(Enter summary)
Abstract: We present an approach for image database retrieval using a very large number of
highly-selective features and simple on-line learning. Our approach is predicated on
the assumption that each image is generated by a sparse set of visual "causes" and that
images which are visually similar share causes. We propose a mechanism for generating
a large number of complex features which capture some aspects of this causal
structure. Boosting is used to learn simple and efficient classifiers in this... (Update)
Similar documents (at the sentence level):
23.1%: Boosting Image Retrieval - Tieu, Viola (2000)
(Correct)
Active bibliography (related documents): More All
0.1: Integrating Color, Texture, and Geometry for Image Retrieval - Nicholas Howe Daniel (2000)
(Correct)
0.1: Contextual Priming for Object Detection - Torralba (2003)
(Correct)
0.1: Statistical Context Priming for Object Detection - Torralba, Sinha (2001)
(Correct)
Similar documents based on text: More All
0.3: Learning Models of Environments with Manifest Causal Structure - Bergman (1995)
(Correct)
0.1: VIOLA: Video on Local-Area-Networks - Lee, Wong (1995)
(Correct)
0.1: A Brief Overview of the VIOLA Engine, and its Applications - Viola Is
(Correct)
BibTeX entry: (Update)
@misc{ tieu-boosting,
author = "Kinh H. Tieu and Paul Viola",
title = "Boosting Image Database Retrieval",
url = "citeseer.ist.psu.edu/tieu99boosting.html" }
Citations (may not include all citations):
524
Support vector networks
- Cortes, Vapnik - 1995
509
A decision-theoretic generalization of on-line learning and ..
- Freund, Schapire - 1997
262
Photobook: Content-based manipulation of image databases
- Pentland, Picard et al. - 1995
226
The qbic project: querying images by content using color (context) - Niblack, Barber et al. - 1993
53
Query by image example: the candid approach (context) - Kelly, Cannon et al. - 1995
8
Structure driven image database retrieval
- DeBonet, Viola - 1998
2
Corel stock photo images (context) - Corporation
Documents on the same site (http://www.ai.mit.edu/people/viola/): More
Multi-Modal Volume Registration by Maximization of .. - Wells, III.. (1995)
(Correct)
Complex Feature Recognition: A Bayesian Approach for Learning to.. - Viola (1996)
(Correct)
A Non-parametric Multi-Scale Statistical Model for Natural.. - De Bonet, Viola (1997)
(Correct)
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC