建模与费舍尔向量空间布局的图像分类(非数据).pdf

建模与费舍尔向量空间布局的图像分类（非数据） (Modeling Spatial Layout with Fisher Vectors for Image Categorization) 数据介绍： We introduce an extension of bag-of-words image representations to encode spatial layout. Using the Fisher kernel framework we derive a representation that encodes the spatial mean and the variance of image regions associated with visual words. We extend this representation by using a Gaussian mixture model to encode spatial layout, and show that this model is related to a soft-assign version of the spatial pyramid representation. We also combine our representation of spatial layout with the use of Fisher kernels to encode the appearance of local features. Through an extensive experimental evaluation, we show that our representation yields state-of-the-art image categorization results, while being more compact than spatial pyramid representations. In particular, using Fisher kernels to encode both appearance and spatial layout results in an image representation that is computationally efficient, compact, and yields excellent performance while using linear classifiers. 关键词： 形象,空间,编码,分类,计算, image,spatial,encodes,categorization,computationally, 数据格式： IMAGE 数据详细介绍： Modeling Spatial Layout with Fisher Vectors for Image Categorization Josip Krapac , Jakob Verbeek , Frédéric Jurie International Conference on Computer Vision (2011) • a – INRIA • 1: LEAR (INRIA Grenoble Rhône-Alpes / LJK Laboratoire Jean Kuntzmann) • http://lear.inrialpes.fr/ CNRS : FR71 – CNRS : UMR5527 – INRIA – Laboratoire Jean Kuntzmann – Université Joseph Fourier - Grenoble I – Institut National Polytechnique de Grenoble - INPG France • 2: Groupe de Recherche en Informatique, Image, Automatique et Instrumentation de Caen (GREYC) • http://www.greyc.unicaen.fr/ CNRS : UMR6072 – Université de Caen – Ecole Nationale Supérieure dIng