Multiple instance classification: Review, taxonomy and comparative study

Amores, Jaume

doi:10.1016/j.artint.2013.06.003

ScienceOpen: research and publishing network

For Publishers

For Researchers

Blog
About

Search
Advanced search

views

recommends

Record: found
Abstract: not found
Article: not found

Multiple instance classification: Review, taxonomy and comparative study

Author(s): Jaume Amores

Publication date Created: August 2013

Publication date (Print): August 2013

Journal: Artificial Intelligence

Publisher: Elsevier BV

Read this article at

ScienceOpenPublisher

Bookmark

There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

Abstract

Related collections

Most cited references 13

Record: found
Abstract: not found
Article: not found

Solving the multiple instance problem with axis-parallel rectangles

Thomas G Dietterich, Richard Lathrop, Tomás Lozano-Pérez (1997)

0 comments Cited 369 times – based on 0 reviews      Review now

Bookmark

Record: found
Abstract: not found
Article: not found

Speaker Verification Using Adapted Gaussian Mixture Models

Douglas A. Reynolds, Thomas Quatieri, Robert B. Dunn (2000)

0 comments Cited 314 times – based on 0 reviews      Review now

Bookmark

Record: found
Abstract: found
Article: not found

Robust object recognition with cortex-like mechanisms.

Thomas Serre, Lior Wolf, Stanley Bileschi … (2007)

We introduce a new general framework for the recognition of complex visual scenes, which is motivated by biology: We describe a hierarchical system that closely follows the organization of visual cortex and builds an increasingly complex and invariant feature representation by alternating between a template matching and a maximum pooling operation. We demonstrate the strength of the approach on a range of recognition tasks: From invariant single object recognition in clutter to multiclass categorization problems and complex scene understanding tasks that rely on the recognition of both shape-based as well as texture-based objects. Given the biological constraints that the system had to satisfy, the approach performs surprisingly well: It has the capability of learning from only a few training examples and competes with state-of-the-art systems. We also discuss the existence of a universal, redundant dictionary of features that could handle the recognition of most object categories. In addition to its relevance for computer vision, the success of this approach suggests a plausibility proof for a class of feedforward models of object recognition in cortex.

0 comments Cited 266 times – based on 0 reviews      Review now

Bookmark

All references

Author and article information

Journal

Title: Artificial Intelligence

Abbreviated Title: Artificial Intelligence

Publisher: Elsevier BV

ISSN (Print): 00043702

Publication date Created: August 2013

Publication date (Print): August 2013

Volume: 201

Issue:

Pages: 81-105

Article

DOI: 10.1016/j.artint.2013.06.003

SO-VID: 4093d9ff-2ef8-4645-b7b2-a0436ea4dced

History

Data availability:

Comments

Comment on this article

scite_

Cited by 98

See all cited by

Most referenced authors 154

See all reference authors

Multiple instance classification: Review, taxonomy and comparative study

Read this article at

Abstract

Related collections

Artificial Intelligence in Medicine

Most cited references 13

Solving the multiple instance problem with axis-parallel rectangles

Speaker Verification Using Adapted Gaussian Mixture Models

Robust object recognition with cortex-like mechanisms.

Author and article information

Journal

Article

History

Comments

Comment on this article

Similar content 4,476

Cited by 98

Most referenced authors 154