Raghavender will present “Indoor Place Recognition System for Localization of Mobile Robots” at 13th Conference on Conference on Computer and Robot Vision 2016
Authors: Calden Wloka and John Tsotsos
Title: Spatially Binned ROC: A Comprehensive Saliency Metric
Abstract: A recent trend in saliency algorithm development is large-scale benchmarking and algorithm ranking with ground truth provided by datasets of human fixations. In order to accommodate the strong bias humans have toward central fixations, it is common to replace traditional ROC metrics with a shuffled ROC metric which uses randomly sampled fixations from other images in the database as the negative set. However, the shuffled ROC introduces a number of problematic elements, including a fundamental assumption that it is possible to separate visual salience and image spatial arrangement.