ECCV 2008 - PDF Preprint Papers

ECCV 2008 European 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 ECCV-2008 Paper

click to vote

ECCV
2008
Springer

898views Computer Vision» more ECCV 2008»

Detecting Carried Objects in Short Video Sequences

15 years 3 months ago

Download www.comp.leeds.ac.uk

We propose a new method for detecting objects such as bags carried by pedestrians depicted in short video sequences. In common with earlier work on the same problem, the method sta...

Dima Damen, David Hogg

posted by dimadamen

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	898	Detecting Carried Objects in Short Video Sequences
2	805	Generative Image Segmentation Using Random Walks with Restart
3	487	Flexible Depth of Field Photography
4	461	Quick Shift and Kernel Methods for Mode Seeking	claim
5	454	SMD: A Locally Stable Monotonic Change Invariant Feature Descriptor	claim
6	450	Robust 3D Pose Estimation and Efficient 2D Region-Based Segmentation from a 3D Shape Prior	claim
7	357	Semi-supervised On-Line Boosting for Robust Tracking
8	356	Toward Global Minimum through Combined Local Minima
9	345	Tracking of Abrupt Motion using Wang-Landau Monte Carlo Estimation
10	320	3D Face Model Fitting for Recognition	claim
11	316	Determining Patch Saliency Using Low-Level Context
12	315	Image Segmentation by Branch-and-Mincut	claim
13	314	Co-Recognition of Image Pairs by Data-Driven Monte Carlo Image Exploration
14	311	Analysis of Building Textures for Reconstructing Partially Occluded Facades	claim
15	309	SIFT Flow: Dense Correspondence across Different Scenes	claim
16	308	Estimating 3D Face Model and Facial Deformation from a Single Image Based on Expression Manifold Optimization	claim
17	308	A Linear Time Histogram Metric for Improved SIFT Matching
18	306	The Naked Truth: Estimating Body Shape Under Clothing	claim
19	302	Online Tracking and Reacquisition Using Co-trained Generative and Discriminative Trackers	claim
20	301	Segmentation and Recognition Using Structure from Motion Point Clouds	claim
21	298	Localizing Objects with Smart Dictionaries
22	294	Fast Automatic Single-View 3-d Reconstruction of Urban Scenes	claim
23	286	Star Shape Prior for Graph-Cut Image Segmentation	claim
24	285	Edge-Preserving Smoothing and Mean-Shift Segmentation of Video Streams	claim
25	285	Face Alignment Via Component-Based Discriminative Search	claim
26	282	Latent Pose Estimator for Continuous Action Recognition	claim
27	278	Weakly Supervised Object Localization with Stable Segmentations	claim
28	277	Feature Correspondence Via Graph Matching: Models and Global Optimization	claim
29	277	Locating Facial Features with an Extended Active Shape Model	claim
30	277	Multiple Instance Boost Using Graph Embedding Based Decision Stump for Pedestrian Detection	claim
31	274	Viewpoint Invariant Pedestrian Recognition with an Ensemble of Localized Features	claim
32	272	Robust Visual Tracking Based on an Effective Appearance Model	claim
33	269	Fast and Accurate Rotation Estimation on the 2-Sphere without Correspondences	claim
34	269	A Pose-Invariant Descriptor for Human Detection and Segmentation	claim
35	267	Belief Propagation with Directional Statistics for Solving the Shape-from-Shading Problem
36	265	Articulated Multi-body Tracking under Egomotion	claim
37	264	Output Regularized Metric Learning with Side Information	claim
38	263	Contour Context Selection for Object Detection: A Set-to-Set Contour Matching Approach	claim
39	263	Object Detection from Large-Scale 3D Datasets Using Bottom-Up and Top-Down Descriptors	claim
40	262	Hamming Embedding and Weak Geometric Consistency for Large Scale Image Search	claim
41	260	Using Multiple Hypotheses to Improve Depth-Maps for Multi-View Stereo	claim
42	259	Discriminative Sparse Image Models for Class-Specific Edge Detection and Image Interpretation	claim
43	258	Simultaneous Detection and Registration for Ileo-Cecal Valve Detection in 3D CT Colonography	claim
44	255	Background Subtraction on Distributions	claim
45	254	A Segmentation Based Variational Model for Accurate Optical Flow Estimation	claim
46	250	Stereo Matching: An Outlier Confidence Approach	claim
47	244	GeoS: Geodesic Image Segmentation	claim
48	244	Beyond Nouns: Exploiting Prepositions and Comparative Adjectives for Learning Visual Classifiers	claim
49	243	Illumination and Person-Insensitive Head Pose Estimation Using Distance Metric Learning	claim
50	242	3D Face Recognition by Local Shape Difference Boosting	claim
51	241	An Efficient Dense and Scale-Invariant Spatio-Temporal Interest Point Detector	claim
52	240	Human Activity Recognition with Metric Learning	claim
53	239	Simultaneous Visual Recognition of Manipulation Actions and Manipulated Objects	claim
54	237	Pose Priors for Simultaneously Solving Alignment and Correspondence	claim
55	237	An Extended Phase Field Higher-Order Active Contour Model for Networks and Its Application to Road Network Extraction from VHR Satellite Images	claim
56	237	Higher Dimensional Affine Registration and Vision Applications	claim
57	237	3D Non-rigid Surface Matching and Registration Based on Holomorphic Differentials	claim
58	236	Scene Segmentation for Behaviour Correlation	claim
59	236	Improving the Agility of Keyframe-Based SLAM	claim
60	235	Automatic Image Colorization Via Multimodal Predictions	claim
61	233	Multiple Tree Models for Occlusion and Spatial Constraints in Human Pose Estimation	claim
62	231	Robust Real-Time Visual Tracking Using Pixel-Wise Posteriors	claim
63	230	Facial Expression Recognition Based on 3D Dynamic Range Model Sequences	claim
64	228	Structuring Visual Words in 3D for Arbitrary-View Object Localization	claim
65	227	Scale Invariant Action Recognition Using Compound Features Mined from Dense Spatio-temporal Corners	claim
66	224	Compressive Sensing for Background Subtraction	claim
67	224	Learning Two-View Stereo Matching	claim
68	223	Scale-Dependent/Invariant Local 3D Shape Descriptors for Fully Automatic Registration of Multiple Sets of Range Images	claim
69	222	Anisotropic Geodesics for Perceptual Grouping and Domain Meshing	claim
70	221	Floor Fields for Tracking in High Density Crowd Scenes	claim
71	221	Estimating 3D Trajectories of Periodic Motions from Stationary Monocular Views	claim
72	220	Constrained Maximum Likelihood Learning of Bayesian Networks for Facial Action Recognition	claim
73	220	Improving Shape Retrieval by Learning Graph Transduction	claim
74	218	An Experimental Comparison of Discrete and Continuous Shape Optimization Methods	claim
75	218	Integration of Multiview Stereo and Silhouettes Via Convex Functionals on Convex Domains	claim
76	218	Projected Texture for Object Classification	claim
77	216	Perspective Nonrigid Shape and Motion Recovery	claim
78	216	What Is a Good Image Segment? A Unified Approach to Segment Extraction	claim
79	215	Implementing Decision Trees and Forests on a GPU	claim
80	215	Window Annealing over Square Lattice Markov Random Field
81	214	Robust Multiple Structures Estimation with J-Linkage	claim
82	213	Texture-Consistent Shadow Removal	claim
83	212	Efficiently Learning Random Fields for Stereo Vision with Sparse Message Passing	claim
84	212	CSDD Features: Center-Surround Distribution Distance for Feature Extraction and Matching	claim
85	212	Extracting Moving People from Internet Videos	claim
86	212	Unsupervised Classification and Part Localization by Consistency Amplification	claim
87	211	Image Feature Extraction Using Gradient Local Auto-Correlations	claim
88	210	Efficient Dense Scene Flow from Sparse or Dense Stereo Data	claim
89	207	A Dynamic Conditional Random Field Model for Joint Labeling of Object and Scene Classes	claim
90	207	Active Matching	claim
91	206	Multiple Component Learning for Object Detection	claim
92	206	Hierarchical Support Vector Random Fields: Joint Training to Combine Local and Global Features	claim
93	205	View Point Tracking of Rigid Objects Based on Shape Sub-manifolds	claim
94	205	Estimating Radiometric Response Functions from Image Noise Variance	claim
95	204	Sparse Long-Range Random Field and Its Application to Image Denoising	claim
96	203	Modeling and Recognition of Landmark Image Collections Using Iconic Scene Graphs	claim
97	203	Image Segmentation in the Presence of Shadows and Highlights	claim
98	202	Learning Spatial Context: Using Stuff to Find Things	claim
99	202	ASN: Image Keypoint Detection from Adaptive Shape Neighborhood	claim
100	202	Vision-Based Multiple Interacting Targets Tracking via On-Line Supervised Learning	claim
101	201	A Probabilistic Approach to Integrating Multiple Cues in Visual Tracking	claim
102	201	Unsupervised Structure Learning: Hierarchical Recursive Composition, Suspicious Coincidence and Competitive Exclusion	claim
103	200	A Lattice-Preserving Multigrid Method for Solving the Inhomogeneous Poisson Equations Used in Image Analysis	claim
104	200	Improving People Search Using Query Expansions	claim
105	200	An Incremental Learning Method for Unconstrained Gaze Estimation	claim
106	199	Event Modeling and Recognition Using Markov Logic Networks	claim
107	199	Discriminative Locality Alignment	claim
108	198	Kernel Codebooks for Scene Categorization	claim
109	197	Closed-Form Solution to Non-rigid 3D Surface Registration	claim
110	196	Movie/Script: Alignment and Parsing of Video and Text Transcription	claim
111	196	Constructing Category Hierarchies for Visual Recognition	claim
112	195	A Fast Algorithm for Creating a Compact and Discriminative Visual Codebook	claim
113	193	Region-Based 2D Deformable Generalized Cylinder for Narrow Structures Segmentation	claim
114	192	Signature-Based Document Image Retrieval	claim
115	190	Automatic Generator of Minimal Problem Solvers	claim
116	190	Reformulating and Optimizing the Mumford-Shah Functional on a Graph - A Faster, Lower Energy Solution	claim
117	189	Multi-stage Contour Based Detection of Deformable Objects	claim
118	188	Relevant Feature Selection for Human Pose Estimation and Localization in Cluttered Images	claim
119	188	Multi-scale Improves Boundary Detection in Natural Images	claim
120	187	Active Image Labeling and Its Application to Facial Action Labeling	claim
121	186	Online Sparse Matrix Gaussian Process Regression and Vision Applications	claim
122	185	Tracking of Abrupt Motion Using Wang-Landau Monte Carlo Estimation	claim
123	185	Learning Visual Shape Lexicon for Document Image Content Recognition	claim
124	185	Efficient Camera Smoothing in Sequential Structure-from-Motion Using Approximate Cross-Validation	claim
125	185	Multi-thread Parsing for Recognizing Complex Events in Videos	claim
126	184	Finding Actions Using Shape Flows	claim
127	182	Learning for Optical Flow Using Stochastic Optimization	claim
128	180	Learning Optical Flow	claim
129	180	Multi-layered Decomposition of Recurrent Scenes	claim
130	179	Discriminative Learning for Deformable Shape Segmentation: A Comparative Study	claim
131	179	FaceTracer: A Search Engine for Large Collections of Images with Faces	claim
132	178	Photo and Video Quality Evaluation: Focusing on the Subject	claim
133	177	Estimating Geo-temporal Location of Stationary Cameras Using Shadow Trajectories	claim
134	177	Temporal Surface Tracking Using Mesh Evolution	claim
135	177	Real-Time Shape Analysis of a Human Body in Clothing Using Time-Series Part-Labeled Volumes	claim
136	176	Understanding Camera Trade-Offs through a Bayesian Analysis of Light Field Projections	claim
137	176	Continuous Energy Minimization Via Repeated Binary Fusion	claim
138	175	Deformed Lattice Discovery Via Efficient Mean-Shift Belief Propagation	claim
139	175	Video Registration Using Dynamic Textures	claim
140	175	Partial Difference Equations over Graphs: Morphological Processing of Arbitrary Discrete Data	claim
141	175	A Statistical Confidence Measure for Optical Flows	claim
142	172	Some Objects Are More Equal Than Others: Measuring and Predicting Importance	claim
143	172	Semidefinite Programming Heuristics for Surface Reconstruction Ambiguities	claim
144	172	Shadows in Three-Source Photometric Stereo	claim
145	171	A Generative Shape Regularization Model for Robust Face Alignment	claim
146	171	Cross-View Action Recognition from Temporal Self-similarities	claim
147	171	Learning to Recognize Activities from the Wrong View Point	claim
148	171	View Synthesis for Recognizing Unseen Poses of Object Classes	claim
149	171	General Imaging Geometry for Central Catadioptric Cameras	claim
150	170	Robust Optimal Pose Estimation	claim
151	170	What Is a Good Nearest Neighbors Algorithm for Finding Similar Patches in Images?	claim
152	170	Cat Head Detection - How to Effectively Exploit Shape and Texture Features	claim
153	169	Temporal Dithering of Illumination for Fast Active Vision	claim
