The Pascal Visual Object Classes (VOC) Challenge

Abstract

The Pascal Visual Object Classes (VOC) challenge is a benchmark in visual object category recognition and detection, providing the vision and machine learning communities with a standard dataset of images and annotation, and standard evaluation procedures. Organised annually from 2005 to present, the challenge and its associated dataset has become accepted as the benchmark for object detection. This paper describes the dataset and evaluation procedure. We review the state-of-the-art in evaluated methods for both classification and detection, analyse whether the methods are statistically different, what they are learning from the images (e.g. the object or its context), and what the methods find easy or confuse. The paper concludes with lessons learnt in the three year history of the challenge, and proposes directions for future improvement and extension.

DOI: 10.1007/s11263-009-0275-4

Extracted Key Phrases

29 Figures and Tables

Showing 1-10 of 57 references

Caltech-256 object category dataset California Institute of Technology

  • G Griffin, A Holub, P Perona
  • 2007
Highly Influential
7 Excerpts

The PASCAL visual object classes challenge 2007 (VOC2007) Results

  • M Everingham, L Van Gool, C K I Williams, J Winn, A Zisserman
  • 2007
Highly Influential
4 Excerpts

The PASCAL visual object classes challenge 2007 (VOC2007) annotation guidelines

  • J Winn, M Everingham
  • 2007
Highly Influential
4 Excerpts

Int J Comput Vis

  • 2010
Showing 1-10 of 2,031 extracted citations
02004006002008200920102011201220132014201520162017
Citations per Year

3,340 Citations

Semantic Scholar estimates that this publication has received between 3,106 and 3,594 citations based on the available data.

See our FAQ for additional information.