hal-00722820, version 1

Learning discriminative spatial representation for image classification

Gaurav Sharma (, ) ^a, 1, 2, Frédéric Jurie (, ) ^1, 2

British Machine Vision Conference (BMVC) (2011)

• a –  Université de Caen
• 1:  LEAR (INRIA Grenoble Rhône-Alpes / LJK Laboratoire Jean Kuntzmann)
• http://lear.inrialpes.fr/
  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.fr
  CNRS : UMR6072 – Université de Caen Basse-Normandie – Ecole Nationale Supérieure d'Ingénieurs de Caen Boulevard du Maréchal Juin - 14050 CAEN Cedex France

Bibliographic reference

• Type of document: Peer-reviewed conferences/proceedings
• Domain: Computer Science/Computer Vision and Pattern Recognition
• Title: Learning discriminative spatial representation for image classification
• Abstract: Spatial Pyramid Representation (SPR) [7] introduces spatial layout information to the orderless bag-of-features (BoF) representation. SPR has become the standard and has been shown to perform competitively against more complex methods for incorporating spatial layout. In SPR the image is divided into regular grids. However, the grids are taken as uniform spatial partitions without any theoretical motivation. In this paper, we address this issue and propose to learn the spatial partitioning with the BoF representation. We define a space of grids where each grid is obtained by a series of recursive axis aligned splits of cells. We cast the classification problem in a maximum margin formulation with the optimization being over the weight vector and the spatial grid. In addition to experiments on two challenging public datasets (Scene-15 and Pascal VOC 2007) showing that the learnt grids consistently perform better than the SPR while being much smaller in vector length, we also introduce a new dataset of human attributes and show that the current method is well suited to the recognition of spatially localized human attributes.
• Full text language: English
• Publication date: 2011-08-29
• Audience: international
• Conference title: British Machine Vision Conference (BMVC)
• Conference city: Dundee
• Country: United Kingdom
• Conference date: 2011-08-29

Attached file list to this document: 

• hal-00722820, version 1
• http://hal.inria.fr/hal-00722820
• oai:hal.inria.fr:hal-00722820
• From: Team Lear <>
• Submitted on: Saturday, 4 August 2012 14:58:40
• Updated on: Friday, 14 September 2012 09:47:50