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

6637views Computer Vision» more ICCV 2009»

A Markov Clustering Topic Model for Mining Behaviour in Video

15 years 4 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	6637	A Markov Clustering Topic Model for Mining Behaviour in Video
2	3893	Super-Resolution From a Single Image
3	3167	Tracking a Hand Manipulating an Object	claim
4	3166	Detection and Removal of Chromatic Moving Shadows in Surveillance Scenarios
5	2301	Class Segmentation and Object Localization with Superpixel Neighborhoods
6	2205	Video stabilization using robust feature trajectories	claim
7	2171	Fast Visibility Restoration from a Single Color or Gray Level Image
8	2061	Background Subtraction for Freely Moving Cameras	claim
9	2030	Robust Tracking-by-Detection using a Detector Confidence Particle Filter
10	1957	Robust Visual Tracking using L1 Minimization
11	1849	Simultaneous Color Consistency and Depth Map Estimation for Radiometrically Varying Stereo Images
12	1824	Beyond the Euclidean distance: Creating effective visual codebooks using the histogram intersection kernel	claim
13	1821	Feature Correspondence and Deformable Object Matching via Agglomerative Correspondence Clustering
14	1735	Coded Aperture Pairs for Depth From Defocus
15	1714	Power watersheds: a new image segmentation framework extending graph cuts, random walker and optimal spanning forest
16	1655	Shift-Map Image Editing
17	1611	Packing bag-of-features	claim
18	1556	Kernel Methods for Weakly Supervised Mean Shift Clustering	claim
19	1520	A Hand-held Photometric Stereo Camera for 3-D Modeling	claim
20	1434	Texel-based Texture Segmentation	claim
21	1425	Fast Ray Features for Learning Irregular Shapes
22	1419	On Feature Combination for Multiclass Object Classification	claim
23	1407	Superresolution Texture Maps for Multiview Reconstruction	claim
24	1363	Human Detection Using Partial Least Squares Analysis	claim
25	1335	Top-Down Color Attention for Object Recognition
26	1331	I know what you did last summer: object-level auto-annotation of holiday snaps	claim
27	1318	Non-Local Sparse Models for Image Restoration	claim
28	1297	Effective and Efficient Interpolation for Mutual Information based Multimodality Elastic Image Registration
29	1265	Reconstructing 3D motion trajectories of particle swarms by global correspondence selection
30	1234	Human Pose Estimation Using Consistent Max-Covering	claim
31	1198	Implicit Color Segmentation Features for Pedestrian Detection	claim
32	1191	3D Open-Surface Shape Correspondence for Statistical Shape Modeling: Identifying Topologically Consistent Landmarks
33	1190	You'll never walk alone: modeling social behavior for multi-target tracking
34	1188	Actionable Information in Vision
35	1184	Learning Based Digital Matting	claim
36	1176	Building Rome in a Day	claim
37	1136	Robust Graph-Cut Scene Segmentation and Reconstruction for Free-Viewpoint Video of Complex Dynamic Scenes	claim
38	1119	Spectral clustering of linear subspaces for motion segmentation	claim
39	1103	Piecewise-Consistent Color Mappings of Images Acquired Under Various Conditions
40	1075	LabelMe video: Building a Video Database with Human Annotations	claim
41	1069	An efficient algorithm for Co-segmentation	claim
42	1068	Illumination Aware MCMC Particle Filter for Long-Term Outdoor Multi-Object Simultaneous Tracking and Classification	claim
43	1052	A direct approach for efficiently tracking with 3D Morphable Models
44	1048	Face Recognition With Contiguous Occlusion Using Markov Random Fields	claim
45	1042	Activity Recognition using the velocity histories of tracked keypoints	claim
46	1038	Combining efficient object localization and image classification	claim
47	1035	Efficient High-Quality Image Contour Detection	claim
48	1022	Kernelized Locality-Sensitive Hashing for Scalable Image Search	claim
49	1019	Similarity Functions for Categorization: from Monolithic to Category Specific	claim
50	997	Poselets: Body Part Detectors Trained Using 3D Human Pose Annotations	claim
51	992	Correlated Probabilistic Trajectories for Pedestrian Motion Detection
52	992	Fast and Robust Earth Mover's Distances
53	988	Compact Signatures for High-Speed Interest Point Description and Matching	claim
54	982	Curvature Regularity for Region-based Image Segmentation and Inpainting: A Linear Programming Relaxation	claim
55	956	Image Segmentation with A Bounding Box Prior	claim
56	945	Automatic annotation of human actions in video	claim
57	937	Decomposing a Scene into Geometric and Semantically Consistent Regions	claim
58	935	Structure- and Motion-adaptive Regularization for High Accuracy Optic Flow	claim
59	932	Using machine learning to predict where people look	claim
60	927	Recovering Planar Homographies between 2D Shapes
61	924	Modeling Deformable Objects from a Single Depth Camera	claim
62	921	Wide-Baseline Image Matching Using Line Signatures	claim
63	914	An Algorithm for Minimizing the Piecewise Smooth Mumford-Shah Functional	claim
64	900	Modelling Activity Global Temporal Dependencies using Time Delayed Probabilistic Graphical Model
65	894	Complete Multi-View Reconstruction of Dynamic Scenes from Probabilistic Fusion of Narrow and Wide Baseline Stereo
66	888	Joint learning of visual attributes, object classes and visual saliency	claim
67	885	Seeing 3D Objects in a Single 2D Image	claim
68	883	Reconstructing Building Interiors from Images	claim
69	876	Multiple Kernels for Object Detection	claim
70	875	Saliency Driven Total Variation Segmentation
71	872	Spatio-Temporal Relationship Match: Video Structure Comparison for Recognition of Complex Human Activities	claim
72	870	A Shape-Based Object Class Model for Knowledge Transfer	claim
73	861	Tracking in Unstructured Crowded Scenes	claim
74	849	Mode-Detection via Median-Shift	claim
75	829	Light Field Video Stabilization	claim
76	827	Sparse Representation of Cast Shadows via L1-Regularized Least Squares
77	821	3D reconstruction from image collections with a single known focal length	claim
78	815	A Theory of Active Object Localization	claim
79	806	Detection of Human Actions From A Single Example
80	792	Tensor completion for estimating missing values in visual data	claim
81	771	Detecting Objects in Large Image Collections and Videos by Efficient Subimage Retrieval	claim
82	770	Large Displacement Optical Flow Computation without Warping	claim
83	749	Finding Good Composition in Panoramic Scenes	claim
84	746	Sparsity Induced Similarity Measure for Label Propagation
85	739	Semi-Supervised Random Forests
86	736	Absolute Scale in Structure from Motion from a Single Vehicle Mounted Camera by Exploiting Nonholonomic Constraints	claim
87	725	Ground truth dataset and baseline evaluations for intrinsic image algorithms	claim
88	714	Video Scene Understanding Using Multi-scale Analysis
89	704	Active Skeleton for Non-rigid Object Detection	claim
90	698	Level Set Segmentation with Both Shape and Intensity Priors	claim
91	697	Higher-Order Gradient Descent by Fusion-Move Graph Cut	claim
92	697	Feature-Centric Efficient Subwindow Search	claim
93	690	Factorizing Scene Albedo and Depth from a Single Foggy Image	claim
94	687	Recovering the Spatial Layout of Cluttered Rooms	claim
95	682	Segmentation and Shading Estimation in Slowly Changing Textured Images	claim
96	668	Efficient Privacy Preserving Video Surveillance	claim
97	651	An Algebraic Approach to Affine Registration of Point Sets	claim
98	649	Detecting Interpretable and Accurate Scale-Invariant keypoints	claim
99	648	Diagram Techniques for Multiple View Geometry	claim
100	638	Keyframe-Based Real-Time Camera Tracking	claim
101	638	Time Series Prediction by Chaotic Modeling of Nonlinear Dynamical Systems	claim
102	629	Super-Resolution from a Single Image	claim
103	606	Boundary Ownership by Lifting to 2.5D	claim
104	602	Max-Margin Additive Classifiers for Detection	claim
105	600	Recognizing Actions by Shape-Motion Prototype Trees	claim
106	591	Active Appearance Models with Rotation Invariant Kernels	claim
107	584	Learning a dense multi-view representation for detection, viewpoint classification and synthesis of object categories	claim
108	581	Image Saliency by Isocentric Curvedness and Color
109	577	Action Detection in Complex Scenes with Spatial and Temporal Ambiguities	claim
110	574	Multiperspective Stereo Matching and Volumetric Reconstruction
111	571	Image Sequence Geolocation with Human Travel Priors	claim
112	569	Multi-Scale Object Detection by Clustering Lines	claim
113	560	Scale Invariance and Noise in Natural Images
114	558	Scene Shape Priors for Superpixel Segmentation	claim
115	548	Convex Optimization for Multi-Class Image Labeling with a Novel Family of Total Variation Based Regularizers	claim
116	547	Shape Guided Contour Grouping with Particle Filters
117	547	Least-Squares Congealing for Large Numbers of Images
118	539	TagProp: Discriminative Metric Learning in Nearest Neighbor Models for Image Auto-Annotation
119	533	Context by Region Ancestry	claim
120	533	A Riemannian Analysis of 3D Nose Shapes For Partial Human Biometrics	claim
121	513	Piecewise Planar Stereo for Image-based Rendering
122	513	What is the Best Multi-Stage Architecture for Object Recognition?	claim
123	511	Seeing through water: Image restoration using model-based tracking	claim
124	501	A Latent Model of Discriminative Aspect	claim
125	496	Convex Multi-Region Segmentation on Manifolds	claim
126	495	Unsupervised Face Alignment by Robust Nonrigid Mapping	claim
127	494	Moving in Stereo: Efficient Structure and Motion Using Lines	claim
128	493	Template-Free Monocular Reconstruction of Deformable Surfaces	claim
129	492	The One-Shot Similarity Kernel	claim
130	491	Non-Negative Matrix Factorization of Partial Track Data for Motion Segmentation	claim
131	488	A novel approach to expression recognition from non-frontal face images	claim
132	486	Scene Categorization from Low Definition Video	claim
133	483	Color Constancy using 3D Scene Geometry	claim
134	474	Globally Optimal Affine Epipolar Geometry from Apparent Contours	claim
135	471	Deformable Model Fitting with a Mixture of Local Experts
136	471	Patch based Within-Object Classification	claim
137	467	Is that you? Metric Learning Approaches for Face Identification
138	467	Subspace Constrained Mean-Shift
139	465	The Swap and Expansion Moves Revisited and Fused
140	464	The Self-Aware Matching Measure for Stereo	claim
141	463	Is a detector only good for detection?	claim
142	463	Shape-based Recognition of 3D Point Clouds in Urban Environments	claim
143	462	Efficient subset selection based on the Renyi entropy	claim
144	461	Adaptive Fragments-Based Tracking of Non-Rigid Objects Using Level Sets	claim
145	461	Radiometric Compensation using Stratified Inverses
146	460	Estimating Natural Illumination from a Single Outdoor Image	claim
147	459	Static Multi-Camera Factorization Using Rigid Motion
148	458	Learning Actions From the Web	claim
149	446	Stabilizing Motion Tracking Using Retrieved Motion Priors	claim
150	445	Jointly estimating demographics and height with a calibrated camera
151	444	Learning Pedestrian Dynamics from the Real World	claim
152	443	Active segmentation with fixation	claim
153	442	Weakly supervised discriminative localization and classification: a joint learning process	claim
154	442	FLoSS: Facility Location for Subspace Segmentation	claim
155	439	Dimensionality Reduction and Principal Surfaces via Kernel Map Manifolds	claim
156	436	A Robust Elastic and Partial Matching Metric for Face Recognition	claim
157	435	Image Restoration using Online Photo Collections	claim
158	434	Constrained Clustering by Spectral Kernel Learning	claim
159	432	Estimating Contact Dynamics	claim
160	432	An HOG-LBP human detector with partial occlusion handling	claim
161	430	Multimodal Partial Estimates Fusion	claim
162	430	Beyond Connecting the Dots: A Polynomial-time Algorithm for Segmentation and Boundary Estimation with Imprecise User Input	claim
163	425	Is Dual Linear Self-Calibration Artificially Ambiguous?	claim
164	423	Robust Fitting of Multiple Structures: The Statistical Learning Approach	claim
165	423	Dense 3D reconstruction method using a single pattern for fast moving object	claim
166	421	Joint Pose Estimator and Feature Learning for Object Detection
167	420	Directional Statistics BRDF Model	claim
168	417	Modeling 3D human poses from uncalibrated monocular images	claim
169	415	Filter Flow	claim
170	415	Semi-automatic stereo extraction from video footage	claim
171	408	Segmentation, ordering and multi-object tracking using graphical models	claim
172	408	Estimating human shape and pose from a single image	claim
173	407	Bayesian selection of scaling laws for motion modeling in images	claim
174	406	A linear formulation of shape from specular flow	claim
175	406	Unlabeled data improves word prediction	claim
176	406	Selection and context for action recognition	claim
177	401	Evaluating Information Contributions of Bottom-up and Top-down Processes	claim
178	400	Time-Constrained Photography	claim
179	398	Learning Deformable Action Templates from Crowded Videos	claim
180	398	Efficient indexing for large scale visual search	claim
181	397	Label Set Perturbation for MRF based Neuroimaging Segmentation	claim
182	394	SURF Tracking	claim
183	392	Efficient Discriminative Learning of Parts-based Models	claim
184	391	Subspace matching: Unique solutions to point matching with geometric constraints	claim
185	386	Efficient human pose estimation via parsing a tree structure based human model	claim
186	382	Optimal Correspondences from Pairwise Constraints	claim
187	381	The Dimensionality of Scene Appearance	claim
188	379	Quantifying Contextual Information for Object Detection	claim
189	378	Joint optimization of segmentation and appearance models	claim
190	377	Real-time visual tracking via Incremental Covariance Tensor Learning	claim
191	377	Video object segmentation by tracking regions	claim
192	374	Domain Adaptive Semantic Diffusion for Large Scale Context-Based Video Annotation	claim
193	374	A Global Perspective on MAP Inference for Low-Level Vision	claim
194	371	Attached shadow coding: Estimating surface normals from shadows under unknown reflectance and lighting conditions	claim
195	370	Multiscale Symmetric Part Detection and Grouping	claim
196	368	Efficient multi-label ranking for multi-class learning: Application to object recognition	claim
197	367	Extending Continuous Cuts: Anisotropic Metrics and Expansion Moves	claim
198	367	A framework for visual saliency detection with applications to image thumbnailing	claim
199	365	Optimizing Parametric Total Variation Models	claim
200	364	A Probabilistic Framework for Partial Intrinsic Symmetries in Geometric Data	claim
201	361	Shadow cameras: Reciprocal views from illumination masks	claim
202	360	Which Faces to Tag: Adding Prior Constraints into Active Learning	claim
203	360	An algebraic model for fast corner detection	claim
204	359	GroupSAC: Efficient Consensus in the Presence of Groupings	claim
205	354	Heterogeneous Feature Machines for Visual Recognition	claim
206	352	Fast realistic multi-action recognition using mined dense spatio-temporal features	claim
207	350	Robust facial feature tracking using selected multi-resolution linear predictors	claim
208	346	Body-Relative Navigation Guidance Using Uncalibrated Cameras	claim
209	344	Large-scale privacy protection in Google Street View	claim
210	342	Non-Euclidean image-adaptive Radial Basis Functions for 3D interactive segmentation	claim
211	339	Globally optimal segmentation of multi-region objects	claim
212	338	BLOGS: Balanced local and global search for non-degenerate two view epipolar geometry	claim
213	334	Building recognition using sketch-based representations and spectral graph matching	claim
214	333	Group-sensitive multiple kernel learning for object categorization	claim
215	329	An algorithm for minimizing the Mumford-Shah functional	claim
216	329	Learning to predict where humans look	claim
217	327	Constructing implicit 3D shape models for pose estimation	claim
218	327	Complex volume and pose tracking with probabilistic dynamical models and visual hull constraints	claim
219	325	Bayesian Poisson regression for crowd counting	claim
220	325	Realtime background subtraction from dynamic scenes	claim
221	323	Storyboard sketches for Content Based Video Retrieval	claim
222	322	Consensus set maximization with guaranteed global optimality for robust geometry estimation	claim
223	321	Incremental action recognition using feature-tree
224	321	Improving accuracy of geometric parameter estimation using projected score method	claim
225	317	A study on automatic age estimation using a large database	claim
226	317	Face alignment through subspace constrained mean-shifts	claim
227	316	Learning with dynamic group sparsity	claim
228	315	A multi-sample, multi-tree approach to bag-of-words image representation for image retrieval	claim
229	314	Simultaneous camera pose and correspondence estimation in cornerless images	claim
230	311	Video scene categorization by 3D hierarchical histogram matching	claim
231	309	Local distance functions: A taxonomy, new algorithms, and an evaluation	claim
232	308	Unsupervised learning of high-order structural semantics from images	claim
233	307	Kernel map compression using generalized radial basis functions	claim
234	307	A hybrid generative/discriminative classification framework based on free-energy terms	claim
235	306	Image annotation using multi-label correlated Green's function	claim
236	305	Non-iterative approach for fast and accurate vanishing point detection	claim
237	305	Analysis of orientation and scale in smoothly varying textures	claim
238	302	Learning image similarity from Flickr groups using Stochastic Intersection Kernel MAchines	claim
239	300	SCRAMSAC: Improving RANSAC's efficiency with a spatial consistency filter	claim
240	299	Quasi-periodic event analysis for social game retrieval	claim
241	299	Structure and kinematics triangulation with a rolling shutter stereo rig	claim
242	299	Attribute and simile classifiers for face verification	claim
243	298	On optimizing subspaces for face recognition	claim
244	295	High-resolution shape reconstruction from multiple range images based on simultaneous estimation of surface and motion	claim
245	294	Associative hierarchical CRFs for object class image segmentation	claim
246	294	Robust dynamical model for simultaneous registration and segmentation in a variational framework: A Bayesian approach	claim
247	292	A robust boosting tracker with minimum error bound in a co-training framework	claim
248	290	Exploiting uncertainty in random sample consensus	claim
249	287	Shape analysis with multivariate tensor-based morphometry and holomorphic differentials	claim
250	287	Incremental Multiple Kernel Learning for object recognition	claim
251	284	Component analysis approach to estimation of tissue intensity distributions of 3D images	claim
252	282	The Normalized Subspace Inclusion: Robust clustering of motion subspaces	claim
253	281	Local Trinary Patterns for human action recognition	claim
254	277	Structural SVM for visual localization and continuous state estimation	claim
255	276	Landmark classification in large-scale image collections	claim
256	276	Minimizing energy functions on 4-connected lattices using elimination	claim
257	276	Matching as a non-cooperative game	claim
258	272	Looking around the corner using transient imaging	claim
259	268	Simultaneous photometric invariance and shape recovery	claim
260	263	Studying brain morphometry using conformal equivalence class	claim
261	261	Stereo from flickering caustics	claim
262	260	Simultaneous alignment and clustering for an image ensemble	claim
263	257	Tracking a large number of objects from multiple views	claim
264	253	Single view reconstruction using shape grammars for urban environments	claim
265	252	Probabilistic occlusion boundary detection on spatio-temporal lattices	claim
266	250	Non-rigid object localization and segmentation using eigenspace representation	claim
267	238	A prism-based system for multispectral video acquisition	claim

Sciweavers

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers