Computer Vision -- ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V [Paperback]

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.Video 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.- TraininglÓ.