Chapter

Machine Learning Challenges. Evaluating Predictive Uncertainty, Visual Object Classification, and Recognising Tectual Entailment

Volume 3944 of the series Lecture Notes in Computer Science pp 117-176

The 2005 PASCAL Visual Object Classes Challenge

  • Mark EveringhamAffiliated withUniversity of Oxford
  • , Andrew ZissermanAffiliated withUniversity of Oxford
  • , Christopher K. I. WilliamsAffiliated withUniversity of Edinburgh
  • , Luc Van GoolAffiliated withETH Zentrum
  • , Moray AllanAffiliated withUniversity of Edinburgh
  • , Christopher M. BishopAffiliated withMicrosoft Research
  • , Olivier ChapelleAffiliated withMax Planck Institute for Biological Cybernetics
  • , Navneet DalalAffiliated withINRIA Rhône-Alpes
  • , Thomas DeselaersAffiliated withRWTH Aachen University
    • , Gyuri DorkóAffiliated withINRIA Rhône-Alpes
    • , Stefan DuffnerAffiliated withFrance Télécom
    • , Jan EichhornAffiliated withMax Planck Institute for Biological Cybernetics
    • , Jason D. R. FarquharAffiliated withUniversity of Southampton
    • , Mario FritzAffiliated withTU-Darmstadt
    • , Christophe GarciaAffiliated withFrance Télécom
    • , Tom GriffithsAffiliated withUniversity of Edinburgh
    • , Frederic JurieAffiliated withINRIA Rhône-Alpes
    • , Daniel KeysersAffiliated withRWTH Aachen University
    • , Markus KoskelaAffiliated withHelsinki University of Technology
    • , Jorma LaaksonenAffiliated withHelsinki University of Technology
    • , Diane LarlusAffiliated withINRIA Rhône-Alpes
    • , Bastian LeibeAffiliated withTU-Darmstadt
    • , Hongying MengAffiliated withUniversity of Southampton
    • , Hermann NeyAffiliated withRWTH Aachen University
    • , Bernt SchieleAffiliated withTU-Darmstadt
    • , Cordelia SchmidAffiliated withINRIA Rhône-Alpes
    • , Edgar SeemannAffiliated withTU-Darmstadt
    • , John Shawe-TaylorAffiliated withUniversity of Southampton
    • , Amos StorkeyAffiliated withUniversity of Edinburgh
    • , Sandor SzedmakAffiliated withUniversity of Southampton
    • , Bill TriggsAffiliated withINRIA Rhône-Alpes
    • , Ilkay UlusoyAffiliated withMiddle East Technical University
    • , Ville ViitaniemiAffiliated withHelsinki University of Technology
    • , Jianguo ZhangAffiliated withINRIA Rhône-Alpes

Abstract

The PASCAL Visual Object Classes Challenge ran from February to March 2005. The goal of the challenge was to recognize objects from a number of visual object classes in realistic scenes (i.e. not pre-segmented objects). Four object classes were selected: motorbikes, bicycles, cars and people. Twelve teams entered the challenge. In this chapter we provide details of the datasets, algorithms used by the teams, evaluation criteria, and results achieved.