Computer Vision -- ECCV 2014

Coarse-to-Fine Auto-Encoder Networks (CFAN) for Real-Time Face Alignment.- From Manifold to Manifold: Geometry-Aware Dimensionality Reduction for SPD Matrices.- Pose Machines: Articulated Pose Estimation via Inference Machines.- Piecewise-Planar StereoScan: Structure and Motion from Plane Primitives.- Nonrigid Surface Registration and Completion from RGBD Images.- Unsupervised Dense Object Discovery, Detection, Tracking and Reconstruction.- Know Your Limits: Accuracy of Long Range Stereoscopic Object Measurements in Practice.- As-Rigid-As-Possible Stereo under Second Order Smoothness Priors.- Real-Time Minimization of the Piecewise Smooth Mumford-Shah Functional.- A MAP-Estimation Framework for Blind Deblurring Using High-Level Edge Priors.- Efficient Color Constancy with Local Surface Reflectance Statistics.- A Contrast Enhancement Framework with JPEG Artifacts Suppression.- Radial Bright Channel Prior for Single Image Vignetting Correction.- Tubular Structure Filtering by RankingOrientation Responses of Path Operators.- Optimization-Based Artifact Correction for Electron Microscopy Image Stacks.- Metric-Based Pairwise and Multiple Image Registration.- Canonical Correlation Analysis on Riemannian Manifolds and Its Applications.- Scalable 6-DOF Localization on Mobile Devices.- On Mean Pose and Variability of 3D Deformable Models.- Hybrid Stochastic / Deterministic Optimization for Tracking Sports Players and Pedestrians.- What Do I See? Modeling Human Visual Perception for Multi-person Tracking.- Consistent Re-identification in a Camera Network.- Surface Normal Deconvolution: Photometric Stereo for Optically Thick Translucent Objects.- Intrinsic Video.- Robust and Accurate Non-parametric Estimation of Reflectance Using Basis Decomposition and Correction Functions.- Intrinsic Textures for Relightable Free-Viewpoint Video.- Reasoning about Object Affordances in a Knowledge Base Representation.- Binary Codes Embedding for Fast Image Tagging with Incomplete Labels.- Recognizing Products: A Per-exemplar Multi-label Image Classification Approach.- Part-Pair Representation for Part Localization.- Weakly Supervised Learning of Objects, Attributes and Their Associations.- Interestingness Prediction by Robust Learning to Rank.- Pairwise Probabilistic Voting: Fast Place Recognition without RANSAC.- Robust Instance Recognition in Presence of Occlusion and Clutter.- Learning 6D Object Pose Estimation Using 3D Object Coordinates.- Growing Regression Forests by Classification: Applications to Object Pose Estimation.- Stacked Deformable Part Model with Shape Regression for Object Part Localization.- Transductive Multi-view Embedding for Zero-Shot Recognition and Annotation.- Self-explanatory Sparse Representation for Image Classification.- Efficient k-Support Matrix Pursuit.- Geodesic Regression on the Grassmannian.- Model Selection by Linear Programming.- Perceptually Inspired Layout-Aware Losses for Image Segmentation.- Large Margin Local Metric Learning.- Movement Pattern Histogram for Action Recognition and Retrieval.- Pose Filter Based Hidden-CRF Models for Activity Detection.- Action Recognition Using Super Sparse Coding Vector with Spatio-temporal Awareness.- HOPC: Histogram of Oriented Principal Components of 3D Pointclouds for Action Recognition.- Natural Action Recognition Using Invariant 3D Motion Encoding.- Detecting Social Actions of Fruit Flies.- Progressive Mode-Seeking on Graphs for Sparse Feature Matching.- Globally Optimal Inlier Set Maximization with Unknown Rotation and Focal Length.- Match Selection and Refinement for Highly Accurate Two-View Structure from Motion.- LSD-SLAM: Large-Scale Direct Monocular SLAM.