ECCV 2010 - PDF Preprint Papers

ECCV 2010 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-2010 Paper

click to vote

ECCV
2010
Springer

623views Computer Vision» more ECCV 2010»

Discriminative Spatial Attention for Robust Tracking

1 years 6 months ago

Download www.eecs.northwestern.edu

Abstract. A major reason leading to tracking failure is the spatial distractions that exhibit similar visual appearances as the target, because they also generate good matches to t...

claim paper

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	623	Discriminative Spatial Attention for Robust Tracking	claim
2	543	Guided Image Filtering	claim
3	486	Reweighted Random Walks for Graph Matching
4	427	Closed-loop Adaptation for Robust Tracking	claim
5	423	Affine Puzzle: Realigning Deformed Object Fragments without Correspondences
6	356	A Shrinkage Learning Approach for Single Image Super-Resolution with Overcomplete Representations
7	353	Lighting and Pose Robust Face Sketch Synthesis	claim
8	335	Non-Local Kernel Regression for Image and Video Restoration	claim
9	308	Analysis of Motion Blur With a Flutter Shutter Camera for Non-Linear Motion
10	295	Tracklet Descriptors for Action Modeling and Video Analysis
11	288	Local Occlusion Detection Under Deformations Using Topological Invariants	claim
12	273	Gabor Feature based Sparse Representation for Face Recognition with Gabor Occlusion Dictionary	claim
13	253	Building Rome on a Cloudless Day	claim
14	242	Automatic Learning of Background Semantics in Generic Surveilled Scenes
15	242	On Parameter Learning in CRF-based Approaches to Object Class Image Segmentation	claim
16	227	Kernel Sparse Representation for Image Classification and Face Recognition	claim
17	222	Maximum Margin Distance Learning for Dynamic Texture Recognition	claim
18	212	An eye fixation database for saliency detection in images	claim
19	207	Object, Scene and Actions: Combining Multiple Features for Human Action Recognition	claim
20	207	Detecting People Using Mutually Consistent Poselet Activations	claim
21	205	Detection and Tracking of Large Number of Targets in Wide Area Surveillance	claim
22	192	What, Where & How Many? Combining Object Detectors and CRFs	claim
23	178	Building Compact Local Pairwise Codebook with Joint Feature Space Clustering	claim
24	178	5D Motion Subspaces for Planar Motions
25	170	Graph Cut based Inference with Co-occurrence Statistics	claim
26	168	Dense Point Trajectories by GPU-accelerated Large Displacement Optical Flow	claim
27	165	Gaussian-like Spatial Priors for Articulated Tracking	claim
28	163	Using Partial Edge Contour Matches for Efficient Object Category Localization
29	160	Programmable Aperture Camera Using LCoS
30	147	Single Image Deblurring Using Motion Density Functions	claim
31	146	Rotation invariant non-rigid shape matching in cluttered scenes	claim
32	142	The Quadratic-Chi Histogram Distance Family	claim
33	141	One-Shot Optimal Exposure Control	claim
34	139	Segmenting Salient Objects from Images and Videos	claim
35	139	ClassCut for Unsupervised Class Segmentation	claim
36	137	Fast Approximate Nearest Neighbor Methods for Non-Euclidean Manifolds with Applications to Human Activity Analysis in Videos
37	136	Robust and Fast Collaborative Tracking with Two Stage Sparse Optimization	claim
38	135	SuperParsing: Scalable Nonparametric Image Parsing with Superpixels	claim
39	135	Being John Malkovich	claim
40	134	A Discriminative Latent Model of Object Classes and Attributes	claim
41	132	Multiresolution models for object detection	claim
42	130	Recursive Coarse-to-Fine Localization for fast Object Detection
43	129	Monocular 3D Scene Modeling and Inference: Understanding Multi-Object Traffic Scenes	claim
44	128	Cosegmentation revisited: Models and optimization	claim
45	127	MRF Inference by k-Fan Decomposition and Tight Lagrangian Relaxation	claim
46	127	Multi-Person Tracking with Sparse Detection and Continuous Segmentation	claim
47	127	Blocks World Revisited: Image Understanding using Qualitative Geometry and Mechanics
48	126	Texture Regimes for Entropy-Based Multiscale Image Analysis
49	124	2D Action Recognition Serves 3D Human Pose Estimation	claim
50	124	Weakly Supervised Shape Based Object Detection with Particle Filter	claim
51	123	Spatially-sensitive affine-invariant image descriptors	claim
52	123	Category Independent Object Proposals	claim
53	121	Object Recognition using Junctions	claim
54	121	Efficient Computation of Scale-Space Features for Deformable Shape Correspondences	claim
55	121	Modeling Temporal Structure of Decomposable Motion Segments for Activity Classification	claim
56	120	2.5D Dual Contouring: A Robust Approach to Creating Building Models from Aerial LiDAR Point Clouds
57	120	Learning What and How of Contextual Models for Scene Labeling	claim
58	118	Multiple Instance Metric Learning from Automatically Labeled Bags of Faces	claim
59	118	Extracting Structures in Image Collections for Object Recognition	claim
60	117	Cascaded Confidence Filtering for Improved Tracking-by-Detection	claim
61	117	TriangleFlow: Optical Flow with Triangulation-based Higher-Order Likelihoods	claim
62	116	A Data-Driven Approach for Event Prediction	claim
63	115	Scene carving: Scene consistent image retargeting	claim
64	115	Fast Multi-Aspect 2D Human Detection	claim
65	115	Semantic Segmentation of Urban Scenes Using Dense Depth Maps	claim
66	115	The Generalized PatchMatch Correspondence Algorithm	claim
67	114	Real-time Spatiotemporal Stereo Matching Using the Dual-Cross-Bilateral Grid	claim
68	114	Critical Nets and Beta-Stable Features for Image Matching	claim
69	114	Learning a Fine Vocabulary	claim
70	113	Improving the Fisher Kernel for Large-Scale Image Classification	claim
71	113	Backprojection Revisited: Scalable Multi-view Object Detection and Similarity Metrics for Detections	claim
72	110	3D Deformable Face Tracking with a Commodity Depth Camera	claim
73	108	Detecting Faint Curved Edges in Noisy Images	claim
74	108	Photometric Stereo from Maximum Feasible Lambertian Reflections	claim
75	108	Depth-Encoded Hough Voting for joint object detection and shape recovery	claim
76	108	Discriminative Mixture-of-Templates for Viewpoint Classification	claim
77	107	Anisotropic Minimal Surfaces Integrating Photoconsistency and Normal Information for Multiview Stereo	claim
78	107	Visual Tracking using a Pixelwise Spatiotemporal Oriented Energy Representation	claim
79	107	A High-Quality Video Denoising Algorithm Based on Reliable Motion Estimation	claim
80	107	Nonlocal Multiscale Hierarchical Decomposition on Graphs	claim
81	107	Blind Reflectometry	claim
82	106	Fast Covariance Computation and Dimensionality Reduction for Sub-Window Features in Images	claim
83	105	Balancing Deformability and Discriminability for Shape Matching	claim
84	105	Learning to Detect Roads in High-Resolution Aerial Images	claim
85	105	A 2D Human Body Model Dressed in Eigen Clothing	claim
86	105	Geodesic Shape Retrieval via Optimal Mass Transport	claim
87	104	Word Spotting in the Wild	claim
88	104	Learning to Recognize Objects from Unseen Modalities	claim
89	104	Seeing through Obscure Glass	claim
90	104	Efficient Highly Over-Complete Sparse Coding using a Mixture Model	claim
91	103	Multiple Target Tracking in World Coordinate with Single, Minimally Calibrated Camera	claim
92	103	Accurate Image Localization Based on Google Maps Street View	claim
93	103	5D Motion Subspaces for Planar Motion	claim
94	103	A Streakline Representation of Flow in Crowded Scenes
95	102	Analyzing Depth from Coded Aperture Sets	claim
96	101	Bilinear factorization via Augmented Lagrange Multipliers	claim
97	100	Geometry Construction from Caustic Images	claim
98	100	Camera Pose Estimation Using Images of Planar Mirror Reflections	claim