154	168	A Comparative Analysis of RANSAC Techniques Leading to Adaptive Real-Time Random Sample Consensus	claim
155	168	Prior-Based Piecewise-Smooth Segmentation by Template Competitive Deformation Using Partitions of Unity	claim
156	166	Towards Scalable Dataset Construction: An Active Learning Approach	claim
157	165	Non-local Regularization of Inverse Problems	claim
158	164	A New Baseline for Image Annotation	claim
159	163	Differential Spatial Resection - Pose Estimation Using a Single Local Image Feature	claim
160	162	Learning to Localize Objects with Structured Output Regression	claim
161	162	Object Recognition by Integrating Multiple Image Segmentations	claim
162	162	Scene Segmentation Using the Wisdom of Crowds	claim
163	161	Compressive Structured Light for Recovering Inhomogeneous Participating Media	claim
164	159	Interactive Tracking of 2D Generic Objects with Spacetime Optimization	claim
165	159	Unsupervised Learning of Skeletons from Motion	claim
166	159	Calibration from Statistical Properties of the Visual World	claim
167	158	Brain Hallucination	claim
168	156	Fourier Analysis of the 2D Screened Poisson Equation for Gradient Domain Problems	claim
169	155	Dynamic Integration of Generalized Cues for Person Tracking	claim
170	154	Learning CRFs Using Graph Cuts	claim
171	154	Regular Texture Analysis as Statistical Model Selection	claim
172	154	Solving Image Registration Problems Using Interior Point Methods	claim
173	152	Recovering Light Directions and Camera Poses from a Single Sphere	claim
174	152	Unified Crowd Segmentation	claim
175	151	Training Hierarchical Feed-Forward Visual Recognition Models Using Transfer Learning from Pseudo-Tasks	claim
176	151	Saliency Based Opportunistic Search for Object Part Extraction and Labeling	claim
177	151	Automated Delineation of Dendritic Networks in Noisy Image Stacks	claim
178	151	Light-Efficient Photography	claim
179	151	Priors for Large Photo Collections and What They Reveal about Cameras	claim
180	150	What Does the Sky Tell Us about the Camera?	claim
181	150	Linking Pose and Motion	claim
182	148	Beyond Loose LP-Relaxations: Optimizing MRFs by Repairing Cycles	claim
183	147	Keypoint Signatures for Fast Learning and Recognition	claim
184	147	Shape Matching by Segmentation Averaging	claim
185	146	Similarity Features for Facial Event Analysis	claim
186	146	Robust Object Tracking by Hierarchical Association of Detection Responses	claim
187	145	Passive Reflectometry	claim
188	144	A Perceptual Comparison of Distance Measures for Color Constancy Algorithms	claim
189	144	The Bi-directional Framework for Unifying Parametric Image Alignment Approaches	claim
190	141	Local Statistic Based Region Segmentation with Automatic Scale Selection	claim
191	140	Multi-camera Tracking and Atypical Motion Detection with Behavioral Maps	claim
192	140	Unified Frequency Domain Analysis of Lightfield Cameras	claim
193	139	Three Dimensional Curvilinear Structure Detection Using Optimally Oriented Flux	claim
194	137	A Convex Formulation of Continuous Multi-label Problems	claim
195	137	Local Regularization for Multiclass Classification Facing Significant Intraclass Variations	claim
196	135	Statistical Analysis of Global Motion Chains	claim
197	132	Grassmann Registration Manifolds for Face Recognition	claim
198	125	Shape-Based Retrieval of Heart Sounds for Disease Similarity Detection	claim
199	124	Surface Visibility Probabilities in 3D Cluttered Scenes	claim
200	123	Searching the World's Herbaria: A System for Visual Identification of Plant Species	claim
201	121	Efficient Edge-Based Methods for Estimating Manhattan Frames in Urban Imagery	claim
202	116	A Generic Neighbourhood Filtering Framework for Matrix Fields	claim
203	115	VideoCut: Removing Irrelevant Frames by Discovering the Object of Interest	claim
204	115	Regularized Partial Matching of Rigid Shapes	claim
205	114	A Probabilistic Cascade of Detectors for Individual Object Recognition	claim
206	114	SERBoost: Semi-supervised Boosting with Expectation Regularization	claim
207	113	Tracking with Dynamic Hidden-State Shape Models	claim
208	110	Something Old, Something New, Something Borrowed, Something Blue	claim
209	108	Search Space Reduction for MRF Stereo	claim

Sciweavers

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers