Computer Vision -- ECCV 2014
Description
The 363 revised papers presented were carefully reviewed and selected from 1444 submissions. The papers are organized in topical sections on tracking and activity recognition; recognition; learning and inference; structure from motion and feature matching; computational photography and low-level vision; vision; segmentation and saliency; context and 3D scenes; motion and 3D scene analysis; and poster sessions.
More details
Other editions
Additional editions
Content
Schwarps: Locally Projective Image Warps Based on 2D Schwarzian Derivatives.- gDLS: A Scalable Solution to the Generalized Pose and Scale Problem.- Generalized Connectivity Constraints for Spatio-temporal 3D Reconstruction.- Passive Tomography of Turbulence Strength.- A Non-local Method for Robust Noisy Image Completion.- Improved Motion Invariant Deblurring through Motion Estimation.- Consistent Matting for Light Field Images.- Consensus of Regression for Occlusion-Robust Facial Feature Localization.- Learning the Face Prior for Bayesian Face Recognition.- Spatio-temporal Event Classification Using Time-Series Kernel Based Structured Sparsity.- Feature Disentangling Machine - A Novel Approach of Feature Selection and Disentangling in Facial Expression Analysis.- Joint Unsupervised Face Alignment and Behaviour Analysis.- Learning a Deep Convolutional Network for Image Super-Resolution.- Discriminative Indexing for Probabilistic Image Patch Priors.- Modeling Video Dynamics with DeepDynencoder.- Good Image Priors for Non-blind Deconvolution: Generic vs. Specific.- Image Deconvolution Ringing Artifact Detection and Removal via PSF Frequency Analysis.- View-Consistent 3D Scene Flow Estimation over Multiple Frames.- Hand Waving Away Scale.- A Non-Linear Filter for Gyroscope-Based Video Stabilization.- Multi-modal and Multi-spectral Registration for Natural Images.- Using Isometry to Classify Correct/Incorrect 3D-2D Correspondences.- Bilateral Functions for Global Motion Modeling.- VCDB: A Large-Scale Database for Partial Copy Detection in Videos.- Single-Image Super-Resolution: A Benchmark.- Well Begun Is Half Done: Generating High-Quality Seeds for Automatic Image Dataset Construction from Web.- Zero-Shot Learning via Visual Abstraction.- Discovering Groups of People in Images.- Untangling Object-View Manifold for Multiview Recognition and Pose Estimation.- Parameterizing Object Detectors in the Continuous Pose Space.- Jointly Optimizing 3D Model Fitting andFine-Grained Classification.- Pipelining Localized Semantic Features for Fine-Grained Action Recognition.- Robust Scene Text Detection with Convolution Neural Network Induced MSER Trees.- Deep Features for Text Spotting.- Improving Image-Sentence Embeddings Using Large Weakly Annotated Photo Collections.- Strengthening the Effectiveness of Pedestrian Detection with Spatially Pooled Features.- Selecting Influential Examples: Active Learning with Expected Model Output Changes.- Efficient Sparsity Estimation via Marginal-Lasso Coding.- Continuous Conditional Neural Fields for Structured Regression.- Learning to Rank Using High-Order Information.- Support Vector Guided Dictionary Learning.- Video Object Discovery and Co-segmentation with Extremely Weak Supervision.- Supervoxel-Consistent Foreground Propagation in Video.- Clustering with Hypergraphs: The Case for Large Hyperedges.- Person Re-identification by Video Ranking.- Bayesian Nonparametric Intrinsic Image Decomposition.- Face Detection without Bells and Whistles.- On Image Contours of Projective Shapes.- Programmable Automotive Headlights.- ROCHADE: Robust Checkerboard Advanced Detection for Camera Calibration.- Correcting for Duplicate Scene Structure in Sparse 3D Reconstruction.- Total Moving Face Reconstruction.- Automatic Single-View Calibration and Rectification from Parallel Planar Curves.- On Sampling Focal Length Values to Solve the Absolute Pose Problem.
