	claim
215	195	Enforcing convexity for improved alignment with constrained local models	claim
216	195	Fast texture segmentation model based on the shape operator and active contour	claim
217	195	Single-image vignetting correction using radial gradient symmetry	claim
218	195	Intensity statistics-based HSI diffusion for color photo denoising	claim
219	194	Learning for stereo vision using the structured support vector machine	claim
220	194	ANSIG - An analytic signature for permutation-invariant two-dimensional shape representation	claim
221	194	Robust fusion of dynamic shape and normal capture for high-quality reconstruction of time-varying geometry	claim
222	194	Matching images under unstable segmentations	claim
223	194	Image de-fencing	claim
224	194	Object recognition and segmentation by non-rigid quasi-dense matching	claim
225	194	High resolution matting via interactive trimap segmentation	claim
226	193	A general solution to the P4P problem for camera with unknown focal length	claim
227	193	Hybrid body representation for integrated pose recognition, localization and segmentation	claim
228	193	Segmentation of multiple, partially occluded objects by grouping, merging, assigning part detection responses	claim
229	193	Optimizing discrimination-efficiency tradeoff in integrating heterogeneous local features for object detection	claim
230	192	Least squares surface reconstruction from measured gradient fields	claim
231	192	Scene classification with low-dimensional semantic spaces and weak supervision	claim
232	192	Evaluation of color descriptors for object and scene recognition	claim
233	192	The statistical modelling of fingerprint minutiae distribution with implications for fingerprint individuality studies	claim
234	192	Motion blur identification from image gradients	claim
235	192	Demosaicking recognition with applications in digital photo authentication based on a quadratic pixel correlation model	claim
236	191	Similarity-based cross-layered hierarchical representation for object categorization	claim
237	191	An experimental study of employing visual appearance as a phenotype	claim
238	190	Robust 3D face recognition in uncontrolled environments	claim
239	190	Dense 3D reconstruction from specularity consistency	claim
240	190	A Loopy Belief Propagation approach for robust background estimation	claim
241	189	Distributed data association and filtering for multiple target tracking	claim
242	189	Learning coupled conditional random field for image decomposition with application on object categorization	claim
243	189	Discriminative human action segmentation and recognition using semi-Markov model	claim
244	189	3D surface models by geometric constraints propagation	claim
245	188	Fusion of time-of-flight depth and stereo for high accuracy depth maps	claim
246	187	High resolution motion layer decomposition using dual-space graph cuts	claim
247	187	Discovering class specific composite features through discriminative sampling with Swendsen-Wang Cut	claim
248	187	3D-2D spatiotemporal registration for sports motion analysis	claim
249	187	Semantic-based indexing of fetal anatomies from 3-D ultrasound data using global/semi-local context and sequential sampling	claim
250	186	Order consistent change detection via fast statistical significance testing	claim
251	186	Dimensionality reduction by unsupervised regression	claim
252	185	Symmetric multi-view stereo reconstruction from planar camera arrays	claim
253	185	Face alignment via boosted ranking model	claim
254	185	Detection with multi-exit asymmetric boosting	claim
255	185	Modeling the structure of multivariate manifolds: Shape maps	claim
256	184	Annotating collections of photos using hierarchical event and scene models	claim
257	184	Detecting and matching repeated patterns for automatic geo-tagging in urban environments	claim
258	184	Probabilistic image registration and anomaly detection by nonlinear warping	claim
259	183	A linear approach to motion estimation using generalized camera models	claim
260	182	Action MACH a spatio-temporal Maximum Average Correlation Height filter for action recognition	claim
261	182	Two-Dimensional Active Learning for image classification	claim
262	182	View and scale invariant action recognition using multiview shape-flow models	claim
263	181	Scale invariance without scale selection	claim
264	181	PSF estimation using sharp edge prediction	claim
265	181	Globally optimal bilinear programming for computer vision applications	claim
266	180	Correlational spectral clustering	claim
267	180	Active microscopic cellular image annotation by superposable graph transduction with imbalanced labels	claim
268	180	Local grouping for optical flow	claim
269	180	Misalignment-robust face recognition	claim
270	180	A quasi-random sampling approach to image retrieval	claim
271	180	Discriminative modeling by Boosting on Multilevel Aggregates	claim
272	180	Fast and robust numerical solutions to minimal problems for cameras with radial distortion	claim
273	180	Image selection for improved Multi-View Stereo	claim
274	180	The Logistic Random Field - A convenient graphical model for learning parameters for MRF-based labeling	claim
275	180	Layered graphical models for tracking partially-occluded objects	claim
276	179	Motion segmentation via robust subspace separation in the presence of outlying, incomplete, or corrupted trajectories	claim
277	178	One step beyond histograms: Image representation using Markov stationary features	claim
278	178	Mining compositional features for boosting	claim
279	178	Silhouette-based camera calibration from sparse views under circular motion	claim
280	178	Characterizing the shadow space of camera-light pairs	claim
281	178	Intrinsic image decomposition with non-local texture cues	claim
282	178	Off-axis aperture camera: 3D shape reconstruction and image restoration	claim
283	177	Motion estimation for multi-camera systems using global optimization	claim
284	177	Simultaneous super-resolution and feature extraction for recognition of low-resolution faces	claim
285	177	Toward automatic 3D modeling of scenes using a generic camera model	claim
286	176	Edge descriptors for robust wide-baseline correspondence	claim
287	176	Recovering consistent video depth maps via bundle optimization	claim
288	176	Computing minimal deformations: application to construction of statistical shape models	claim
289	176	Detection and matching of rectilinear structures	claim
290	176	Unified Principal Component Analysis with generalized Covariance Matrix for face recognition	claim
291	175	Radiometric calibration with illumination change for outdoor scene analysis	claim
292	175	Shading models for illumination and reflectance invariant shape detectors	claim
293	175	Joint tracking of features and edges	claim
294	174	Learning a geometry integrated image appearance manifold from a small training set	claim
295	174	Hallucinating 3D facial shapes	claim
296	173	A NURBS-based spectral reflectance descriptor with applications in computer vision and pattern recognition	claim
297	173	Learning patch correspondences for improved viewpoint invariant face recognition	claim
298	173	Unifying discriminative visual codebook generation with classifier training for object category recognition	claim
299	173	An LED-only BRDF measurement device	claim
300	173	Learning stick-figure models using nonparametric Bayesian priors over trees	claim
301	172	Modeling complex luminance variations for target tracking	claim
302	172	Directions of egomotion from antipodal points	claim
303	172	Unsupervised modeling of object categories using link analysis techniques	claim
304	172	Partitioning of image datasets using discriminative context information	claim
305	171	Graph-shifts: Natural image labeling by dynamic hierarchical computing	claim
306	171	Manifold learning using robust Graph Laplacian for interactive image search	claim
307	171	FuzzyMatte: A computationally efficient scheme for interactive matting	claim
308	171	3D pose refinement from reflections	claim
309	171	Consistent image analogies using semi-supervised learning	claim
310	171	Real-time global localization with a pre-built visual landmark database	claim
311	171	Probabilistic multi-tensor estimation using the Tensor Distribution Function	claim
312	170	A polynomial-time bound for matching and registration with outliers	claim
313	170	Overcoming visual reverberations	claim
314	170	Unsupervised feature selection via distributed coding for multi-view object recognition	claim
315	170	Learning object motion patterns for anomaly detection and improved object detection	claim
316	169	Light-invariant fitting of active appearance models	claim
317	169	Context-aware clustering	claim
318	169	Spectrally optimal factorization of incomplete matrices	claim
319	169	A joint appearance-spatial distance for kernel-based image categorization	claim
320	169	Rotation symmetry group detection via frequency analysis of frieze-expansions	claim
321	168	Robust null space representation and sampling for view-invariant motion trajectory analysis	claim
322	168	Image decomposition into structure and texture subcomponents with multifrequency modulation constraints	claim
323	168	Max Margin AND/OR Graph learning for parsing the human body	claim
324	168	Dimensionality reduction using covariance operator inverse regression	claim
325	167	Learning subcategory relevances for category recognition	claim
326	167	Accurate camera calibration from multi-view stereo and bundle adjustment	claim
327	167	Quasi-perspective projection with applications to 3D factorization from uncalibrated image sequences	claim
328	167	Estimating camera response functions using probabilistic intensity similarity	claim
329	167	Sparsity, redundancy and optimal image support towards knowledge-based segmentation	claim
330	167	A three-point minimal solution for panoramic stitching with lens distortion	claim
331	166	Stereo reconstruction with mixed pixels using adaptive over-segmentation	claim
332	166	Classification and evaluation of cost aggregation methods for stereo correspondence	claim
333	166	Joint multi-label multi-instance learning for image classification	claim
334	165	Probabilistic graph and hypergraph matching	claim
335	165	Automatic symmetry plane estimation of bilateral objects in point clouds	claim
336	165	Recursive photometric stereo when multiple shadows and highlights are present	claim
337	164	A statistical deformation prior for non-rigid image and shape registration	claim
338	164	Integrated feature selection and higher-order spatial feature extraction for object categorization	claim
339	163	Cost-sensitive face recognition	claim
340	163	Coherent Laplacian 3-D protrusion segmentation	claim
341	162	Pair-activity classification by bi-trajectories analysis	claim
342	162	The Kneed Walker for human pose tracking	claim
343	161	Model-based hand tracking with texture, shading and self-occlusions	claim
344	161	An adaptive learning method for target tracking across multiple cameras	claim
345	161	Reconstructing non-stationary articulated objects in monocular video using silhouette information	claim
346	161	Principled fusion of high-level model and low-level cues for motion segmentation	claim
347	160	Increasing the density of Active Appearance Models	claim
348	160	Dense correspondence finding for parametrization-free animation reconstruction from video	claim
349	160	Linear motion estimation for systems of articulated planes	claim
350	160	Simultaneous clustering and tracking unknown number of objects	claim
351	160	Variable baseline/resolution stereo	claim
352	159	Enhanced biologically inspired model	claim
353	159	Summarizing visual data using bidirectional similarity	claim
354	158	Face illumination normalization on large and small scale features	claim
355	158	A unified framework for generalized Linear Discriminant Analysis	claim
356	158	Incremental learning of nonparametric Bayesian mixture models	claim
357	158	Information-theoretic active scene exploration	claim
358	158	A theoretical analysis of linear and multi-linear models of image appearance	claim
359	157	Conditional density learning via regression with application to deformable shape segmentation	claim
360	157	Semi-supervised learning of multi-factor models for face de-identification	claim
361	156	Calibration of an Articulated Camera System	claim
362	155	What are the high-level concepts with small semantic gaps?	claim
363	155	Hierarchical, learning-based automatic liver segmentation	claim
364	155	Fast algorithms for large scale conditional 3D prediction	claim
365	154	Extracting smooth and transparent layers from a single image	claim
366	153	Measuring camera translation by the dominant apical angle	claim
367	153	Connected Segmentation Tree - A joint representation of region layout and hierarchy	claim
368	153	Human-assisted motion annotation	claim
369	152	A mixed generative-discriminative framework for pedestrian classification	claim
370	151	Enforcing stochastic inverse consistency in non-rigid image registration and matching	claim
371	151	Learning on lie groups for invariant detection and tracking	claim
372	151	Directional independent component analysis with tensor representation	claim
373	151	Large margin pursuit for a Conic Section classifier	claim
374	151	Who killed the directed model?	claim
375	150	Pan, zoom, scan - Time-coherent, trained automatic video cropping	claim
376	150	Context-dependent kernel design for object matching and recognition	claim
377	150	Efficient subdivision-based image and volume warping	claim
378	149	Non-refractive modulators for encoding and capturing scene appearance and depth	claim
379	149	High-arity interactions, polyhedral relaxations, and cutting plane algorithm for soft constraint optimisation (MAP-MRF)	claim
380	149	On the use of independent tasks for face recognition	claim
381	149	Simultaneous data volume reconstruction and pose estimation from slice samples	claim
382	149	Joint data alignment up to (lossy) transformations	claim
383	149	Fuzzy chamfer distance and its probabilistic formulation for visual tracking	claim
384	148	Object categorization using co-occurrence, location and appearance	claim
385	148	Dynamic visual category learning	claim
386	147	Observe-and-explain: A new approach for multiple hypotheses tracking of humans and objects	claim
387	147	Efficient object shape recovery via slicing planes	claim
388	146	Epitomic location recognition	claim
389	146	Kernel integral images: A framework for fast non-uniform filtering	claim
390	146	Photometric stereo with non-parametric and spatially-varying reflectance	claim
391	146	Improving local learning for object categorization by exploring the effects of ranking	claim
392	145	Simple calibration of non-overlapping cameras with a mirror	claim
393	145	Multi-label image segmentation via point-wise repetition	claim
394	145	Flat refractive geometry	claim
395	145	A rank constrained continuous formulation of multi-frame multi-target tracking problem	claim
396	144	Re-thinking non-rigid structure from motion	claim
397	144	Structure learning in random fields for heart motion abnormality detection	claim
398	144	Tracking rotating fluids in realtime using snapshots	claim
399	143	Reduce, reuse & recycle: Efficiently solving multi-label MRFs	claim
400	143	Margin-based discriminant dimensionality reduction for visual recognition	claim
401	142	Recognising faces in unseen modes: A tensor based approach	claim
402	142	Adaptive and compact shape descriptor by progressive feature combination and selection with boosting	claim
403	142	Granularity and elasticity adaptation in visual tracking	claim
404	142	View-invariant recognition of body pose from space-time templates	claim
405	141	Optical flow estimation with uncertainties through dynamic MRFs	claim
406	141	A Scalable graph-cut algorithm for N-D grids	claim
407	141	Enforcing non-positive weights for stable support vector tracking	claim
408	141	Filtering Internet image search results towards keyword based category recognition	claim
409	141	Smoothing-based Optimization	claim
410	141	Scene understanding with discriminative structured prediction	claim
411	140	Coarse-to-fine low-rank structure-from-motion	claim
412	140	Taylor expansion based classifier adaptation: Application to person detection	claim
413	140	Relaxed matching kernels for robust image comparison	claim
414	140	Graph cut with ordering constraints on labels and its applications	claim
415	140	Photogeometric structured light: A self-calibrating and multi-viewpoint framework for accurate 3D modeling	claim
416	139	Sensor planning for automated and persistent object tracking with multiple cameras	claim
417	138	Transductive object cutout	claim
418	138	From skeletons to bone graphs: Medial abstraction for object recognition	claim
419	137	Vital sign estimation from passive thermal video	claim
420	137	Demosaicing by smoothing along 1D features	claim
421	137	Learning based coarse-to-fine image registration	claim
422	136	High quality mesostructure acquisition using specularities	claim
423	135	Performance evaluation of state-of-the-art discrete symmetry detection algorithms	claim
424	135	Learning and using taxonomies for fast visual categorization	claim
425	135	Classifiability-based Optimal Discriminatory Projection Pursuit	claim
426	135	Visual quasi-periodicity	claim
427	134	Robust estimation of gaussian mixtures from noisy input data	claim
428	133	A recursive filter for linear systems on Riemannian manifolds	claim
429	133	Volumetric reconstruction from multi-energy single-view radiography	claim
430	132	Geo-located image analysis using latent representations	claim
431	132	Globally optimal shape-based tracking in real-time	claim
432	131	Exploiting side information in locality preserving projection	claim
433	130	Minimal solutions for generic imaging models	claim
434	130	What do color changes reveal about an outdoor scene?	claim
435	129	The scale of a texture and its application to segmentation	claim
436	127	Robust unambiguous parametrization of the essential manifold	claim
437	125	Robust higher order potentials for enforcing label consistency	claim
438	124	Interactive image matting for multiple layers	claim
439	124	What can missing correspondences tell us about 3D structure and motion?	claim
440	122	Subspace segmentation with outliers: A grassmannian approach to the maximum consensus subspace	claim
441	121	Radiometric calibration using temporal irradiance mixtures	claim
442	119	Sensing increased image resolution using aperture masks	claim
443	118	Unsupervised learning of visual taxonomies	claim
444	114	Finding trails	claim

Sciweavers

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers