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.
Table of ContentsVideo Registration to SfM Models.- Soft Cost Aggregation with Multi-resolution Fusion.- Inverse Kernels for Fast Spatial Deconvolution.- Deep Network Cascade for Image Super-resolution.- Spectral Edge Image Fusion: Theory and Applications.- Spatio-chromatic Opponent Features.- Modeling Perceptual Color Differences by Local Metric Learning.- Online Graph-Based Tracking.- Fast Visual Tracking via Dense Spatio-temporal Context Learning.- Extended Lucas-Kanade Tracking.- Appearances Can Be Deceiving: Learning Visual Tracking from Few Trajectory Annotations.- Generalized Background Subtraction Using Superpixels with Label Integrated Motion Estimation.- Spectra Estimation of Fluorescent and Reflective Scenes by Using Ordinary Illuminants.- Interreflection Removal Using Fluorescence.- Intrinsic Face Image Decomposition with Human Face Priors.- Recovering Scene Geometry under Wavy Fluid via Distortion and Defocus Analysis.- Human Detection Using Learned Part Alphabet and Pose Dictionary.- SPADE: Scalar Product Accelerator by Integer Decomposition for Object Detection.- Detecting Snap Points in Egocentric Video with a Web Photo Prior.- Towards Unified Object Detection and Semantic Segmentation.- Foreground Consistent Human Pose Estimation Using Branch and Bound.- Human Pose Estimation with Fields of Parts.-Unsupervised Video Adaptation for Parsing Human Motion.- Training Object Class Detectors from Eye Tracking Data.- Symmetric Objects.- Edge Boxes: Locating Object Proposals from Edges.- Training Deformable Object Models for Human Detection Based on Alignment and Clustering.- Predicting Actions from Static Scenes.- Exploiting Privileged Information from Web Data for Image Categorization.- Multi-modal Unsupervised Feature Learning for RGB-D Scene Labeling.- Discriminatively Trained Dense Surface Normal Estimation.- Numerical Inversion of SRNFs for Efficient Elastic Shape Analysis of Star-Shaped Objects Classification.- Learning Where to Classify in Multi-view Semantic Segmentation.- Semantics: A Medium-Level Model for Real-Time Semantic Scene Understanding.- Sparse Dictionaries for Semantic Segmentation.- Video Action Detection with Relational Dynamic-Poselets.- Action Recognition with Stacked Fisher Vectors.- A Discriminative Model with Multiple Temporal Scales for Action Prediction.- Seeing is Worse than Believing: Reading People’s Minds Better than Computer-Vision Methods Recognize Actions.- Weakly Supervised Action Labeling in Videos under Ordering Constraints.- Active Random Forests: An Application to Autonomous Unfolding of Clothes.- Model-Free Segmentation and Grasp Selection of Unknown Stacked Objects.- Convexity Shape Prior for Segmentation.- Pseudo-bound Optimization for Binary Energies.- A Closer Look at Context: From Coxels to the Contextual Emergence of Object Saliency.- Geodesic Object Proposals.- Microsoft COCO: Common Objects in Context.- Efficient Joint Segmentation, Occlusion Labeling, Stereo and Flow Estimation.- Robust Bundle Adjustment Revisited.- Accurate Intrinsic Calibration of Depth Camera with Cuboids.- Statistical Pose Averaging with Non-isotropic and Incomplete Relative Measurements.- A Pot of Gold: Rainbows as a Calibration Cue.- Let There Be Color! Large-Scale Texturing of 3D Reconstructions.