New York: Springer, 2012. 889 p.Oral Session 5: MRFs and Early Vision. Diverse M-Best Solutions in Markov Random Fields. Generic Cuts: An Eﬃcient Algorithm for Optimal Inference in Higher Order MRF-MAP. Filter-BasedMean-Field Inference for Random Fields with Higher-OrderTerms and Product Label-Spaces. Continuous Markov Random Fields for Robust Stereo Estimation. Good Regions to Deblur. Patch Complexity, Finite Pixel Correlations and Optimal Denoising. Poster Session 6. Guaranteed Ellipse Fitting with the Sampson Distance. A Locally Linear Regression Model for Boundary Preserving Regularization in Stereo Matching. A Novel Fast Method for L∞ Problems in Multiview Geometry. Visibility Probability Structure from SfM Datasets and Applications. A Generative Model for Online Depth Fusion. Depth Recovery Using an Adaptive Color-Guided Auto-Regressive Model. Learning Hybrid Part Filters for Scene Recognition. Parametric Manifold of an Object under Diﬀerent Viewing Directions. Fast Approximations to Structured Sparse Coding and Applications to Object Classiﬁcation. Displacement Template with Divide-&-Conquer Algorithm for Signiﬁcantly Improving Descriptor Based Face Recognition Approaches Latent Pyramidal Regions for Recognizing Scenes. Augmented Attribute Representations. Exploring the Spatial Hierarchy of Mixture Models for Human Pose Estimation. People Orientation Recognition by Mixtures of Wrapped Distributions on Random Trees. Hybrid Classiﬁers for Object Classiﬁcation with a Rich Background. Unsupervised and Supervised Visual Codes with Restricted Boltzmann Machines. A New Biologically Inspired Color Image Descriptor. Finding Correspondence from Multiple Images via Sparse and Low-Rank Decomposition. Multidimensional Spectral Hashing. What Makes a Good Detector? – Structured Priors for Learning from Few Examples. A Convolutional Treelets Binary Feature Approach to Fast Keypoint Recognition. Categorizing Turn-Taking Interactions. Local Expert Forest of Score Fusion for Video Event Classiﬁcation. View-Invariant Action Recognition Using Latent Kernelized Structural SVM. Trajectory-Based Modeling of Human Actions with Motion Reference Points. PatchMatchGraph: Building a Graph of Dense Patch Correspondences for Label Transfer. A Unifying Theory of Active Discovery and Learning. Extracting 3D Scene-Consistent Object Proposals and Depth from Stereo Images. Repairing Sparse Low-Rank Texture. Active Frame Selection for Label Propagation in Videos. Non-causal Temporal Prior for Video Deblocking. Text Image Deblurring Using Text-Speciﬁc Properties. Sequential Spectral Learning to Hash with Multiple Representations. Two-Granularity Tracking: Mediating Trajectory and Detection Graphs for Tracking under Occlusions. Taking Mobile Multi-object Tracking to the Next Level: People, Unknown Objects, and Carried Items. Dynamic Context for Tracking behind Occlusions. To Track or To Detect? An Ensemble Framework for Optimal Selection. Spatial and Angular Variational Super-Resolution of 4D Light Fields. Blur-Kernel Estimation from Spectral Irregularities. Deconvolving PSFs for a Better Motion Deblurring Using Multiple Images. Depth and Deblurring from a Spectrally-Varying Depth-of-Field. Segmentation over Detection by Coupled Global and Local Sparse Representations. Moving Object Segmentation Using Motor Signals. Block-Sparse RPCA for Consistent Foreground Detection. A Generative Model for Simultaneous Estimation of Human Body Shape and Pixel-Level Segmentation. Visual Dictionary Learning for Joint Object Categorization and Segmentation. Oral Session 6: Geometry and Recognition. People Watching: Human Actions as a Cue for Single View Geometry. Indoor Segmentation and Support Inference from RGBD Images. Beyond the Line of Sight: Labeling the Underlying Surfaces. Depth Extraction from Video Using Non-parametric Sampling. Multiple View Object Cosegmentation Using Appearance and Stereo Cues. Poster Session 7. Elastic Shape Matching of Parameterized Surfaces Using Square Root Normal Fields. N-tuple Color Segmentation for Multi-view Silhouette Extraction. Motion-Aware Structured Light Using Spatio-Temporal Decodable Patterns. Refractive Calibration of Underwater Cameras. Detection of Independently Moving Objects in Non-planar Scenes via Multi-Frame Monocular Epipolar Constraint.
Чтобы скачать этот файл зарегистрируйтесь и/или войдите на сайт используя форму сверху.