Ebook: Computer Vision – ECCV 2012: 12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012, Proceedings, Part III

The seven-volume set comprising LNCS volumes 7572-7578 constitutes the refereed proceedings of the 12th European Conference on Computer Vision, ECCV 2012, held in Florence, Italy, in October 2012. The 408 revised papers presented were carefully reviewed and selected from 1437 submissions. The papers are organized in topical sections on geometry, 2D and 3D shapes, 3D reconstruction, visual recognition and classification, visual features and image matching, visual monitoring: action and activities, models, optimisation, learning, visual tracking and image registration, photometry: lighting and colour, and image segmentation.

---

The seven-volume set comprising LNCS volumes 7572-7578 constitutes the refereed proceedings of the 12th European Conference on Computer Vision, ECCV 2012, held in Florence, Italy, in October 2012. The 408 revised papers presented were carefully reviewed and selected from 1437 submissions. The papers are organized in topical sections on geometry, 2D and 3D shapes, 3D reconstruction, visual recognition and classification, visual features and image matching, visual monitoring: action and activities, models, optimisation, learning, visual tracking and image registration, photometry: lighting and colour, and image segmentation.

---

The seven-volume set comprising LNCS volumes 7572-7578 constitutes the refereed proceedings of the 12th European Conference on Computer Vision, ECCV 2012, held in Florence, Italy, in October 2012. The 408 revised papers presented were carefully reviewed and selected from 1437 submissions. The papers are organized in topical sections on geometry, 2D and 3D shapes, 3D reconstruction, visual recognition and classification, visual features and image matching, visual monitoring: action and activities, models, optimisation, learning, visual tracking and image registration, photometry: lighting and colour, and image segmentation.
Content:
Front Matter....Pages -
Polynomial Regression on Riemannian Manifolds....Pages 1-14
Approximate Gaussian Mixtures for Large Scale Vocabularies....Pages 15-28
Geodesic Saliency Using Background Priors....Pages 29-42
Joint Face Alignment with Non-parametric Shape Models....Pages 43-56
Discriminative Bayesian Active Shape Models....Pages 57-70
Patch Based Synthesis for Single Depth Image Super-Resolution....Pages 71-84
Annotation Propagation in Large Image Databases via Dense Image Correspondence....Pages 85-99
Numerically Stable Optimization of Polynomial Solvers for Minimal Problems....Pages 100-113
Has My Algorithm Succeeded? An Evaluator for Human Pose Estimators....Pages 114-128
Group Tracking: Exploring Mutual Relations for Multiple Object Tracking....Pages 129-143
A Discrete Chain Graph Model for 3d+t Cell Tracking with High Misdetection Robustness....Pages 144-157
Robust Tracking with Weighted Online Structured Learning....Pages 158-172
Fast Regularization of Matrix-Valued Images....Pages 173-186
Blind Correction of Optical Aberrations....Pages 187-200
Inverse Rendering of Faces on a Cloudy Day....Pages 201-214
On Tensor-Based PDEs and Their Corresponding Variational Formulations with Application to Color Image Denoising....Pages 215-228
Kernelized Temporal Cut for Online Temporal Segmentation and Recognition....Pages 229-243
Grain Segmentation of 3D Superalloy Images Using Multichannel EWCVT under Human Annotation Constraints....Pages 244-257
Hough Regions for Joining Instance Localization and Segmentation....Pages 258-271
Learning to Segment a Video to Clips Based on Scene and Camera Motion....Pages 272-286
Evaluation of Image Segmentation Quality by Adaptive Ground Truth Composition....Pages 287-300
Exact Acceleration of Linear Object Detectors....Pages 301-311
Latent Hough Transform for Object Detection....Pages 312-325
Using Linking Features in Learning Non-parametric Part Models....Pages 326-339
Diagnosing Error in Object Detectors....Pages 340-353
Attributes for Classifier Feedback....Pages 354-368
Constrained Semi-Supervised Learning Using Attributes and Comparative Attributes....Pages 369-383
Renormalization Returns: Hyper-renormalization and Its Applications....Pages 384-397
Scale Robust Multi View Stereo....Pages 398-411
Laplacian Meshes for Monocular 3D Shape Recovery....Pages 412-425
Soft Inextensibility Constraints for Template-Free Non-rigid Reconstruction....Pages 426-440
Spatiotemporal Descriptor for Wide-Baseline Stereo Reconstruction of Non-rigid and Ambiguous Scenes....Pages 441-454
Elevation Angle from Reflectance Monotonicity: Photometric Stereo for General Isotropic Reflectances....Pages 455-468
Local Log-Euclidean Covariance Matrix (L2ECM) for Image Representation and Its Applications....Pages 469-482
Ensemble Partitioning for Unsupervised Image Categorization....Pages 483-496
Set Based Discriminative Ranking for Recognition....Pages 497-510
A Global Hypotheses Verification Method for 3D Object Recognition....Pages 511-524
Are You Really Smiling at Me? Spontaneous versus Posed Enjoyment Smiles....Pages 525-538
Efficient Monte Carlo Sampler for Detecting Parametric Objects in Large Scenes....Pages 539-552
Supervised Geodesic Propagation for Semantic Label Transfer....Pages 553-565
Bayesian Face Revisited: A Joint Formulation....Pages 566-579
Beyond Bounding-Boxes: Learning Object Shape by Model-Driven Grouping....Pages 580-593
In Defence of Negative Mining for Annotating Weakly Labelled Data....Pages 594-608
Describing Clothing by Semantic Attributes....Pages 609-623
Graph Matching via Sequential Monte Carlo....Pages 624-637
Jet-Based Local Image Descriptors....Pages 638-650
Abnormal Object Detection by Canonical Scene-Based Contextual Model....Pages 651-664
Shapecollage: Occlusion-Aware, Example-Based Shape Interpretation....Pages 665-678
Interactive Facial Feature Localization....Pages 679-692
Propagative Hough Voting for Human Activity Recognition....Pages 693-706
Spatio-Temporal Phrases for Activity Recognition....Pages 707-721
Complex Events Detection Using Data-Driven Concepts....Pages 722-735
Directional Space-Time Oriented Gradients for 3D Visual Pattern Analysis....Pages 736-749
Learning to Recognize Unsuccessful Activities Using a Two-Layer Latent Structural Model....Pages 750-763
Action Recognition Using Subtensor Constraint....Pages 764-777
Globally Optimal Closed-Surface Segmentation for Connectomics....Pages 778-791
Reduced Analytical Dependency Modeling for Classifier Fusion....Pages 792-805
Learning to Match Appearances by Correlations in a Covariance Metric Space....Pages 806-820
On the Convergence of Graph Matching: Graduated Assignment Revisited....Pages 821-835
Image Annotation Using Metric Learning in Semantic Neighbourhoods....Pages 836-849
Dynamic Programming for Approximate Expansion Algorithm....Pages 850-863
Real-Time Compressive Tracking....Pages 864-877
Back Matter....Pages -

---

The seven-volume set comprising LNCS volumes 7572-7578 constitutes the refereed proceedings of the 12th European Conference on Computer Vision, ECCV 2012, held in Florence, Italy, in October 2012. The 408 revised papers presented were carefully reviewed and selected from 1437 submissions. The papers are organized in topical sections on geometry, 2D and 3D shapes, 3D reconstruction, visual recognition and classification, visual features and image matching, visual monitoring: action and activities, models, optimisation, learning, visual tracking and image registration, photometry: lighting and colour, and image segmentation.
Content:
Front Matter....Pages -
Polynomial Regression on Riemannian Manifolds....Pages 1-14
Approximate Gaussian Mixtures for Large Scale Vocabularies....Pages 15-28
Geodesic Saliency Using Background Priors....Pages 29-42
Joint Face Alignment with Non-parametric Shape Models....Pages 43-56
Discriminative Bayesian Active Shape Models....Pages 57-70
Patch Based Synthesis for Single Depth Image Super-Resolution....Pages 71-84
Annotation Propagation in Large Image Databases via Dense Image Correspondence....Pages 85-99
Numerically Stable Optimization of Polynomial Solvers for Minimal Problems....Pages 100-113
Has My Algorithm Succeeded? An Evaluator for Human Pose Estimators....Pages 114-128
Group Tracking: Exploring Mutual Relations for Multiple Object Tracking....Pages 129-143
A Discrete Chain Graph Model for 3d+t Cell Tracking with High Misdetection Robustness....Pages 144-157
Robust Tracking with Weighted Online Structured Learning....Pages 158-172
Fast Regularization of Matrix-Valued Images....Pages 173-186
Blind Correction of Optical Aberrations....Pages 187-200
Inverse Rendering of Faces on a Cloudy Day....Pages 201-214
On Tensor-Based PDEs and Their Corresponding Variational Formulations with Application to Color Image Denoising....Pages 215-228
Kernelized Temporal Cut for Online Temporal Segmentation and Recognition....Pages 229-243
Grain Segmentation of 3D Superalloy Images Using Multichannel EWCVT under Human Annotation Constraints....Pages 244-257
Hough Regions for Joining Instance Localization and Segmentation....Pages 258-271
Learning to Segment a Video to Clips Based on Scene and Camera Motion....Pages 272-286
Evaluation of Image Segmentation Quality by Adaptive Ground Truth Composition....Pages 287-300
Exact Acceleration of Linear Object Detectors....Pages 301-311
Latent Hough Transform for Object Detection....Pages 312-325
Using Linking Features in Learning Non-parametric Part Models....Pages 326-339
Diagnosing Error in Object Detectors....Pages 340-353
Attributes for Classifier Feedback....Pages 354-368
Constrained Semi-Supervised Learning Using Attributes and Comparative Attributes....Pages 369-383
Renormalization Returns: Hyper-renormalization and Its Applications....Pages 384-397
Scale Robust Multi View Stereo....Pages 398-411
Laplacian Meshes for Monocular 3D Shape Recovery....Pages 412-425
Soft Inextensibility Constraints for Template-Free Non-rigid Reconstruction....Pages 426-440
Spatiotemporal Descriptor for Wide-Baseline Stereo Reconstruction of Non-rigid and Ambiguous Scenes....Pages 441-454
Elevation Angle from Reflectance Monotonicity: Photometric Stereo for General Isotropic Reflectances....Pages 455-468
Local Log-Euclidean Covariance Matrix (L2ECM) for Image Representation and Its Applications....Pages 469-482
Ensemble Partitioning for Unsupervised Image Categorization....Pages 483-496
Set Based Discriminative Ranking for Recognition....Pages 497-510
A Global Hypotheses Verification Method for 3D Object Recognition....Pages 511-524
Are You Really Smiling at Me? Spontaneous versus Posed Enjoyment Smiles....Pages 525-538
Efficient Monte Carlo Sampler for Detecting Parametric Objects in Large Scenes....Pages 539-552
Supervised Geodesic Propagation for Semantic Label Transfer....Pages 553-565
Bayesian Face Revisited: A Joint Formulation....Pages 566-579
Beyond Bounding-Boxes: Learning Object Shape by Model-Driven Grouping....Pages 580-593
In Defence of Negative Mining for Annotating Weakly Labelled Data....Pages 594-608
Describing Clothing by Semantic Attributes....Pages 609-623
Graph Matching via Sequential Monte Carlo....Pages 624-637
Jet-Based Local Image Descriptors....Pages 638-650
Abnormal Object Detection by Canonical Scene-Based Contextual Model....Pages 651-664
Shapecollage: Occlusion-Aware, Example-Based Shape Interpretation....Pages 665-678
Interactive Facial Feature Localization....Pages 679-692
Propagative Hough Voting for Human Activity Recognition....Pages 693-706
Spatio-Temporal Phrases for Activity Recognition....Pages 707-721
Complex Events Detection Using Data-Driven Concepts....Pages 722-735
Directional Space-Time Oriented Gradients for 3D Visual Pattern Analysis....Pages 736-749
Learning to Recognize Unsuccessful Activities Using a Two-Layer Latent Structural Model....Pages 750-763
Action Recognition Using Subtensor Constraint....Pages 764-777
Globally Optimal Closed-Surface Segmentation for Connectomics....Pages 778-791
Reduced Analytical Dependency Modeling for Classifier Fusion....Pages 792-805
Learning to Match Appearances by Correlations in a Covariance Metric Space....Pages 806-820
On the Convergence of Graph Matching: Graduated Assignment Revisited....Pages 821-835
Image Annotation Using Metric Learning in Semantic Neighbourhoods....Pages 836-849
Dynamic Programming for Approximate Expansion Algorithm....Pages 850-863
Real-Time Compressive Tracking....Pages 864-877
Back Matter....Pages -
....