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

572views Computer Vision» more ECCV 2008»

Detecting Carried Objects in Short Video Sequences

3 years 25 days 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	572	Detecting Carried Objects in Short Video Sequences
2	290	Generative Image Segmentation Using Random Walks with Restart
3	256	Flexible Depth of Field Photography
4	191	Toward Global Minimum through Combined Local Minima
5	168	Quick Shift and Kernel Methods for Mode Seeking	claim
6	148	Belief Propagation with Directional Statistics for Solving the Shape-from-Shading Problem
7	145	Localizing Objects with Smart Dictionaries
8	143	Tracking of Abrupt Motion using Wang-Landau Monte Carlo Estimation
9	142	The Naked Truth: Estimating Body Shape Under Clothing	claim
10	138	Image Segmentation by Branch-and-Mincut	claim
11	137	Robust 3D Pose Estimation and Efficient 2D Region-Based Segmentation from a 3D Shape Prior	claim
12	134	A Linear Time Histogram Metric for Improved SIFT Matching
13	131	Edge-Preserving Smoothing and Mean-Shift Segmentation of Video Streams	claim
14	128	Human Activity Recognition with Metric Learning	claim
15	128	Semi-supervised On-Line Boosting for Robust Tracking
16	127	A Pose-Invariant Descriptor for Human Detection and Segmentation	claim
17	122	Face Alignment Via Component-Based Discriminative Search	claim
18	120	SIFT Flow: Dense Correspondence across Different Scenes	claim
19	117	Articulated Multi-body Tracking under Egomotion	claim
20	116	Hamming Embedding and Weak Geometric Consistency for Large Scale Image Search	claim
21	115	Simultaneous Visual Recognition of Manipulation Actions and Manipulated Objects	claim
22	113	Co-Recognition of Image Pairs by Data-Driven Monte Carlo Image Exploration
23	111	Higher Dimensional Affine Registration and Vision Applications	claim
24	111	Pose Priors for Simultaneously Solving Alignment and Correspondence	claim
25	106	Viewpoint Invariant Pedestrian Recognition with an Ensemble of Localized Features	claim
26	106	Feature Correspondence Via Graph Matching: Models and Global Optimization	claim
27	101	Object Detection from Large-Scale 3D Datasets Using Bottom-Up and Top-Down Descriptors	claim
28	101	Illumination and Person-Insensitive Head Pose Estimation Using Distance Metric Learning	claim
29	100	Determining Patch Saliency Using Low-Level Context
30	99	Beyond Nouns: Exploiting Prepositions and Comparative Adjectives for Learning Visual Classifiers	claim
31	99	Segmentation and Recognition Using Structure from Motion Point Clouds	claim
32	98	An Extended Phase Field Higher-Order Active Contour Model for Networks and Its Application to Road Network Extraction from VHR Satellite Images	claim
33	97	Multiple Tree Models for Occlusion and Spatial Constraints in Human Pose Estimation	claim
34	94	Stereo Matching: An Outlier Confidence Approach	claim
35	93	Robust Visual Tracking Based on an Effective Appearance Model	claim
36	93	3D Face Model Fitting for Recognition	claim
37	93	Improving the Agility of Keyframe-Based SLAM	claim
38	93	Floor Fields for Tracking in High Density Crowd Scenes	claim
39	89	Implementing Decision Trees and Forests on a GPU	claim
40	89	Weakly Supervised Object Localization with Stable Segmentations	claim
41	88	Window Annealing over Square Lattice Markov Random Field
42	87	Simultaneous Detection and Registration for Ileo-Cecal Valve Detection in 3D CT Colonography	claim
43	87	Reformulating and Optimizing the Mumford-Shah Functional on a Graph - A Faster, Lower Energy Solution	claim
44	85	An Experimental Comparison of Discrete and Continuous Shape Optimization Methods	claim
45	85	Analysis of Building Textures for Reconstructing Partially Occluded Facades	claim
46	84	Robust Multiple Structures Estimation with J-Linkage	claim
47	84	Fast Automatic Single-View 3-d Reconstruction of Urban Scenes	claim
48	83	Discriminative Sparse Image Models for Class-Specific Edge Detection and Image Interpretation	claim
49	83	Automatic Image Colorization Via Multimodal Predictions	claim
50	83	Estimating 3D Face Model and Facial Deformation from a Single Image Based on Expression Manifold Optimization	claim