99	99	Object Recognition with Hierarchical Stel Models	claim
100	99	Two-Phase Kernel Estimation for Robust Motion Deblurring	claim
101	99	Efficiently Scaling Up Video Annotation with Crowdsourced Marketplaces	claim
102	98	Finding Semantic Structures in Image Hierarchies using Laplacian Graph Energy	claim
103	98	3D Reconstruction of a Moving Point from a Series of 2D Projections	claim
104	97	Towards Optimal Naive Bayes Nearest Neighbor	claim
105	96	Image Segmentation with Topic Random Field	claim
106	95	Inferring 3D Shapes and Deformations from Single Views	claim
107	95	Handling Urban Location Recognition as a 2D Homothetic Problem	claim
108	95	Detecting ground shadows in outdoor consumer photographs	claim
109	94	A Dual Theory of Inverse and Forward Light Transport	claim
110	94	Localizing Objects while Learning Their Appearance	claim
111	93	Real-Time Spherical Mosaicing using Whole Image Alignment	claim
112	93	Compact video description for copy detection with precise temporal alignment	claim
113	92	Making Action Recognition Robust to Occlusions and Viewpoint Changes	claim
114	91	Geometric Image Parsing in Man-Made Environments	claim
115	91	Stacked Hierarchical Labeling	claim
116	90	Adaptive Regularization for Image Segmentation Using Local Image Curvature Cues	claim
117	90	Location Recognition Using Prioritized Feature Matching	claim
118	90	Object Segmentation by Long Term Analysis of Point Trajectories	claim
119	90	What does classifying more than 10,000 image categories tell us?	claim
120	89	MIForests: Multiple-Instance Learning with Randomized Trees	claim
121	89	We Are Family: Joint Pose Estimation of Multiple Persons	claim
122	88	Dynamic Color Flow: A Motion-Adaptive Color Model for Object Segmentation in Video	claim
123	88	Boosting Chamfer Matching by Learning Chamfer Distance Normalization	claim
124	88	Joint Estimation of Motion, Structure and Geometry from Stereo Sequences	claim
125	88	Disparity statistics for pedestrian detection: Combining appearance, motion, and stereo	claim
126	87	Piecewise Quadratic Reconstruction of Non-Rigid Surfaces from Monocular Sequences	claim
127	87	Adapting Visual Category Models to New Domains	claim
128	86	Photo-consistent Planar Patches from Unstructured Cloud of Points	claim
129	86	Discriminative Nonorthogonal Binary Subspace Tracking	claim
130	86	Hough Transform and 3D SURF for robust three dimensional classification	claim
131	85	Robust Multi-View Boosting with Priors	claim
132	85	Probabilistic Deformable Surface Tracking From Multiple Videos	claim
133	84	Face Liveness Detection from A Single Image with Sparse Low Rank Bilinear Discriminative Model	claim
134	84	Feature tracking for wide-baseline image retrieval	claim
135	84	Binary coherent edge descriptors	claim
136	84	Descattering Transmission via Angular Filtering	claim
137	83	A Fast Dual Method for HIK SVM Learning	claim
138	83	Shape Analysis of Planar Objects with Arbitrary Topologies using Conformal Geometry	claim
139	83	Anomalous Behaviour Detection using Spatiotemporal Oriented Energies, Subset Inclusion Histogram Comparison and Event-Driven Processing	claim
140	83	Manifold Valued Statistics, Exact Principal Geodesic Analysis and the Effect of Linear Approximations	claim
141	82	Bundle Adjustment in the Large	claim
142	82	Shape from Second-bounce of Light Transport	claim
143	81	Combining Geometric and Appearance Priors for Robust Homography Estimation	claim
144	80	Visibility Subspaces: Uncalibrated Photometric Stereo with Shadows	claim
145	80	Crowd Detection with a Multiview Sampler	claim
146	80	Image Classification Using Super-Vector Coding of Local Image Descriptors	claim
147	80	Video Synchronization Using Temporal Signals from Epipolar Lines	claim
148	79	Convolutional learning of spatio-temporal features	claim
149	79	Human Attributes from 3D Pose Tracking	claim
150	79	Cascaded Models for Articulated Pose Estimation	claim
151	79	Emotion Recognition from Arbitrary View Facial Images	claim
152	79	Multiple Hypothesis Video Segmentation from Superpixel Flows	claim
153	79	Efficient Inference with Multiple Heterogeneous Part Detectors for Human Pose Estimation	claim
154	79	Discriminative Learning with Latent Variables for Cluttered Indoor Scene Understanding	claim
155	79	Randomized Locality Sensitive Vocabularies for Bag-of-Features Model	claim
156	78	Superpixels and Supervoxels in an Energy Optimization Framework	claim
157	78	Seeing People in Social Context: Recognizing People and Social Relationships
158	78	Compressive Acquisition of Dynamic Scenes	claim
159	77	Discriminative Tracking by Metric Learning	claim
160	77	Geometric Constraints for Human Detection in Aerial Imagery	claim
161	77	An Efficient Graph Cut Algorithm for Computer Vision Problems	claim
162	76	Predicting Facial Beauty without Landmarks	claim
163	76	An Oriented Flux Symmetry Based Active Contour Model for Three Dimensional Vessel Segmentation	claim
164	75	Colorization for Single Image Super Resolution	claim
165	74	3D Point Correspondence by Minimum Description Length in Feature Space	claim
166	74	Hybrid Compressive Sampling via a New Total Variation TVL1	claim
167	74	A Stochastic Graph Evolution Framework for Robust Multi-Target Tracking	claim
168	73	Learning Relations Among Movie Characters: A Social Network Perspective	claim
169	73	Converting Level Set Gradients to Shape Gradients	claim
170	73	Modeling and Analysis of Dynamic Behaviors of Web Image Collections	claim
171	73	Practical Methods For Convex Multi-View Reconstruction	claim
172	73	BRIEF: Binary Robust Independent Elementary Features	claim
173	73	What Does Classifying More Than 10, 000 Image Categories Tell Us?	claim
174	72	The Semi-Explicit Shape Model for Multi-object Detection and Classification	claim
175	72	Ring-Light Photometric Stereo	claim
176	72	Weakly-Paired Maximum Covariance Analysis for Multimodal Dimensionality Reduction and Transfer Learning	claim
177	72	Learning Shape Segmentation Using Constrained Spectral Clustering and Probabilistic Label Transfer	claim
178	72	Learning Pre-attentive Driving Behaviour from Holistic Visual Features	claim
179	72	Transferring Visual Category Models to New Domains	claim
180	71	Exploiting loops in the graph of trifocal tensors for calibrating a network of cameras	claim
181	71	Error-tolerant Image Compositing	claim
182	71	Discovering Multipart Appearance Models from Captioned Images	claim
183	71	Tensor Sparse Coding for Region Covariances	claim
184	71	Visual Recognition With Humans in the Loop	claim
185	70	A Novel Parameter Estimation Algorithm for the Multivariate t-Distribution and Its Application to Computer	claim
186	70	Bilinear Kernel Reduced Rank Regression for Facial Expression Synthesis	claim
187	70	A Robust and Scalable Approach to Face Identification	claim
188	70	Joint People, Event, and Location Recognition in Personal Photo Collections using Cross-Domain Context	claim
189	69	Max-Margin Dictionary Learning for Multiclass Image Categorization	claim
190	69	Aligning Spatio-Temporal Signals on a Special Manifold	claim
191	68	Disparity Statistics for Pedestrian Detection: Combining Appearance, Motion and Stereo	claim
192	68	Representing Pairwise Spatial and Temporal Relations for Action Recognition	claim
193	68	Efficient object category recognition using classemes	claim
194	68	Chrono-Gait Image: A Novel Temporal Template for Gait Recognition	claim
195	67	Descriptor Learning for Efficient Retrieval	claim
196	67	Contour Grouping and Abstraction using Simple Part Models	claim
197	67	Fast dynamic texture detection	claim
198	67	Exploring Ambiguities for Monocular Non-Rigid Shape Estimation	claim
199	67	Convex Relaxation for Multilabel Problems with Product Label Spaces	claim
200	66	Energy Minimization Under Constraints on Label Counts	claim
201	66	Optimizing Complex Loss Functions in Structured Prediction	claim
202	66	Face Image Relighting using Locally Constrained Global Optimization	claim
203	66	Non-local Characterization of Scenery Images: Statistics, 3D Reasoning, and a Generative Model	claim
204	65	Enhancing Interactive Image Segmentation with Automatic Label Set Augmentation	claim
205	65	Self-Adapting Feature Layers	claim
206	64	A coarse-to-fine taxonomy of constellations for fast multi-class object detection	claim
207	64	Velocity-Dependent Shutter Sequences for Motion Deblurring	claim
208	64	Partition Min-Hash for Partial Duplicate Image Discovery	claim
209	64	Articulation-Invariant Representation of Non-planar Shapes	claim
210	64	Supervised Label Transfer for Semantic Segmentation of Street Scenes	claim
211	63	Programmable Aperture Photography	claim
212	63	Correlation-based intrinsic image extraction from a single image	claim
213	63	Image Invariants for Smooth Reflective Surfaces	claim
214	62	Optimal Contour Closure by Superpixel Grouping	claim
215	62	Learning PDEs for Image Restoration via Optimal Control	claim
216	62	Automatic Attribute Discovery and Characterization	claim
217	61	Sequential Non-Rigid Structure-from-Motion with the 3D-Implicit Low-Rank Shape Model	claim
218	61	Co-transduction for Shape Retrieval	claim
219	61	Clustering Complex Data with Group-Dependent Feature Selection	claim
220	61	Conjugate Gradient Bundle Adjustment	claim
221	60	Practical Autocalibration	claim
222	60	Semantic Label Sharing for Learning with Many Categories	claim
223	60	Membrane Nonrigid Image Registration	claim
224	60	Simultaneous Segmentation and Figure/Ground Organization using Angular Embedding	claim
225	59	Towards More Efficient and Effective LP-based algorithms for MRF Optimization	claim
226	59	Intrinsic Regularity Detection in 3D Geometry	claim
227	59	Activities as Time Series of Human Postures	claim
228	59	Object of Interest Detection by Saliency Learning	claim
229	59	Towards Computational Models of Visual Aesthetic Appeal of Consumer Videos	claim
230	58	Fast and Exact Primal-Dual Iterations for Variational Problems in Computer Vision	claim
231	57	Inter-Camera Association of Multi-Target Tracks by On-line Learned Appearance Affinity Models	claim
232	57	Exploiting Repetitive Object Patterns for Model Compression and Completion	claim
233	57	Flexible Voxels for Motion-Aware Videography	claim
234	57	Efficient Non-Consecutive Feature Tracking for Structure-from-Motion	claim
235	56	Coupled Gaussian Process Regression for Pose-Invariant Facial Expression Recognition	claim
236	55	Adaptive Metric Registration of 3D Models to Non-rigid Image Trajectories	claim
237	55	Fast Optimization for Mixture Prior Models	claim
238	55	Spatial-Temporal Granularity-Tunable Gradients Partition (STGGP) Descriptors for Human Detection	claim
239	54	Avoiding confusing features in place recognition	claim
240	53	Loosely Distinctive Features for Robust Surface Alignment	claim
241	53	Learning Artistic Lighting Template from Portrait Photographs	claim
242	52	Unique Signatures of Histograms for Local Surface Description	claim
243	51	From a Set of Shapes to Object Discovery	claim
244	51	Lighting Aware Preprocessing for Face Recognition across Varying Illumination	claim
245	51	Weakly-Paired Maximum Covariance Analysis for Multimodal Dimensionality Reduction and Transfer	claim
246	50	Element-Wise Factorization for N-View Projective Reconstruction	claim
247	49	Archive Film Restoration Based on Spatiotemporal Random Walks	claim
248	49	Modeling the Temporal Extent of Actions	claim
249	47	Extrinsic camera calibration using multiple reflections	claim
250	46	Optimum Subspace Learning and Error Correction for Tensors	claim
251	45	Photometric Stereo for Dynamic Surface Orientations	claim

Sciweavers

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers