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.With this cost function, our Unified Robust Learning to Rank (URLR) framework identifies outliers globally by integrating all local pairwise comparison together. ... 1(a) shows that among the five compared pairs, majority voting can successfully identify four outlier cases: Aagt;B, Bagt;C, Cagt;D, ... edges B a A, C a B, D a C, and E a D, which are accumulated into much bigger global inconsistency with the annotation. ... Green arrows indicate correct annotations, while red arrows are outliers.
|Title||:||Computer Vision -- ECCV 2014|
|Author||:||David Fleet, Tomas Pajdla, Bernt Schiele, Tinne Tuytelaars|
|Publisher||:||Springer - 2014-08-14|