Computer Vision -- Eccv 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part VII

ISBN-13: 9783319105833 / Angielski / Miękka / 2014 / 658 str.

David Fleet; Tomas Pajdla; Bernt Schiele

Opis

The seven-volume set comprising LNCS volumes 8689-8695 constitutes the refereed proceedings of the 13th European Conference on Computer Vision, ECCV 2014, held in Zurich, Switzerland, in September 2014. 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.

Spis treści

Person Re-Identification Using Kernel-Based Metric Learning Methods.- Saliency in Crowd.- Webpage Saliency.- Deblurring Face Images with Exemplars.- Sparse Spatio-spectral Representation for Hyperspectral Image Super-resolution.- Hybrid Image Deblurring by Fusing Edge and Power Spectrum Information.- Affine Subspace Representation for Feature Description.- A Generative Model for the Joint Registration of Multiple Point Sets.- Change Detection in the Presence of Motion Blur and Rolling Shutter Effect.- An Analysis of Errors in Graph-Based Keypoint Matching and Proposed Solutions.- OpenDR: An Approximate Differentiable Renderer.- A Superior Tracking Approach: Building a Strong Tracker through Fusion.- Training-Based Spectral Reconstruction from a Single RGB Image.- On Shape and Material Recovery from Motion.- Intrinsic Image Decomposition Using Structure-Texture Separation and Surface Normals.- Multi-level Adaptive Active Learning for Scene Classification.- Graph Cuts for Supervised Binary Coding.- Planar Structure Matching under Projective Uncertainty for Geolocation.- Active Deformable Part Models Inference.- Simultaneous Detection and Segmentation.- Learning Graphs to Model Visual Objects across Different Depictive Styles.- Analyzing the Performance of Multilayer Neural Networks for Object Recognition.- Learning Rich Features from RGB-D Images for Object Detection and Segmentation.- Scene Classification via Hypergraph-Based Semantic Attributes Subnetworks Identification.- OTC: A Novel Local Descriptor for Scene Classification.- Multi-scale Orderless Pooling of Deep Convolutional Activation Features.- Expanding the Family of Grassmannian Kernels: An Embedding Perspective.- Image Tag Completion by Noisy Matrix Recovery.- ConceptMap: Mining Noisy Web Data for Concept Learning.- Shrinkage Expansion Adaptive Metric Learning.- Salient Montages from Unconstrained Videos.- Action-Reaction: Forecasting the Dynamics of Human Interaction.- Creating Summaries from User Videos.- Spatiotemporal Background Subtraction Using Minimum Spanning Tree and Optical Flow.- Robust Foreground Detection Using Smoothness and Arbitrariness Constraints.- Video Object Co-segmentation by Regulated Maximum Weight Cliques.- Dense Semi-rigid Scene Flow Estimation from RGBD Images.- Video Pop-up: Monocular 3D Reconstruction of Dynamic Scenes.- Joint Object Class Sequencing and Trajectory Triangulation (JOST).- Scene Chronology.