51	83	An Efficient Dense and Scale-Invariant Spatio-Temporal Interest Point Detector	claim
52	82	Locating Facial Features with an Extended Active Shape Model	claim
53	82	Multiple Instance Boost Using Graph Embedding Based Decision Stump for Pedestrian Detection	claim
54	81	A Dynamic Conditional Random Field Model for Joint Labeling of Object and Scene Classes	claim
55	81	A Segmentation Based Variational Model for Accurate Optical Flow Estimation	claim
56	81	ASN: Image Keypoint Detection from Adaptive Shape Neighborhood	claim
57	80	Star Shape Prior for Graph-Cut Image Segmentation	claim
58	80	Scene Segmentation for Behaviour Correlation	claim
59	80	SMD: A Locally Stable Monotonic Change Invariant Feature Descriptor	claim
60	80	GeoS: Geodesic Image Segmentation	claim
61	80	Facial Expression Recognition Based on 3D Dynamic Range Model Sequences	claim
62	79	Extracting Moving People from Internet Videos	claim
63	79	Event Modeling and Recognition Using Markov Logic Networks	claim
64	79	Learning Spatial Context: Using Stuff to Find Things	claim
65	79	Integration of Multiview Stereo and Silhouettes Via Convex Functionals on Convex Domains	claim
66	78	Structuring Visual Words in 3D for Arbitrary-View Object Localization	claim
67	76	Using Multiple Hypotheses to Improve Depth-Maps for Multi-View Stereo	claim
68	76	Contour Context Selection for Object Detection: A Set-to-Set Contour Matching Approach	claim
69	75	Robust Optimal Pose Estimation	claim
70	75	Estimating Geo-temporal Location of Stationary Cameras Using Shadow Trajectories	claim
71	75	Latent Pose Estimator for Continuous Action Recognition	claim
72	75	Region-Based 2D Deformable Generalized Cylinder for Narrow Structures Segmentation	claim
73	74	Background Subtraction on Distributions	claim
74	74	Anisotropic Geodesics for Perceptual Grouping and Domain Meshing	claim
75	74	View Synthesis for Recognizing Unseen Poses of Object Classes	claim
76	73	Constrained Maximum Likelihood Learning of Bayesian Networks for Facial Action Recognition	claim
77	73	Multi-thread Parsing for Recognizing Complex Events in Videos	claim
78	73	Robust Real-Time Visual Tracking Using Pixel-Wise Posteriors	claim
79	73	Compressive Sensing for Background Subtraction	claim
80	72	Estimating 3D Trajectories of Periodic Motions from Stationary Monocular Views	claim
81	72	Improving Shape Retrieval by Learning Graph Transduction	claim
82	71	What Is a Good Image Segment? A Unified Approach to Segment Extraction	claim
83	71	A Fast Algorithm for Creating a Compact and Discriminative Visual Codebook	claim
84	70	Output Regularized Metric Learning with Side Information	claim
85	70	Efficiently Learning Random Fields for Stereo Vision with Sparse Message Passing	claim
86	69	An Incremental Learning Method for Unconstrained Gaze Estimation	claim
87	69	Some Objects Are More Equal Than Others: Measuring and Predicting Importance	claim
88	69	A Lattice-Preserving Multigrid Method for Solving the Inhomogeneous Poisson Equations Used in Image Analysis	claim
89	69	Semidefinite Programming Heuristics for Surface Reconstruction Ambiguities	claim
90	68	Sparse Long-Range Random Field and Its Application to Image Denoising	claim
91	68	Learning Optical Flow	claim
92	68	A Generative Shape Regularization Model for Robust Face Alignment	claim
93	68	Relevant Feature Selection for Human Pose Estimation and Localization in Cluttered Images	claim
94	68	Hierarchical Support Vector Random Fields: Joint Training to Combine Local and Global Features	claim
95	67	View Point Tracking of Rigid Objects Based on Shape Sub-manifolds	claim
96	67	Unified Crowd Segmentation	claim
97	67	Continuous Energy Minimization Via Repeated Binary Fusion	claim
98	66	Closed-Form Solution to Non-rigid 3D Surface Registration	claim
99	66	Constructing Category Hierarchies for Visual Recognition	claim
100	66	Multi-stage Contour Based Detection of Deformable Objects	claim
101	65	Scale-Dependent/Invariant Local 3D Shape Descriptors for Fully Automatic Registration of Multiple Sets of Range Images	claim
102	65	3D Non-rigid Surface Matching and Registration Based on Holomorphic Differentials	claim
103	65	Image Segmentation in the Presence of Shadows and Highlights	claim
104	64	Discriminative Locality Alignment	claim
105	64	Unsupervised Classification and Part Localization by Consistency Amplification	claim
106	63	Efficient Camera Smoothing in Sequential Structure-from-Motion Using Approximate Cross-Validation	claim
107	63	Priors for Large Photo Collections and What They Reveal about Cameras	claim
108	63	Learning to Localize Objects with Structured Output Regression	claim
109	63	Modeling and Recognition of Landmark Image Collections Using Iconic Scene Graphs	claim
110	63	Scale Invariant Action Recognition Using Compound Features Mined from Dense Spatio-temporal Corners	claim
111	63	Shadows in Three-Source Photometric Stereo	claim
112	63	Online Tracking and Reacquisition Using Co-trained Generative and Discriminative Trackers	claim
113	62	Prior-Based Piecewise-Smooth Segmentation by Template Competitive Deformation Using Partitions of Unity	claim
114	62	Real-Time Shape Analysis of a Human Body in Clothing Using Time-Series Part-Labeled Volumes	claim
115	61	Partial Difference Equations over Graphs: Morphological Processing of Arbitrary Discrete Data	claim
116	61	Non-local Regularization of Inverse Problems	claim
117	61	Recovering Light Directions and Camera Poses from a Single Sphere	claim
118	61	Perspective Nonrigid Shape and Motion Recovery	claim
119	59	Understanding Camera Trade-Offs through a Bayesian Analysis of Light Field Projections	claim
120	59	Three Dimensional Curvilinear Structure Detection Using Optimally Oriented Flux	claim
121	59	Keypoint Signatures for Fast Learning and Recognition	claim
122	59	3D Face Recognition by Local Shape Difference Boosting	claim
123	59	Multiple Component Learning for Object Detection	claim
124	59	Video Registration Using Dynamic Textures	claim
125	58	Estimating Radiometric Response Functions from Image Noise Variance	claim
126	58	Brain Hallucination	claim
127	58	Discriminative Learning for Deformable Shape Segmentation: A Comparative Study	claim
128	57	Multi-layered Decomposition of Recurrent Scenes	claim
129	57	CSDD Features: Center-Surround Distribution Distance for Feature Extraction and Matching	claim
130	57	Projected Texture for Object Classification	claim
131	57	Compressive Structured Light for Recovering Inhomogeneous Participating Media	claim
132	57	Passive Reflectometry	claim
133	57	Regular Texture Analysis as Statistical Model Selection	claim
134	57	A Statistical Confidence Measure for Optical Flows	claim
135	57	Interactive Tracking of 2D Generic Objects with Spacetime Optimization	claim
136	57	Tracking of Abrupt Motion Using Wang-Landau Monte Carlo Estimation	claim
137	57	Learning CRFs Using Graph Cuts	claim
138	56	Light-Efficient Photography	claim
139	55	Unsupervised Structure Learning: Hierarchical Recursive Composition, Suspicious Coincidence and Competitive Exclusion	claim
140	54	Vision-Based Multiple Interacting Targets Tracking via On-Line Supervised Learning	claim
141	54	Learning to Recognize Activities from the Wrong View Point	claim
142	54	A Comparative Analysis of RANSAC Techniques Leading to Adaptive Real-Time Random Sample Consensus	claim
143	53	Photo and Video Quality Evaluation: Focusing on the Subject	claim
144	53	Automatic Generator of Minimal Problem Solvers	claim
145	53	Beyond Loose LP-Relaxations: Optimizing MRFs by Repairing Cycles	claim
146	53	Solving Image Registration Problems Using Interior Point Methods	claim
147	53	Online Sparse Matrix Gaussian Process Regression and Vision Applications	claim
148	53	Image Feature Extraction Using Gradient Local Auto-Correlations	claim
149	52	A New Baseline for Image Annotation	claim
150	52	Movie/Script: Alignment and Parsing of Video and Text Transcription	claim
151	52	Linking Pose and Motion	claim
152	52	Learning for Optical Flow Using Stochastic Optimization	claim
153	51	Temporal Dithering of Illumination for Fast Active Vision	claim
154	51	Active Matching	claim
155	51	Efficient Dense Scene Flow from Sparse or Dense Stereo Data	claim
156	50	The Bi-directional Framework for Unifying Parametric Image Alignment Approaches	claim
157	50	Unsupervised Learning of Skeletons from Motion	claim
158	50	Tracking with Dynamic Hidden-State Shape Models	claim
159	50	Local Statistic Based Region Segmentation with Automatic Scale Selection	claim
160	49	Kernel Codebooks for Scene Categorization	claim
161	49	FaceTracer: A Search Engine for Large Collections of Images with Faces	claim
162	49	Fourier Analysis of the 2D Screened Poisson Equation for Gradient Domain Problems	claim
163	49	Improving People Search Using Query Expansions	claim
164	48	Saliency Based Opportunistic Search for Object Part Extraction and Labeling	claim
165	48	Cat Head Detection - How to Effectively Exploit Shape and Texture Features	claim
166	48	Differential Spatial Resection - Pose Estimation Using a Single Local Image Feature	claim
167	48	A Probabilistic Approach to Integrating Multiple Cues in Visual Tracking	claim
168	48	Temporal Surface Tracking Using Mesh Evolution	claim
169	48	Finding Actions Using Shape Flows	claim
170	47	A Convex Formulation of Continuous Multi-label Problems	claim
171	47	Training Hierarchical Feed-Forward Visual Recognition Models Using Transfer Learning from Pseudo-Tasks	claim
172	47	Signature-Based Document Image Retrieval	claim
173	47	Multi-camera Tracking and Atypical Motion Detection with Behavioral Maps	claim
174	47	Calibration from Statistical Properties of the Visual World	claim
175	47	Texture-Consistent Shadow Removal	claim
176	47	Similarity Features for Facial Event Analysis	claim
177	47	Deformed Lattice Discovery Via Efficient Mean-Shift Belief Propagation	claim
178	46	Towards Scalable Dataset Construction: An Active Learning Approach	claim
179	46	Shape Matching by Segmentation Averaging	claim
180	46	Learning Visual Shape Lexicon for Document Image Content Recognition	claim
181	45	General Imaging Geometry for Central Catadioptric Cameras	claim
182	45	Dynamic Integration of Generalized Cues for Person Tracking	claim
183	45	Cross-View Action Recognition from Temporal Self-similarities	claim
184	45	Fast and Accurate Rotation Estimation on the 2-Sphere without Correspondences	claim
185	45	Efficient Edge-Based Methods for Estimating Manhattan Frames in Urban Imagery	claim
186	45	Statistical Analysis of Global Motion Chains	claim
187	44	Multi-scale Improves Boundary Detection in Natural Images	claim
188	44	Automated Delineation of Dendritic Networks in Noisy Image Stacks	claim
189	44	Robust Object Tracking by Hierarchical Association of Detection Responses	claim
190	44	Scene Segmentation Using the Wisdom of Crowds	claim
191	44	Surface Visibility Probabilities in 3D Cluttered Scenes	claim
192	43	Learning Two-View Stereo Matching	claim
193	43	What Does the Sky Tell Us about the Camera?	claim
194	42	Object Recognition by Integrating Multiple Image Segmentations	claim
195	42	Unified Frequency Domain Analysis of Lightfield Cameras	claim
196	42	Active Image Labeling and Its Application to Facial Action Labeling	claim
197	42	A Perceptual Comparison of Distance Measures for Color Constancy Algorithms	claim
198	41	Searching the World's Herbaria: A System for Visual Identification of Plant Species	claim
199	41	Regularized Partial Matching of Rigid Shapes	claim
200	40	SERBoost: Semi-supervised Boosting with Expectation Regularization	claim
201	40	What Is a Good Nearest Neighbors Algorithm for Finding Similar Patches in Images?	claim
202	39	A Generic Neighbourhood Filtering Framework for Matrix Fields	claim
203	39	VideoCut: Removing Irrelevant Frames by Discovering the Object of Interest	claim
204	39	Grassmann Registration Manifolds for Face Recognition	claim
205	37	Local Regularization for Multiclass Classification Facing Significant Intraclass Variations	claim
206	34	A Probabilistic Cascade of Detectors for Individual Object Recognition	claim
207	34	Search Space Reduction for MRF Stereo	claim
208	31	Shape-Based Retrieval of Heart Sounds for Disease Similarity Detection	claim
209	30	Something Old, Something New, Something Borrowed, Something Blue	claim

Sciweavers

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers