ICCV 2009 - PDF Preprint Papers

ICCV 2009 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-2009 Paper

click to vote

ICCV
2009
IEEE

5342views Computer Vision» more ICCV 2009»

A Markov Clustering Topic Model for Mining Behaviour in Video

2 years 6 months ago

Download www.dcs.qmul.ac.uk

This paper addresses the problem of fully automated mining of public space video data. A novel Markov Clustering Topic Model (MCTM) is introduced which builds on existing Dynami...

Timothy Hospedales, Shaogang Gong, Tao Xiang

posted by tmh

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.

Click here to Browse ICCV 2009 by Program Order

Id	Views	Title	Status
1	5342	A Markov Clustering Topic Model for Mining Behaviour in Video
2	2607	Super-Resolution From a Single Image
3	2186	Tracking a Hand Manipulating an Object	claim
4	2041	Detection and Removal of Chromatic Moving Shadows in Surveillance Scenarios
5	1452	Background Subtraction for Freely Moving Cameras	claim
6	1378	Video stabilization using robust feature trajectories	claim
7	1318	Beyond the Euclidean distance: Creating effective visual codebooks using the histogram intersection kernel	claim
8	1260	Class Segmentation and Object Localization with Superpixel Neighborhoods
9	1257	Robust Tracking-by-Detection using a Detector Confidence Particle Filter
10	1253	Simultaneous Color Consistency and Depth Map Estimation for Radiometrically Varying Stereo Images
11	1241	Power watersheds: a new image segmentation framework extending graph cuts, random walker and optimal spanning forest
12	1161	Coded Aperture Pairs for Depth From Defocus
13	1150	Feature Correspondence and Deformable Object Matching via Agglomerative Correspondence Clustering
14	1098	Shift-Map Image Editing
15	1074	Packing bag-of-features	claim
16	1011	Kernel Methods for Weakly Supervised Mean Shift Clustering	claim
17	966	Superresolution Texture Maps for Multiview Reconstruction	claim
18	960	A Hand-held Photometric Stereo Camera for 3-D Modeling	claim
19	941	On Feature Combination for Multiclass Object Classification	claim
20	917	Fast Visibility Restoration from a Single Color or Gray Level Image
21	917	Fast Ray Features for Learning Irregular Shapes
22	895	Non-Local Sparse Models for Image Restoration	claim
23	863	Top-Down Color Attention for Object Recognition
24	842	Implicit Color Segmentation Features for Pedestrian Detection	claim
25	842	I know what you did last summer: object-level auto-annotation of holiday snaps	claim
26	838	Robust Visual Tracking using L1 Minimization
27	833	You'll never walk alone: modeling social behavior for multi-target tracking
28	832	Human Detection Using Partial Least Squares Analysis	claim
29	813	Texel-based Texture Segmentation	claim
30	789	Building Rome in a Day	claim
31	787	Actionable Information in Vision
32	762	Reconstructing 3D motion trajectories of particle swarms by global correspondence selection
33	761	3D Open-Surface Shape Correspondence for Statistical Shape Modeling: Identifying Topologically Consistent Landmarks
34	750	Human Pose Estimation Using Consistent Max-Covering	claim
35	733	Robust Graph-Cut Scene Segmentation and Reconstruction for Free-Viewpoint Video of Complex Dynamic Scenes	claim
36	720	LabelMe video: Building a Video Database with Human Annotations	claim
37	713	Piecewise-Consistent Color Mappings of Images Acquired Under Various Conditions
38	711	An efficient algorithm for Co-segmentation	claim
39	680	Correlated Probabilistic Trajectories for Pedestrian Motion Detection
40	679	Curvature Regularity for Region-based Image Segmentation and Inpainting: A Linear Programming Relaxation	claim
41	676	Fast and Robust Earth Mover's Distances
42	675	Compact Signatures for High-Speed Interest Point Description and Matching	claim
43	669	Illumination Aware MCMC Particle Filter for Long-Term Outdoor Multi-Object Simultaneous Tracking and Classification	claim
44	660	Effective and Efficient Interpolation for Mutual Information based Multimodality Elastic Image Registration
45	658	Learning Based Digital Matting	claim
46	654	Spectral clustering of linear subspaces for motion segmentation	claim
47	649	Decomposing a Scene into Geometric and Semantically Consistent Regions	claim
48	641	Modeling Deformable Objects from a Single Depth Camera	claim
49	629	Efficient High-Quality Image Contour Detection	claim
50	625	Poselets: Body Part Detectors Trained Using 3D Human Pose Annotations	claim
51	615	A direct approach for efficiently tracking with 3D Morphable Models
52	604	Kernelized Locality-Sensitive Hashing for Scalable Image Search	claim
53	601	Spatio-Temporal Relationship Match: Video Structure Comparison for Recognition of Complex Human Activities	claim
54	598	Recovering Planar Homographies between 2D Shapes
55	589	Combining efficient object localization and image classification	claim
56	585	Image Segmentation with A Bounding Box Prior	claim
57	581	Similarity Functions for Categorization: from Monolithic to Category Specific	claim
58	578	Joint learning of visual attributes, object classes and visual saliency	claim
59	577	Structure- and Motion-adaptive Regularization for High Accuracy Optic Flow	claim
60	570	Reconstructing Building Interiors from Images	claim
61	570	A Shape-Based Object Class Model for Knowledge Transfer	claim
62	568	Face Recognition With Contiguous Occlusion Using Markov Random Fields	claim
63	548	Multiple Kernels for Object Detection	claim
64	545	Using machine learning to predict where people look	claim
65	532	Saliency Driven Total Variation Segmentation
66	505	Sparse Representation of Cast Shadows via L1-Regularized Least Squares
67	503	Complete Multi-View Reconstruction of Dynamic Scenes from Probabilistic Fusion of Narrow and Wide Baseline Stereo
68	491	Automatic annotation of human actions in video	claim
69	489	Large Displacement Optical Flow Computation without Warping	claim
70	486	An Algorithm for Minimizing the Piecewise Smooth Mumford-Shah Functional	claim
71	479	Light Field Video Stabilization	claim
72	477	Activity Recognition using the velocity histories of tracked keypoints	claim
73	475	Wide-Baseline Image Matching Using Line Signatures	claim
74	456	Tensor completion for estimating missing values in visual data	claim
75	455	A Theory of Active Object Localization	claim
76	452	3D reconstruction from image collections with a single known focal length	claim
77	448	Tracking in Unstructured Crowded Scenes	claim
78	446	Active Skeleton for Non-rigid Object Detection	claim
79	444	Mode-Detection via Median-Shift	claim
80	440	Finding Good Composition in Panoramic Scenes	claim
81	439	Absolute Scale in Structure from Motion from a Single Vehicle Mounted Camera by Exploiting Nonholonomic Constraints	claim
82	436	Higher-Order Gradient Descent by Fusion-Move Graph Cut	claim
83	433	Sparsity Induced Similarity Measure for Label Propagation
84	425	Detection of Human Actions From A Single Example
85	423	Level Set Segmentation with Both Shape and Intensity Priors	claim
86	419	Recovering the Spatial Layout of Cluttered Rooms	claim
87	404	Video Scene Understanding Using Multi-scale Analysis
88	402	Seeing 3D Objects in a Single 2D Image	claim
89	402	Segmentation and Shading Estimation in Slowly Changing Textured Images	claim
90	399	Ground truth dataset and baseline evaluations for intrinsic image algorithms	claim
91	390	Diagram Techniques for Multiple View Geometry	claim
92	385	Efficient Privacy Preserving Video Surveillance	claim
93	370	Learning a dense multi-view representation for detection, viewpoint classification and synthesis of object categories	claim
94	367	Modelling Activity Global Temporal Dependencies using Time Delayed Probabilistic Graphical Model
95	358	Image Sequence Geolocation with Human Travel Priors	claim
96	357	Recognizing Actions by Shape-Motion Prototype Trees	claim
97	354	Boundary Ownership by Lifting to 2.5D	claim
98	347	Max-Margin Additive Classifiers for Detection	claim
99	341	Multi-Scale Object Detection by Clustering Lines	claim
100	337	Detecting Interpretable and Accurate Scale-Invariant keypoints	claim
101	337	Factorizing Scene Albedo and Depth from a Single Foggy Image	claim
102	336	Detecting Objects in Large Image Collections and Videos by Efficient Subimage Retrieval	claim
103	335	An Algebraic Approach to Affine Registration of Point Sets	claim
104	330	Scene Shape Priors for Superpixel Segmentation	claim
105	318	Scale Invariance and Noise in Natural Images
106	310	Image Saliency by Isocentric Curvedness and Color
107	306	Feature-Centric Efficient Subwindow Search	claim
108	299	Action Detection in Complex Scenes with Spatial and Temporal Ambiguities	claim
109	296	Multiperspective Stereo Matching and Volumetric Reconstruction
110	293	A Riemannian Analysis of 3D Nose Shapes For Partial Human Biometrics	claim
111	287	Time Series Prediction by Chaotic Modeling of Nonlinear Dynamical Systems	claim
112	286	Seeing through water: Image restoration using model-based tracking	claim
113	286	Super-Resolution from a Single Image	claim
114	280	Semi-Supervised Random Forests
115	274	TagProp: Discriminative Metric Learning in Nearest Neighbor Models for Image Auto-Annotation
116	272	What is the Best Multi-Stage Architecture for Object Recognition?	claim
117	267	Keyframe-Based Real-Time Camera Tracking	claim
118	267	Context by Region Ancestry	claim
119	266	Least-Squares Congealing for Large Numbers of Images
120	262	Patch based Within-Object Classification	claim
121	259	Globally Optimal Affine Epipolar Geometry from Apparent Contours	claim
122	255	Subspace Constrained Mean-Shift
123	253	The One-Shot Similarity Kernel	claim
124	251	Shape Guided Contour Grouping with Particle Filters
125	249	Estimating Natural Illumination from a Single Outdoor Image	claim
126	248	The Self-Aware Matching Measure for Stereo	claim
127	248	Scene Categorization from Low Definition Video	claim
128	247	Convex Multi-Region Segmentation on Manifolds	claim
129	247	Unsupervised Face Alignment by Robust Nonrigid Mapping	claim
130	243	Piecewise Planar Stereo for Image-based Rendering
131	243	Image Restoration using Online Photo Collections	claim
132	242	Non-Negative Matrix Factorization of Partial Track Data for Motion Segmentation	claim
133	240	Deformable Model Fitting with a Mixture of Local Experts
134	239	Convex Optimization for Multi-Class Image Labeling with a Novel Family of Total Variation Based Regularizers	claim
135	234	Radiometric Compensation using Stratified Inverses
136	233	Moving in Stereo: Efficient Structure and Motion Using Lines	claim
137	230	Static Multi-Camera Factorization Using Rigid Motion
138	228	Is a detector only good for detection?	claim
139	224	Active Appearance Models with Rotation Invariant Kernels	claim
140	220	Shape-based Recognition of 3D Point Clouds in Urban Environments	claim
141	218	Template-Free Monocular Reconstruction of Deformable Surfaces	claim
142	218	Time-Constrained Photography	claim
143	218	Stabilizing Motion Tracking Using Retrieved Motion Priors	claim
144	216	A Latent Model of Discriminative Aspect	claim
145	215	Learning Actions From the Web	claim
146	214	The Swap and Expansion Moves Revisited and Fused
147	211	Efficient subset selection based on the Renyi entropy	claim
148	211	Color Constancy using 3D Scene Geometry	claim
149	210	Directional Statistics BRDF Model	claim
150	209	A Robust Elastic and Partial Matching Metric for Face Recognition	claim
151	208	Dimensionality Reduction and Principal Surfaces via Kernel Map Manifolds	claim
152	204	A linear formulation of shape from specular flow	claim
153	203	Robust Fitting of Multiple Structures: The Statistical Learning Approach	claim
154	202	FLoSS: Facility Location for Subspace Segmentation	claim
155	202	Label Set Perturbation for MRF based Neuroimaging Segmentation	claim
156	202	Learning Pedestrian Dynamics from the Real World	claim
157	200	Beyond Connecting the Dots: A Polynomial-time Algorithm for Segmentation and Boundary Estimation with Imprecise User Input	claim
158	198	Joint Pose Estimator and Feature Learning for Object Detection
159	196	Learning Deformable Action Templates from Crowded Videos	claim
160	195	Is that you? Metric Learning Approaches for Face Identification
161	193	Weakly supervised discriminative localization and classification: a joint learning process	claim
162	193	Constrained Clustering by Spectral Kernel Learning	claim
163	192	Estimating Contact Dynamics	claim
164	187	Evaluating Information Contributions of Bottom-up and Top-down Processes	claim
165	186	Adaptive Fragments-Based Tracking of Non-Rigid Objects Using Level Sets	claim
166	185	Is Dual Linear Self-Calibration Artificially Ambiguous?	claim
167	182	Shadow cameras: Reciprocal views from illumination masks	claim
168	177	Subspace matching: Unique solutions to point matching with geometric constraints	claim
169	177	Quantifying Contextual Information for Object Detection	claim
170	177	Unlabeled data improves word prediction	claim
171	177	Joint optimization of segmentation and appearance models	claim
172	175	Multimodal Partial Estimates Fusion	claim
173	174	Domain Adaptive Semantic Diffusion for Large Scale Context-Based Video Annotation	claim
174	173	Multiscale Symmetric Part Detection and Grouping	claim
175	173	Efficient Discriminative Learning of Parts-based Models	claim
176	166	Filter Flow	claim
177	165	Heterogeneous Feature Machines for Visual Recognition	claim
178	164	Optimal Correspondences from Pairwise Constraints	claim
179	163	Bayesian selection of scaling laws for motion modeling in images	claim
180	163	The Dimensionality of Scene Appearance	claim
181	163	Semi-automatic stereo extraction from video footage	claim
182	162	Optimizing Parametric Total Variation Models	claim
183	160	GroupSAC: Efficient Consensus in the Presence of Groupings	claim
184	157	A Global Perspective on MAP Inference for Low-Level Vision	claim
185	153	Body-Relative Navigation Guidance Using Uncalibrated Cameras	claim
186	152	Extending Continuous Cuts: Anisotropic Metrics and Expansion Moves	claim
187	146	Which Faces to Tag: Adding Prior Constraints into Active Learning	claim
188	145	A Probabilistic Framework for Partial Intrinsic Symmetries in Geometric Data	claim
189	132	Modeling 3D human poses from uncalibrated monocular images	claim
190	126	SURF Tracking	claim
191	123	Real-time visual tracking via Incremental Covariance Tensor Learning	claim
192	123	An HOG-LBP human detector with partial occlusion handling	claim
193	118	Dense 3D reconstruction method using a single pattern for fast moving object	claim
194	117	Efficient human pose estimation via parsing a tree structure based human model	claim
195	115	Efficient indexing for large scale visual search	claim
196	111	Storyboard sketches for Content Based Video Retrieval	claim
197	110	Segmentation, ordering and multi-object tracking using graphical models	claim
198	109	Active segmentation with fixation	claim
199	108	Globally optimal segmentation of multi-region objects	claim
200	106	Fast realistic multi-action recognition using mined dense spatio-temporal features	claim
201	104	BLOGS: Balanced local and global search for non-degenerate two view epipolar geometry	claim
202	103	A novel approach to expression recognition from non-frontal face images	claim
203	103	Video object segmentation by tracking regions	claim
204	103	A multi-sample, multi-tree approach to bag-of-words image representation for image retrieval	claim
205	103	Building recognition using sketch-based representations and spectral graph matching	claim
206	102	On optimizing subspaces for face recognition	claim
207	101	Selection and context for action recognition	claim
208	101	Learning image similarity from Flickr groups using Stochastic Intersection Kernel MAchines	claim
209	100	An algebraic model for fast corner detection	claim
210	99	Structural SVM for visual localization and continuous state estimation	claim
211	97	Incremental Multiple Kernel Learning for object recognition	claim
212	97	Group-sensitive multiple kernel learning for object categorization	claim
213	96	Incremental action recognition using feature-tree
214	95	A robust boosting tracker with minimum error bound in a co-training framework	claim
215	95	Bayesian Poisson regression for crowd counting	claim
216	95	Realtime background subtraction from dynamic scenes	claim
217	95	An algorithm for minimizing the Mumford-Shah functional	claim
218	95	Looking around the corner using transient imaging	claim
219	94	Non-Euclidean image-adaptive Radial Basis Functions for 3D interactive segmentation	claim
220	94	A study on automatic age estimation using a large database	claim
221	94	Local Trinary Patterns for human action recognition	claim
222	94	Analysis of orientation and scale in smoothly varying textures	claim
223	94	Learning to predict where humans look	claim
224	93	Improving accuracy of geometric parameter estimation using projected score method	claim
225	93	Estimating human shape and pose from a single image	claim
226	93	SCRAMSAC: Improving RANSAC's efficiency with a spatial consistency filter	claim
227	91	Efficient multi-label ranking for multi-class learning: Application to object recognition	claim
228	91	Structure and kinematics triangulation with a rolling shutter stereo rig	claim
229	91	Attached shadow coding: Estimating surface normals from shadows under unknown reflectance and lighting conditions	claim
230	90	Tracking a large number of objects from multiple views	claim
231	90	Jointly estimating demographics and height with a calibrated camera
232	90	Large-scale privacy protection in Google Street View	claim
233	90	Learning with dynamic group sparsity	claim
234	89	Shape analysis with multivariate tensor-based morphometry and holomorphic differentials	claim
235	89	Landmark classification in large-scale image collections	claim
236	89	Exploiting uncertainty in random sample consensus	claim
237	88	Associative hierarchical CRFs for object class image segmentation	claim
238	88	Kernel map compression using generalized radial basis functions	claim
239	88	Attribute and simile classifiers for face verification	claim
240	87	Video scene categorization by 3D hierarchical histogram matching	claim
241	87	Complex volume and pose tracking with probabilistic dynamical models and visual hull constraints	claim
242	86	High-resolution shape reconstruction from multiple range images based on simultaneous estimation of surface and motion	claim
243	86	Robust facial feature tracking using selected multi-resolution linear predictors	claim
244	86	Face alignment through subspace constrained mean-shifts	claim
245	86	Component analysis approach to estimation of tissue intensity distributions of 3D images	claim
246	86	Local distance functions: A taxonomy, new algorithms, and an evaluation	claim
247	85	Constructing implicit 3D shape models for pose estimation	claim
248	85	Matching as a non-cooperative game	claim
249	84	Studying brain morphometry using conformal equivalence class	claim
250	83	Non-iterative approach for fast and accurate vanishing point detection	claim
251	82	Consensus set maximization with guaranteed global optimality for robust geometry estimation	claim
252	82	Unsupervised learning of high-order structural semantics from images	claim
253	81	Probabilistic occlusion boundary detection on spatio-temporal lattices	claim
254	80	Simultaneous camera pose and correspondence estimation in cornerless images	claim
255	79	A hybrid generative/discriminative classification framework based on free-energy terms	claim
256	79	The Normalized Subspace Inclusion: Robust clustering of motion subspaces	claim
257	79	A framework for visual saliency detection with applications to image thumbnailing	claim
258	79	A prism-based system for multispectral video acquisition	claim
259	79	Simultaneous photometric invariance and shape recovery	claim
260	78	Quasi-periodic event analysis for social game retrieval	claim
261	77	Stereo from flickering caustics	claim
262	76	Simultaneous alignment and clustering for an image ensemble	claim
263	76	Single view reconstruction using shape grammars for urban environments	claim
264	76	Minimizing energy functions on 4-connected lattices using elimination	claim
265	73	Non-rigid object localization and segmentation using eigenspace representation	claim
266	72	Robust dynamical model for simultaneous registration and segmentation in a variational framework: A Bayesian approach	claim
267	70	Image annotation using multi-label correlated Green's function	claim

Sciweavers

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers