The 2005 PASCAL visual object classes challenge

Mark Everingham*, Andrew Zisserman, Christopher K. I. Williams, Luc Van Gool, Moray Allan, Christopher M. Bishop, Olivier Chapelle, Navneet Dalal, Thomas Deselaers, Gyuri Dorko, Stefan Duffner, Jan Eichhorn, Jason D. R. Farquhar, Mario Fritz, Christophe Garcia, Tom Griffiths, Frederic Jurie, Daniel Keysers, Markus Koskela, Jorma LaaksonenDiane Larlus, Bastian Leibe, Hongying Meng, Hermann Ney, Bernt Schiele, Cordelia Schmid, Edgar Seemann, John Shawe-Taylor, Amos Storkey, Sandor Szedmak, Bill Triggs, Ilkay Ulusoy, Ville Viitaniemi, Jianguo Zhang

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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.

Original languageEnglish
Title of host publicationMachine Learning Challenges
Subtitle of host publicationEvaluating Predictive Uncertainty, Visual Object Classification, and Recognising Tectual Entailment
EditorsJ Quinonero-Candela, Dagan, B Magnini, F D'Alche-Buc
Place of PublicationBerlin
PublisherSpringer
Pages117-176
Number of pages60
ISBN (Electronic)978-3-540-33428-6
ISBN (Print)978-3-540-33427-9
DOIs
Publication statusPublished - 2006
Event1st PASCAL Machine Learning Challenges Workshop (MLCW 2005) - Southampton, United Kingdom
Duration: 11 Apr 200513 Apr 2005

Publication series

NameLecture Notes in Computer Science
PublisherSpringer Berlin Heidelberg
Volume3944
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference1st PASCAL Machine Learning Challenges Workshop (MLCW 2005)
Country/TerritoryUnited Kingdom
Period11/04/0513/04/05

Keywords / Materials (for Non-textual outputs)

  • IMAGE
  • DESCRIPTORS
  • SCALE

Fingerprint

Dive into the research topics of 'The 2005 PASCAL visual object classes challenge'. Together they form a unique fingerprint.

Cite this