Papperoni

2010

The PASCAL Visual Object Classes (VOC) Challenge

Mark Everingham, Luc Van Gool, Christopher K. I. Williams, John Winn, Andrew Zisserman

Open PDF Google Scholar

citations

Cite Score

93

AI summary

This paper introduces the PASCAL Visual Object Classes (VOC) Challenge, a benchmark in visual object category recognition and detection, providing a standardized dataset of images and annotation, and standard evaluation procedures, and reviews the state-of-the-art methods evaluated in the challenge.

Main Contributions

Introduced the PASCAL Visual Object Classes (VOC) Challenge as a benchmark for visual object category recognition and detection.
Provided a standard dataset of images with annotations and evaluation procedures for the vision and machine learning communities.
Reviewed state-of-the-art methods for classification and detection, analyzed statistical differences, and explored what methods learn from images.
Identified common failure modes, such as reliance on scene context and sensitivity to object size, and discussed challenges for future improvement.
Proposed future directions for the challenge, including increasing object classes, incorporating object parts, and exploring alternative annotation methods.

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.

Citation Graph

Loading graph...

References [57]

Sort:

Filter:

[1]Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories

Svetlana Lazebnik, Cordelia Schmid, Jean Ponce - 2006

14 papers in library cite

It's a fun read, but in the end is just an application of the spatial pyramid matching kernel from the other paper.

[2]Video google: A Text Retrieval Approach to Object Matching in Videos

Josef Sivic, Andrew Zisserman - 2003

5 papers in library cite

Fun read! It's not really related to AI, but TBH the way they do search on video is more interesting than the object recog.

[3]Labelme: A Database and Web-Based Tool for Image Annotation

Bryan C. Russell, Antonio Torralba, Kevin P. Murphy, William T. Freeman - 2008

10 papers in library cite

It's a good paper overall but not worth the read. They just describe the platform (which for the time may have been a paradigm shift from in-house datasets). Maybe the basis for Amazon MT?

[4]One-Shot Learning of Object Categories

Li Fei Fei, Rob Fergus, Pietro Perona - 2006

5 papers in library cite

It's a nice problem they are trying to solve, though I doubt the effectiveness. Maybe it was really relevant in a time where they didn't have data. Problem is it focuses too much on the methodology, and I am not too interested in it.

[5]Caltech-256 Object Category Dataset

Greg Griffin, Alex Holub, Pietro Perona - 2007

9 papers in library cite

Boring read, but at least they were somewhat impactful.

[6]Labeling Images With a Computer Game

Luis Von Ahn, Laura Dabbish - 2004

5 papers in library cite

It's alright. TBH I expected a bit more. It's a good idea but I feel that they were very optimist around people playing - and it didn't work

[7]The Pyramid Match kernel: Discriminative Classification With Sets of Image Features

Kristen Grauman, Trevor Darrell - 2005

4 papers in library cite

Very simple and elegant solution to set matching. At first I didn't understand, but then it clicked. I think it could be used for other stuff as well!

[8]Learning Object Categories From Google's Image Search

Rob Fergus, Li Fei Fei, Pietro Perona, Andrew Zisserman - 2005

3 papers in library cite

Wow, they focus totally on the LSA stuff, and not on the Google Image Search stuff. Anticlimatic.

[9]Utility Data Annotation With Amazon Mechanical Turk

Alexander Sorokin, David Forsyth - 2008

2 papers in library cite

It's an alright guide to using Amazon MT. It's good that they lay the foundations to the methodology, but nothing too amazing

[10]WordNet: An Electronic Lexical Database

C. Fellbaum - 1998

12 papers in library cite

It's huge and I don't think it will add much (it is a book)

[11]Histograms of Oriented Gradients for Human Detection

N. Dalal, B. Triggs - 2005

12 papers in library cite

[12]Distinctive Image Features From Scale-Invariant Keypoints

D. Lowe - 2004

9 papers in library cite

[13]The PASCAL Visual Object Classes Challenge 2007 (VOC2007) Results

Mark Everingham, Luc Van Gool, Christopher K. I. Williams, John Winn, Andrew Zisserman - 2007

7 papers in library cite

[14]The PASCAL Visual Object Classes Challenge 2007 (VOC2007) Results

Mark Everingham, Luc Van Gool, Christopher K. I. Williams, John Winn, Andrew Zisserman - 2007

7 papers in library cite

[15]Why Is Real-World Visual Object Recognition Hard?

N. Pinto, D. D. Cox, J. J. Dicarlo - 2008

5 papers in library cite

[16]Combined Object Categorization and Segmentation With an Implicit Shape Model

B. Leibe, A. Leonardis, B. Schiele - 2004

4 papers in library cite

[17]Putting Objects in Perspective

D. Hoiem, A. A. Efros, M. Hebert - 2006

4 papers in library cite

[18]Fisher Kernels on Visual Vocabularies for Image Categorization

F. Perronnin, C. Dance - 2007

3 papers in library cite

[19]Introduction to a Large-Scale General Purpose Ground Truth Database: Methodology, Annotation Tool and Benchmarks

B. Yao, X. Yang, S. Zhu - 2007

3 papers in library cite

[20]Textonboost: Joint Appearance, Shape and Context Modeling for Multi-Class Object Recognition and Segmentation

J. Shotton, John Winn, C. Rother, A. Criminisi - 2006

3 papers in library cite

[21]The 2005 PASCAL Visual Object Classes Challenge

Mark Everingham, Andrew Zisserman, Christopher K. I. Williams, Luc Van Gool - 2006

3 papers in library cite

66 pages

[22]Visual Categorization With Bags of Keypoints

G. Csurka, C. Bray, C. Dance, L. Fan - 2004

3 papers in library cite

[23]A Discriminatively Trained, Multiscale, Deformable Part Model

P. F. Felzenszwalb, D. Mcallester, D. Ramanan - 2008

2 papers in library cite

[24]A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms

D. Scharstein, R. Szeliski - 2002

2 papers in library cite

[25]Beyond Sliding Windows: Object Localization by Efficient Subwindow Search

C. H. Lampert, M. B. Blaschko, T. Hofmann - 2008

2 papers in library cite

[26]Contextual Priming for Object Detection

Antonio Torralba - 2003

2 papers in library cite

[27]Introduction to Modern Information Retrieval

G. Salton, M. J. Mcgill - 1986

2 papers in library cite

[28]Object Recognition as Machine Translation: Learning a Lexicon for a Fixed Image Vocabulary

P. Duygulu, K. Barnard, N. D. Freitas, D. A. Forsyth - 2002

2 papers in library cite

[29]Semantic Hierarchies for Visual Object Recognition

M. Marszalek, Cordelia Schmid - 2007

2 papers in library cite

[30]An Efficient Multi-Class Detection Cascade

P. Zehnder, E. K. Meier, Luc Van Gool - 2008

1 paper in library cites

[31]An Exemplar Model for Learning Object Classes

O. Chum, Andrew Zisserman - 2007

1 paper in library cites

[32]Coloring Local Feature Extraction

J. V. D. Weijer, Cordelia Schmid - 2006

1 paper in library cites

[33]Compact Object Descriptors From Local Colour Invariant Histograms

J. Geusebroek - 2006

1 paper in library cites

[34]Decomposition, Discovery and Detection of Visual Categories Using Topic Models

M. Fritz, B. Schiele - 2008

1 paper in library cites

[35]Describing Visual Scenes Using Transformed Objects and Parts

E. B. Sudderth, A. B. Torralba, William T. Freeman, W. S. Willsky - 2008

1 paper in library cites

[36]Do Colour Interest Points Improve Image Retrieval?

J. Stoettinger, A. Hanbury, N. Sebe, T. Gevers - 2007

1 paper in library cites

[37]Early Versus Late Fusion in Semantic Video Analysis

C. Snoek, M. Worring, A. Smeulders - 2005

1 paper in library cites

[38]Estimating Average Precision With Incomplete and Imperfect Judgments

E. Yilmaz, J. Aslam - 2006

1 paper in library cites

[39]Evaluation Campaigns and TRECVID

A. F. Smeaton, P. Over, W. Kraaij - 2006

1 paper in library cites

[40]Evaluation of Color Descriptors for Object and Scene Recognition

K. E. A. V. D. Sande, T. Gevers, C. G. M. Snoek - 2008

1 paper in library cites

[41]Evaluation of Techniques for Image Classification, Object Detection and Object Segmentation

V. Viitaniemi, J. Laaksonen - 2008

1 paper in library cites

[42]Groups of Adjacent Contour Segments for Object Detection

V. Ferrari, L. Fevrier, F. Jurie, Cordelia Schmid - 2008

1 paper in library cites

[43]Improvements of Object Detection Using Boosted Histograms

I. Laptev - 2006

1 paper in library cites

[44]Learning of Graphical Models and Efficient Inference for Object Class Recognition

M. Bergtholdt, J. Kappes, C. Schnorr - 2006

1 paper in library cites

[45]Local Features and Kernels for Classification of Texture and Object Categories: A Comprehensive Study

J. Zhang, M. Marszalek, Svetlana Lazebnik, Cordelia Schmid - 2007

1 paper in library cites

[46]Relay Boost Fusion for Learning Rare Concepts in Multimedia

D. Wang, Jeffrey Li, B. Zhang - 2006

1 paper in library cites

[47]Robust Higher Order Potentials for Enforcing Label Consistency

P. Kohli, L. Ladicky, P. Torr - 2008

1 paper in library cites

[48]Robust Real-Time Face Detection

P. A. Viola, M. J. Jones - 2004

1 paper in library cites

[49]Robust Scene Categorization by Learning Image Statistics in Context

J. V. Gemert, J. Geusebroek, C. Veenman, C. Snoek, A. Smeulders - 2006

1 paper in library cites

[50]Scalable Near Identical Image and Shot Detection

O. Chum, J. Philbin, M. Isard, Andrew Zisserman - 2007

1 paper in library cites

[51]Sharing Visual Features for Multiclass and Multiview Object Detection

A. B. Torralba, Kevin P. Murphy, William T. Freeman - 2007

1 paper in library cites

[52]Some Objects Are More Equal Than Others: Measuring and Predicting Importance

M. Spain, Pietro Perona - 2008

1 paper in library cites

[53]Statistical Comparisons of Classifiers Over Multiple Data Sets

J. Demsar - 2006

1 paper in library cites

[54]The Challenge Problem for Automated Detection of 101 Semantic Concepts in Multimedia

C. Snoek, M. Worring, J. V. Gemert, J. Geusebroek, A. Smeulders - 2006

1 paper in library cites

[55]The Feature and Spatial Covariant Kernel: Adding Implicit Spatial Constraints to Histogram

Xiaodong Liu, D. Wang, Jeffrey Li, B. Zhang - 2007

1 paper in library cites

[56]The PASCAL Visual Object Classes Challenge 2007 (VOC2007) Annotation Guidelines

John Winn, Mark Everingham - 2007

1 paper in library cites

[57]Weakly Supervised Scale-Invariant Learning of Models for Visual Recognition

Rob Fergus, Pietro Perona, Andrew Zisserman - 2007

1 paper in library cites

Cited by

7

papers in your library

Cites

10

papers in your library

Read

on February 14, 2026

Good overview of the VOC challenge and good read, but too long and the part that they describe methods and results is very boring. Also, not related to NNs at the time!

Tags

Paper Aliases

No aliases