ICCV 2011 - PDF Preprint Papers

ICCV 2011 IEEE International Conference on Computer Vision

3D Immersive Browsing | Click Here

Teaser Browsing | Click Here

Queue Browsing | Click Here

Title Browsing | Click Here

Wall of Fame | Most Viewed ICCV-2011 Paper

click to vote

ICCV
2011
IEEE

249views Computer Vision» more ICCV 2011»

Segmentation as Selective Search for Object Recognition

7 months 10 days ago

Download disi.unitn.it

Software available at http://disi.unitn.it/~uijlings or http://koen.me/research/ For object recognition, the current state-of-the-art is based on exhaustive search. However, to ...

K van de Sande, J Uijlings, T Gevers, A Smeulders

posted by jrruijli

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	249	Segmentation as Selective Search for Object Recognition
2	217	Fast Template Matching in Non-Linear Tone-Mapped Images
3	119	Manhattan Scene Understanding Using Monocular, Stereo, and 3D Features	claim
4	96	Outdoor Human Motion Capture using Inverse Kinematics and von Mises-Fisher Sampling
5	93	Superpixels via Pseudo-Boolean Optimization	claim
6	84	Tracking by Sampling Trackers
7	82	Edge foci interest points	claim
8	82	Object Recoloring based on Intrinsic Image Estimation	claim
9	69	DTAM: Dense Tracking and Mapping in Real-Time	claim
10	63	Home 3D Body Scans from Noisy Image and Range Data	claim
11	59	Centralized Sparse Representation for Image Restoration	claim
12	59	Dense Disparity Maps from Sparse Disparity Measurements	claim
13	58	Human Action Recognition by Learning Bases of Action Attributes and Parts	claim
14	58	Correspondence Free Registration through a Point-to-Model Distance Minimization
15	57	Latent Low-Rank Representation for Subspace Segmentation and Feature Extraction	claim
16	57	A Nonparametric Riemannian Framework on Tensor Field with Application to Foreground Segmentation	claim
17	57	End-to-end Scene Text Recognition	claim
18	55	HMDB: A Large Video Database for Human Motion Recognition	claim
19	55	Articulated Part-based Model for Joint Object Detection and Pose Estimation	claim
20	52	The NBNN kernel	claim
21	52	Scene Recognition and Weakly Supervised Object Localization with Deformable Part-Based Models	claim
22	52	Are Spatial and Global Constraints Really Necessary for Segmentation?	claim
23	52	Human Activity Prediction: Early Recognition of Ongoing Activities from Streaming Videos	claim
24	51	Object Detection and Segmentation from Joint Embedding of Parts and Pixels	claim
25	50	CARD: Compact And Real-time Descriptors	claim
26	49	3D Scene Flow Estimation with a Rigid Motion Prior	claim
27	49	Adaptive Deconvolutional Networks for Mid and High Level Feature Learning	claim
28	49	What Characterizes a Shadow Boundary under the Sun and Sky?	claim
29	48	Multi-hypothesis Motion Planning for Visual Object Tracking	claim
30	47	Hough-based Tracking of Non-Rigid Objects	claim
31	47	Fast Image-Based Localization using Direct 2D-to-3D Matching	claim
32	47	Level-Set Person Segmentation and Tracking with Multi-Region Appearance Models and Top-Down Shape Information	claim
33	46	From Contours to 3D Object Detection and Pose Estimation	claim
34	46	Learning Component-Level Sparse Representation Using Histogram Information for Image Classification	claim
35	46	Image Based Detection of Geometric Changes in Urban Environments	claim
36	46	A Data-Driven Approach for Real-Time Full Body Pose Reconstruction from a Depth Camera	claim
37	45	Complementary Hashing for Approximate Nearest Neighbor Search	claim
38	45	Fisher Discrimination Dictionary Learning for Sparse Representation	claim
39	45	Center-surround Divergence of Feature Statistics for Salient Object Detection	claim
40	44	Multimodal Templates for Real-Time Detection of Texture-less Objects in Heavily Cluttered Scenes	claim
41	44	Annotator Rationales for Visual Recognition	claim
42	44	Dynamic Manifold Warping for View Invariant Action Recognition	claim
43	44	Automatic Salient Object Extraction with Contextual Cue	claim
44	43	Birdlets: Subordinate Categorization Using Volumetric Primitives and Pose-Normalized Appearance	claim
45	43	Pushing the limits of digital imaging using Structured Illumination	claim
46	43	A Convex Framework for Image Segmentation with Moment Constraints	claim
47	43	Regression from Local Features for Viewpoint and Pose Estimation
48	42	Illumination Demultiplexing from a Single Image	claim
49	42	Scale and Object Aware Image Retargeting for Thumbnail Browsing	claim
50	42	From Learning Models of Natural Image Patches to Whole Image Restoration	claim
51	42	Delta-Dual Hierarchical Dirichlet Processes: A pragmatic abnormal behaviour detector	claim
52	42	BRISK: Binary Robust Invariant Scalable Keypoints	claim
53	42	Discriminative Figure-Centric Models for Joint Action Localization and Recognition	claim
54	42	Localized Principal Component Analysis based Curve Evolution: A Divide and Conquer Approach	claim
55	42	Simultaneous Multi-Body Stereo and Segmentation	claim
56	41	Double Window Optimisation for Constant Time Visual SLAM	claim
57	41	Fourier Active Appearance Models	claim
58	40	Domain Adaptation for Object Recognition: An Unsupervised Approach	claim
59	40	Discriminative Learning of Relaxed Hierarchy for Large-scale Visual Recognition	claim
60	40	Content-Based Photo Quality Assessment	claim
61	40	Contextual Weighting for Vocabulary Tree based Image Retrieval	claim
62	40	Who Blocks Who: Simultaneous Clothing Segmentation for Grouping Images	claim
63	39	Sparse Dictionary-based Representation and Recognition of Action Attributes	claim
64	39	Kernel Non-Rigid Structure from Motion	claim
65	39	Discovering Favorite Views of Popular Places with Iconoid Shift	claim
66	39	RECON: Scale-Adaptive Robust Estimation via Residual Consensus	claim
67	39	Feature Seeding for Action Recognition	claim
68	39	Decoupling Photometry and Geometry in Dense Variational Camera Calibration	claim
69	39	Optical Flow Estimation Using Learned Sparse Model	claim
70	39	Multiclass Recognition and Part Localization with Humans in the Loop	claim
71	39	Introducing Total Curvature for Image Processing	claim
72	39	Understanding Egocentric Activities	claim
73	39	Optimal Landmark Detection using Shape Models and Branch and Bound	claim
74	39	Automatic Construction of an Action Video Shot Database using Web Videos	claim
75	38	Informative Feature Selection for Object Recognition via Sparse PCA	claim
76	38	A New Distance for Scale-Invariant 3D Shape Recognition and Registration	claim
77	38	Data-driven Crowd Analysis in Videos	claim
78	38	Dynamic Fluid Surface Acquisition Using a Camera Array	claim
79	38	In Defense of Soft-assignment Coding	claim
80	38	Probabilistic Group-Level Motion Analysis and Scenario Recognition	claim
81	37	Decision Tree Fields	claim
82	37	Blurred Target Tracking by Blur-driven Tracker	claim
83	37	Actively Selecting Annotations Among Objects and Attributes	claim
84	37	Learning Cross-modality Similarity for Multinomial Data	claim
85	37	Diffusion Runs Low on Persistence Fast	claim
86	37	Active Scene Recognition with Vision and Language	claim
87	37	Extracting Foreground Masks towards Object Recognition	claim
88	37	Local Intensity Order Pattern for Feature Description	claim
89	37	Gaussian Process Regression Flow for Analysis of Motion Trajectories	claim
90	37	Sparse Representation or Collaborative Representation: Which Helps Face Recognition?	claim
91	37	Video Primal Sketch: A Generic Middle-Level Representation of Video	claim
92	37	Multiview 3D Warps	claim
93	36	Detailed Reconstruction of 3D Plant Root Shape	claim
94	36	Recursive MDL via Graph Cuts: Application to Segmentation	claim
95	36	Active Geodesics: Region based Active Contour Segmentation with a Global Edge based Constraint	claim
96	36	Face Reconstruction in the Wild	claim
97	36	Building a better probabilistic model of images by factorization	claim
98	36	Discovering Object Instances from Scenes of Daily Living	claim
99	35	Strong Supervision From Weak Annotation: Interactive Training of Deformable Part Models	claim
100	35	A Linear Subspace Learning Approach via Sparse Coding	claim
101	35	Visual Word Disambiguation by Semantic Contexts	claim
102	35	Conditional Random Fields for Multi-Camera Object Detection	claim
103	35	Refractive Shape from Light Field Distortion	claim
104	34	Non-stationary Correction of Optical Aberrations	claim
105	34	Gradient-based learning of higher-order image features	claim
106	34	Basis constrained 3D scene flow on a dynamic proxy	claim
107	34	Blurring-Invariant Riemannian Metrics for Comparing Signals and Images	claim
108	34	2D-3D Fusion for Layer Decomposition of Urban Facades	claim
109	34	Learning Universal Multi-view Age Estimator by Video Contexts	claim
110	34	Color Photometric Stereo for Multicolored Surfaces	claim
111	34	Optimizing Polynomial Solvers for Minimal Geometry Problems	claim
112	34	3D Reconstruction of a Smooth Articulated Trajectory from a Monocular Image Sequence	claim
113	34	Large-Scale Image Annotation using Visual Synset	claim
114	34	Realtime Multibody Visual SLAM with a Smoothly Moving Monocular Camera	claim
115	33	Source Constrained Clustering	claim
116	33	Learning Spatiotemporal Graphs of Human Activities	claim
117	33	Superpixel Tracking	claim
118	33	Fast Removal of Non-uniform Camera Shake	claim
119	33	An adaptive coupled-layer visual model for robust visual tracking	claim
120	33	Means in spaces of tree-like shapes	claim
121	33	Self-Calibrating Depth from Refraction	claim
122	32	Exemplar Extraction using Spatio-Temporal Hierarchical Agglomerative Clustering for Face Recognition in Video	claim
123	32	iGroup : Weakly supervised image and video grouping	claim
124	32	A robust pipeline for rapid feature-based pre-alignment of dense range scans	claim
125	32	Viewpoint-Aware Object Detection and Pose Estimation	claim
126	32	Generalized Subgraph Preconditioners for Large-Scale Bundle Adjustment	claim
127	32	Generalized Roof Duality for Pseudo-Boolean Optimization	claim
128	32	Image Segmentation by Figure-Ground Composition into Maximal Cliques	claim
129	32	The Power of Comparative Reasoning	claim
130	32	Key-Segments for Video Object Segmentation	claim
131	32	Stereo Time-of-Flight	claim
132	31	Maximizing All Margins: Pushing Face Recognition with Kernel Plurality	claim
133	31	Relative Attributes	claim
134	31	Simultaneous Correspondence and Non-Rigid 3D Reconstruction of the Coronary Tree from Single X-ray Images	claim
135	31	Physically-based Motion Models for 3D Tracking: A Convex Formulation	claim
136	31	Shape-constrained Gaussian Process Regression for Facial-point-based Head-pose Normalization	claim
137	31	Temporally Coded Flash Illumination for Motion Deblurring	claim
138	31	N-best maximal decoders for part models	claim
139	31	Modeling Temporal Coherence for Optical Flow	claim
140	30	Distributed Cosegmentation via Submodular Optimization on Anisotropic Diffusion	claim
141	30	Learning a Category Independent Object Detection Cascade	claim
142	30	Imaging via Three-dimensional Compressive Sampling	claim
143	30	A Theory of Coprime Blurred Pairs	claim
144	29	Revisiting Radiometric Calibration for Color Computer Vision	claim
145	29	Kinecting the dots: Particle Based Scene Flow from depth sensors	claim
146	29	Parsing Video Events with Goal inference and Intent Prediction	claim
147	29	Multi-View 3D Reconstruction for Scenes under the Refractive Plane with Known Vertical Direction	claim
148	29	Robust Topological Features for Deformation Invariant Image Matching	claim
149	28	Object Segmentation in Video: A Hierarchical Variational Approach for Turning Point Trajectories into Dense Regions	claim
150	28	The Generalized Trace-Norm and its Application to Structure-from-Motion Problems	claim
151	28	Geometrically Consistent Elastic Matching of 3D Shapes: A Linear Programming Solution	claim
152	28	Semantic Contours from Inverse Detectors	claim
153	28	Struck: Structured Output Tracking with Kernels	claim
154	28	Understanding Scenes on Many Levels	claim
155	28	Evaluation of Image Features Using a Photorealistic Virtual World	claim
156	28	Handling Outliers in Non-Blind Image Deconvolution	claim
157	28	Smooth Object Retrieval using a Bag of Boundaries	claim
158	28	Perturb-and-MAP Random Fields: Using Discrete Optimization\\to Learn and Sample from Energy Models	claim
159	28	Multiplexed Illumination for Scene Recovery in the Presence of Global Illumination	claim
160	28	Coherency Sensitive Hashing	claim
161	27	Unwrapping Low-rank Textures on Generalized Cylindrical Surfaces	claim
162	27	A String of Feature Graphs Model for Recognition of Complex Activities in Natural Videos	claim
163	27	Optimal Estimation of Vanishing Points in a Manhattan World	claim
164	27	Incremental On-line Semi-supervised Learning for Segmenting the Left Ventricle of the Heart from Ultrasound Data	claim
165	27	Segmentation from a Box	claim
166	27	Generalized Ordering Constraints for Multilabel Optimization	claim
167	27	Recognising Spontaneous Facial Micro-expressions	claim
168	27	Ask the locals: multi-way local pooling for image recognition	claim
169	26	Trajectory reconstruction from non-overlapping surveillance cameras with relative depth ordering constraints	claim
170	26	Scale Space for Central Catadioptric Systems. Towards a generic camera feature extractor.	claim
171	26	Tracking Multiple People under Global Appearance Constraints	claim
172	26	Predicting Occupation via Human Clothing and Contexts	claim
173	26	Real-time Indoor Scene Understanding using Bayesian Filtering with Motion Cues	claim
174	25	A Graph-matching Kernel for Object Categorization	claim
175	25	Inferring Social Relations from Visual Concepts	claim
176	25	HEAT: Iterative Relevance Feedback with One Million Images	claim
177	25	Automated Articulated Structure and 3D Shape Recovery from Point Correspondences	claim
178	25	Robust Object Pose Estimation via Statistical Manifold Modeling	claim
179	25	Segmentation Fusion for Connectomics	claim
180	25	The Truth about Cats and Dogs	claim
181	24	A 3D Laplacian-Driven Parametric Deformable Model	claim
182	24	Tight Convex Relaxations for Vector-Valued Labeling Problems	claim
183	23	Learning to Cluster Using High Order Graphical Models with Latent Variables	claim
184	23	Spatiotemporal Oriented Energies for Spacetime Stereo	claim
185	20	Tabula Rasa: Model Transfer for Object Category Detection	claim

Sciweavers

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers