ICIP 2010 - PDF Preprint Papers

ICIP 2010 International Conference on Image Processing

3D Immersive Browsing | Click Here

Teaser Browsing | Click Here

Queue Browsing | Click Here

Title Browsing | Click Here

Wall of Fame | Most Viewed ICIP-2010 Paper

click to vote

ICIP
2010
IEEE

520views Image Processing» more ICIP 2010»

Saliency detection using maximum symmetric surround

13 years 9 months ago

Download infoscience.epfl.ch

Detection of visually salient image regions is useful for applications like object segmentation, adaptive compression, and object recognition. Recently, full-resolution salient ma...

Radhakrishna Achanta, Sabine Süsstrunk

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	520	Saliency detection using maximum symmetric surround	claim
2	430	Real-time content-aware image resizing using reduced linear model
3	341	A fast accurate implicit polynomial fitting approach
4	337	Metaface learning for sparse representation based face recognition	claim
5	326	Stationary foreground detection using background subtraction and temporal difference in video surveillance	claim
6	323	Spiral FFT: An efficient method for 3-D FFTS on spiral MRI contours	claim
7	312	Compact visual codebook for action recognition	claim
8	307	Fast object detection using boosted co-occurrence histograms of oriented gradients	claim
9	305	Fast geometric re-ranking for image-based retrieval	claim
10	299	Fast l1-minimization algorithms and an application in robust face recognition: A review	claim
11	298	3D vertebrae segmentation using graph cuts with shape prior constraints	claim
12	298	Security analysis for privacy preserving search of multimedia	claim
13	296	Rotation invariant texture classification using adaptive LBP with directional statistical features	claim
14	288	Face-TLD: Tracking-Learning-Detection applied to faces	claim
15	288	Rotating sensor-matrix camera calibration	claim
16	286	People identification using shadow dynamics	claim
17	278	3D video formats and coding methods	claim
18	277	Spread spectrum-based watermarking for Tardos code-based fingerprinting for H.264/AVC video	claim
19	274	Undetectable image tampering through JPEG compression anti-forensics	claim
20	274	Entropies and cross-entropies of exponential families	claim
21	273	Bit-plane stack filter algorithm for focal plane processors	claim
22	272	Comparison of local feature descriptors for mobile visual search	claim
23	270	Earth Mover Distance on superpixels
24	266	Exemplar-Based EM-like image denoising via manifold reconstruction	claim
25	263	Bacteria Filters: Persistent Particle Filters for Background Subtraction
26	260	Joint decoding of stereo JPEG image Pairs	claim
27	258	Human age estimation using enhanced bio-inspired features (EBIF)	claim
28	255	Frame compatible formats for 3D video distribution	claim
29	255	Temporal pooling of video quality estimates using perceptual motion models	claim
30	253	Texture classification via patch-based sparse texton learning	claim
31	250	Building Emerging Pattern (EP) Random forest for recognition	claim
32	249	Single image deblurring with adaptive dictionary learning	claim
33	249	Combining free energy score spaces with information theoretic kernels: Application to scene classification	claim
34	249	A fast Multilinear ICA algorithm	claim
35	248	Font retrieval on a large scale: An experimental study	claim
36	244	Hierarchical multiscale LBP for face and palmprint recognition	claim
37	240	Estimation of linear deformations of 3D objects
38	240	Anisotropic diffusion-based detail-preserving smoothing for image restoration	claim
39	239	Real-time 3D reconstruction and pose estimation for human motion analysis	claim
40	238	Non-rigid image registration by using graph-cuts with mutual information	claim
41	237	A view-dependent adaptivity metric for real time mesh tessellation	claim
42	235	Compressed sensing of multiview images using disparity compensation	claim
43	232	Characterization of signal perturbation using voting based curve fitting for multispectral images
44	232	Robust and efficient background subtraction by quadratic polynomial fitting	claim
45	231	Natural image matting for multiple wide-baseline views	claim
46	231	Blind invisible watermarking for 3D meshes with textures	claim
47	231	Improving histology images segmentation through spatial constraints and supervision	claim
48	231	Object detection and segmentation on a hierarchical region-based image representation	claim
49	230	Gradient field descriptor for sketch based retrieval and localization	claim
50	229	Improving subpixel stereo matching with segment evolution	claim
51	228	Dynamic selection of a feature-rich query frame for mobile video retrieval	claim
52	228	MVMP: Multi-view Matching Pursuit with geometry constraints	claim
53	228	A two-stage framework for blind image quality assessment	claim
54	227	Robust object detection scheme using feature selection	claim
55	227	Video retargeting: A visual-friendly dynamic programming approach	claim
56	227	Automatic target recognition based on simultaneous sparse representation	claim
57	225	Multi-label propagation for coherent video segmentation and artistic stylization	claim
58	224	Intra frame coding with template matching prediction and adaptive transform	claim
59	223	3D augmented Markov random field for object recognition	claim
60	222	Enhanced prediction for motion estimation in Scalable Video Coding	claim
61	222	Bayesian regularization of diffusion tensor images using hierarchical MCMC and loopy belief propagation	claim
62	222	Comparison of merging orders and pruning strategies for Binary Partition Tree in hyperspectral data	claim
63	222	Multi-stream partitioning and parity rate allocation for scalable IPTV delivery	claim
64	221	Correlation histogram analysis of depth-enhanced 3D video coding	claim
65	220	Multiframe blind deconvolution, super-resolution, and saturation correction via incremental EM	claim
66	218	Stereoscopic content production of complex dynamic scenes using a wide-baseline monoscopic camera set-up	claim
67	218	RFSIM: A feature based image quality assessment metric using Riesz transforms	claim
68	218	ESUR: A system for Events detection in SURveillance video	claim
69	217	Objective assessment of tone mapping algorithms	claim
70	216	Two-dimensional statistical test for the presence of almost cyclostationarity on images	claim
71	216	Photometric stereo under unknown light sources using robust SVD with missing data	claim
72	215	Image partitioning with kernel mapping and graph cuts	claim
73	214	Image modeling and enhancement via structured sparse model selection	claim
74	214	Fast semantic scene segmentation with conditional random field	claim
75	214	Shape from shading for hybrid surfaces as applied to tooth reconstruction	claim
76	214	Total subset variation prior	claim
77	214	A close-up detection method for movies	claim
78	214	Edge-adaptive image segmentation based on seam processing and K-Means clustering	claim
79	213	Matching of interest point groups with pairwise spatial constraints	claim
80	212	Evaluation of on-line quality estimators for object tracking	claim
81	210	Compressed domain global motion estimation using the Helmholtz Tradeoff Estimator	claim
82	209	Reduced-reference SSIM estimation	claim
83	209	A cascaded hierarchical framework for moving object detection and tracking	claim
84	209	A novel method for generation of motion saliency	claim
85	209	Restoration of images and 3D data to higher resolution by deconvolution with sparsity regularization	claim
86	209	Image retrieval with feature selection and relevance feedback	claim
87	208	Enhancing low light images using near infrared flash images	claim
88	207	Auction protocol for camera active control	claim
89	207	A classifier based approach for the detection of potential threats in CT based Baggage Screening	claim
90	207	Towards computational models of kinship verification	claim
91	206	3D video performance segmentation	claim
92	205	Poisson NL means: Unsupervised non local means for Poisson noise	claim
93	205	Randomized motion estimation
94	205	OmniSIFT: Scale invariant features in omnidirectional images	claim
95	205	A novel V-line Radon transform and its imaging applications	claim
96	205	Morphological wavelet transform with adaptive dyadic structures	claim
97	204	Barcode-based calibration of a 1-D blur restoration pipeline	claim
98	203	Constructing a sparse convolution matrix for shift varying image restoration problems	claim
99	203	Automatic production of personalized basketball video summaries from multi-sensored data	claim
100	202	FTV (Free-viewpoint TV)	claim
101	202	Palmprint recognition using rank level fusion	claim
102	202	Motion-blur-free exposure fusion	claim
103	202	Optimal exposure control for high dynamic range imaging	claim
104	201	Fast pedestrian detection with multi-scale orientation features and two-stage classifiers	claim
105	201	A game theoretical approach for image denoising	claim
106	201	P2P group communication using Scalable Video Coding	claim
107	201	High quality scanned book compression using pattern matching	claim
108	201	Video stylization by single image example	claim
109	200	Super-resolution for multiview images using depth information	claim
110	200	Adaptive blotches detection for film restoration	claim
111	199	Curvature analysis of pattern transformation manifolds	claim
112	199	Saliency detection based on short-term sparse representation	claim
113	198	Adaptive motion model selection using a cubic spline based estimation framework	claim
114	198	Invisible light: Using infrared for video conference relighting	claim
115	198	Generalized YUV interpolation of CFA images	claim
116	198	Filterbank-based universal demosaicking	claim
117	197	Reducing graphs in graph cut segmentation	claim
118	197	Multi-spectral image analysis for skin pigmentation classification	claim
119	197	An automated vertebra identification and segmentation in CT images	claim
120	196	Consistent optical flow for stereo video	claim
121	196	Monocular Extraction of 2.1D Sketch	claim
122	196	2000-fps multi-object extraction based on cell-based labeling	claim
123	195	An adaptive clustering and chrominance-based merging approach for image segmentation and abstraction	claim
124	195	Affine-invariant modeling of shape-appearance images applied on sign language handshape classification	claim
125	195	Ball event recognition using hmm for automatic tennis annotation	claim
126	195	Discarding moving objects in quasi-simultaneous stereovision	claim
127	195	Rapid stereo-vision enhanced face recognition	claim
128	195	Anisotropic diffusion using power watersheds	claim
129	195	A fourth order dual method for staircase reduction in texture extraction and image restoration problems	claim
130	193	Sectional image reconstruction in optical scanning holography using compressed sensing	claim
131	193	Fast bilateral filtering by adapting block size	claim
132	193	Semi-automatic motion based segmentation using long term motion trajectories	claim
133	192	Video anomaly detection in spatiotemporal context	claim
134	192	A hybrid fusion method of fingerprint identification for high security applications	claim
135	192	Direction-adaptive transforms for coding prediction residuals	claim
136	192	Performance impact of ordinal ranking on content fingerprinting	claim
137	192	Fast traumatic brain injury CT slice indexing via anatomical feature classification	claim
138	192	Wavelet-based image compression anti-forensics	claim
139	191	Patch-based reconstruction and rendering of human heads	claim
140	190	Joint color decrosstalk and demosaicking for CFA cameras	claim
141	190	Multiplexed clustered-dot halftone watermarks using bi-directional phase modulation and detection	claim
142	190	Tone mapping HDR images using optimization: A general framework	claim
143	190	Rotation robust detection of copy-move forgery	claim
144	190	Multi-description of local interest point for partial-duplicate image retrieval	claim
145	189	Image analysis with regularized Laplacian eigenmaps	claim
146	189	Robust segmentation of lung tissue in chest CT scanning	claim
147	189	Multi-view object and human body part detection utilizing 3D scene information	claim
148	188	A two-pass random forests classification of airborne lidar and image data on urban scenes	claim
149	188	A simple, fast and efficient approach to denoisaicking: Joint demosaicking and denoising	claim
150	188	Recent advances in high dynamic range imaging technology	claim
151	188	Accelerated video encoding using render context information	claim
152	188	Histogram of confidences for person detection	claim
153	187	Disparity and normal estimation through alternating maximization	claim
154	186	View synthesis based on Conditional Random Fields and graph cuts	claim
155	186	Subjective study on compressed asymmetric stereoscopic video	claim
156	186	Video categorization using object of interest detection	claim
157	185	A dynamic threshold approach for skin segmentation in color images	claim
158	185	Transferable Belief Model for hair mask segmentation	claim
159	184	Fast and robust active contours for image segmentation	claim
160	184	Learning simple texture discrimination filters	claim
161	184	Complexity-scalable H.264/AVC in an IPP-based video encoder	claim
162	183	Interactive graph cut segmentation of touching neuronal structures from electron micrographs	claim
163	183	Fast and correspondence-less camera motion estimation based on voting mechanism and morton codes	claim
164	183	Decoding positional and color information from a coded pattern	claim
165	183	Multimedia forensic hash based on visual words	claim
166	183	Compressed sensing for aperture synthesis imaging	claim
167	183	Video retargeting with nonlinear spatial-temporal saliency fusion	claim
168	182	A comparative study on quality assessment of high resolution fingerprint images	claim
169	182	Evolutionary games for cooperative P2P video streaming	claim
170	181	An aliasing detection algorithm based on suspicious colocalizations of Fourier coefficients	claim
171	181	Explore multiple clues for urban images matching	claim
172	181	Distance-based weighted prediction for Adaptive Intra Mode Bit Skip in H.264/AVC	claim
173	181	Using Adaboost on contourlet based image deblurring for Fluid Lens Camera Systems	claim
174	180	A no-reference image content metric and its application to denoising	claim
175	180	Spatial bayesian surprise for image saliency and quality assessment	claim
176	179	Deterministic structured network coding for WWAN video broadcast with cooperative peer-to-peer repair	claim
177	179	Objective quality analysis for free-viewpoint DIBR	claim
178	179	The 2D orientation is unique through principal moments analysis	claim
179	179	Probing the local-feature space of interest points	claim
180	178	Rate-distortion based reconstruction optimization in distributed source coding for interactive multiview video streaming	claim
181	178	Multimodal template matching based on gradient and mutual information using scale-space	claim
182	178	Global motion temporal filtering for in-loop deblocking	claim
183	178	Polyconvexification of the multi-label optical flow problem	claim
184	177	Poisson image reconstruction with total variation regularization	claim
185	177	Distributed classification of multiple observations by consensus	claim
186	177	Quantization optimized H.264 encoding for traffic video tracking applications	claim
187	177	Implicit Motion-Shape Model: A generic approach for action matching	claim
188	176	Learning image similarities via Probabilistic Feature Matching	claim
189	176	From patches to pixels in Non-Local methods: Weighted-average reprojection	claim
190	176	GAME-theory-based cross-layer optimization for wireless DS-CDMA visual sensor networks	claim
191	175	Dual Range Deringing for non-blind image deconvolution	claim
192	175	Towards high-precision lens distortion correction	claim
193	175	Joint Sparsity Model with Matrix Completion for an ensemble of face images	claim
194	175	Spatio-temporal combination of saliency maps and eye-tracking assessment of different strategies	claim
195	175	Resolving distortion between linear and area sensors for forensic print inspection	claim
196	174	A new subspace learning method in Fourier domain for texture classification	claim
197	174	Maximizing intra-individual correlations for illumination-insensitive face recognition	claim
198	174	Hyper-DEMIX: Blind source separation of hyperspectral images using local ML estimates	claim
199	173	Human action recognition using the motion of interest points	claim
200	173	Detecting photo manipulation on signs and billboards	claim
201	173	Local two-channel critically sampled filter-banks on graphs	claim
202	173	Patch confidence k-nearest neighbors denoising	claim
203	173	Occlusion handling based on support and decision	claim
204	172	Gradient projection for linearly constrained convex optimization in sparse signal recovery	claim
205	172	A split Bregman method for non-negative sparsity penalized least squares with applications to hyperspectral demixing	claim
206	172	On the role of differentiation for resampling detection	claim
207	172	Classification and feature selection with human performance data	claim
208	172	In-loop denoising of reference frames for lossless coding of noisy image sequences	claim
209	172	Gaussian mixture models for spots in microscopy using a new split/merge em algorithm	claim
210	172	Snakules: Snakes that seek spicules on mammography	claim
211	171	A variational multiphase level set approach to simultaneous segmentation and bias correction	claim
212	171	Multiview image compression using a layer-based representation	claim
213	171	New view synthesis for stereo cinema by hybrid disparity remapping	claim
214	170	Mixed-resolution distributed video codec without motion estimation at the encoder	claim
215	170	Transform-domain temporal prediction in video coding: Exploiting correlation variation across coefficients	claim
216	170	An integer programming approach to visual compliance	claim
217	170	Functional vanishing point estimation via a filtered-Radon operator	claim
218	170	Tensor-based image diffusions derived from generalizations of the Total Variation and Beltrami Functionals	claim
219	170	A concave cost formulation for parametric curve fitting: Detection of leukocytes from intravital microscopy images	claim
220	170	Instrument parameter estimation in bayesian convex deconvolution	claim
221	170	Plenoptic based super-resolution for omnidirectional image sequences	claim
222	169	Geometrical features for the classification of very high resolution multispectral remote-sensing images	claim
223	169	Detecting multiple copies in tampered images	claim
224	169	Network of evolutionary binary classifiers for classification and retrieval in macroinvertebrate databases	claim
225	168	A class-separability-based method for multi/hyperspectral image color visualization	claim
226	168	Example-based image compression	claim
227	168	Sparse shapes prototype modeling using genetic algorithms	claim
228	168	Robust decoding of a 3D-ESCOT bitstream transmitted over a noisy channel	claim
229	167	Distributed joint source-channel arithmetic coding	claim
230	167	Virtual jewel rendering for augmented reality environments	claim
231	167	Real-time interactive multi-target tracking using kernel-based trackers	claim
232	167	Comparison of registration methods using mamographic images	claim
233	166	Learning denoising bounds for noisy images	claim
234	166	Hyperspectral image segmentation and unmixing using hidden Markov trees	claim
235	165	A sparsity-distortion-optimized multiscale representation of geometry	claim
236	165	Acquiring shaking-free route panorama by stationary blurring	claim
237	165	Towards unifying diffusion and exemplar-based inpainting	claim
238	164	Detecting pitching frames in baseball game video using Markov random walk	claim
239	164	Stochastic gradient descent for robust inverse photomask synthesis in optical lithography	claim
240	163	Geometric averaging of X-ray signals in automatic exposure control	claim
241	163	Surgical needle reconstruction using small-angle multi-view X-ray	claim
242	162	Level lines shortening yields an image curvature microscope	claim
243	162	An improved content-adaptive mesh-generation method for image representation	claim
244	161	A no-reference Blocking Artifacts Visibility Estimator in images	claim
245	161	Position dependent linear intra prediction for image coding	claim
246	160	Robust interactive image segmentation with automatic boundary refinement	claim
247	160	Temporal synchronization in stereoscopic video: Influence on quality of experience and automatic asynchrony detection	claim
248	159	Natural DCT statistics approach to no-reference image quality assessment	claim
249	159	Visual saliency as sequential eye fixation probability	claim
250	157	An adaptive approach for overlapping people tracking based on foreground silhouettes	claim
251	157	Image recognition using maximal cliques of interest points	claim
252	157	On the use of feature tracks for dynamic concept detection in video	claim
253	156	Sampling-aware polar descriptors on the sphere	claim
254	155	Collaborative particle filters for group tracking	claim
255	155	Preattentive co-saliency detection	claim
256	154	Dual-tree wavelets for estimation of locally varying and anisotropic fractal dimension	claim
257	152	Pyramidal segmentation using higher-order local auto-correlations and its applications to Landsat forestry data	claim
258	151	Semi-supervised regression with temporal image sequences	claim
259	151	Probabilistic human pose recovery from 2D images	claim
260	150	Streaming Compressive Sensing for high-speed periodic videos	claim
261	150	Patch-based compression for Time-Varying Meshes	claim
262	149	A supervised micro-calcification detection approach in digitised mammograms	claim
263	149	Estimation-theoretic approach to delayed prediction in scalable video coding	claim
264	149	A scalable multi-view audiovisual entertainment framework with content-aware distribution	claim
265	149	Laplacian based structure-aware error diffusion	claim
266	148	A non-stationary Hidden Markov Model of multiview video traffic	claim
267	148	Statistical modeling of the lung nodules in low dose computed tomography scans of the chest	claim
268	143	A robust framework for region based video object segmentation	claim
269	142	Learning local pixel structure for face hallucination	claim
270	141	Scanner identification using spectral noise in the frequency domain	claim
271	137	Randomly driven fuzzy key extraction of unclonable images	claim
272	135	Passive imaging exploiting multiple scattering using distributed apertures	claim
273	130	Undecimated haar thresholding for poisson intensity estimation	claim
274	129	Image quantization under spatial smoothness constraints	claim

Sciweavers

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers