Speaker: Frédéric Jurie, professor at Université de Caen, Caen, France.
Abstract: This talk will summarize the work presented in two recent papers [1,2], where we introduce a novel image representation capturing feature dependencies through the mining of meaningful combinations of visual features. This representation leads to a compact and discriminative encoding of images that can be used for image classification, object detection, object recognition or even image re-ranking. The method relies on (i) multiple random projections of the input space followed by local binarization of projected histograms encoded as sets of items, and (ii) the representation of images as Histograms of Pattern Sets (HoPS). The approach is validated on four publicly available datasets (Daimler Pedestrian Classification, Oxford flowers Classification, KTH Texture Categorization, PASCAL VOC2007), allowing comparisons with many recent approaches. The proposed image representation reaches state-of-the-art performance on each of these datasets. We will also present an efficient framework for image re-reanking based on the same image representation. References: