Computer Vision -- ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part I [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.

Visual Tracking by Sampling Tree-Structured Graphical Models.-?Tracking Interacting Objects Optimally Using Integer Programming.-?Learning Latent Constituents for Recognition of Group Activities in Video.-?Large-Scale Object Classification Using Label Relation Graphs.-?30Hz Object Detection with DPM V5.-?Knowing a Good HOG Filter when You See It: Efficient Selection of Filters for Detection.-?Linking People in Videos with Their Names Using Coreference Resolution.-?Optimal Essential Matrix Estimation via Inlier-Set Maximization.-?UPnP: An Optimal O(n) Solution to the Absolute Pose Problem with Universal Applicability.-?3D Reconstruction of Dynamic Textures in Crowd Sourced Data.-?3D Interest Point Detection via Discriminative Learning.-?Pose Locality Constrained Representation for 3D Human Pose Reconstruction.-?Synchronization of Two Independently Moving Cameras without Feature Correspondences.- Multi Focus Structured Light for? ecovering Scene Shape and Global Illumination.-?Coplanar Common Points in Non-centric Cameras.-?SRA: Fast Removal of General Multipath for ToF Sensors.-?Sub-pixel Layout for Super-Resolution with Images in the Octic Group.-?Simultaneous Feature and Dictionary Learning for Image Set Based Face Recognition.-?Read My Lips: Continuous Signer Independent Weakly Supervised Viseme Recognition.-?MultilinearlS*