Learning from User Behavior in Image Retrieval: Application of Market Basket Analysis

Müller, Henning; Pun, Thierry; Squire, David

doi:10.1023/b:visi.0000004832.02269.45

Cited by 46 publications

(26 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our particular domain of application, NASA's Solar Dynamics Observatory (SDO) mission generates approximately 69,000 images per day, thus making the task of hand labeling them (meta-data generation) impossible, and making it a relevant problem for CBIR. There are several important surveys on CBIR [5,6,7,8], but we found that until [1], there has not been new work done in CBIR. For the domain specific problem of solar images that this framework was originally developed for, we referred to surveys of high-dimensional indexing of multimedia data [9] and applications to medicine [10], which fit the constraints of our particular application.…”

Section: Introductionmentioning

confidence: 99%

ImageFARMER: Introducing a Data Mining Framework for the Creation of Large-scale Content-based Image Retrieval Systems

Banda¹,

Angryk²,

Martens³

2013

IJCA

View full text Add to dashboard Cite

In this paper we introduce imageFARMER, a framework that allows information retrieval researchers and educators to develop and customize domain-specific content-based image retrieval systems with ease while developing a deeper understanding of the underlying representation of domainspecific image data. imageFARMER incorporates different aspects of image processing and content-based information retrieval, such as: image representation via image parameter extraction, validation via image parameters, analysis of multiple dissimilarity measures for accurate data analysis, testing of dimensionality reduction methods for storage and processing optimization, and indexing algorithms for fast and efficient querying. The unique capabilities of this framework have not been available together as an open-source software package designed for research, while offering enhanced knowledge discovery and validation of all steps involved when creating large-scale content-based image retrieval systems. General TermsImage retrieval, content-based image retrieval, open-source software applications, evaluation framework.

show abstract

Section: Introductionmentioning

confidence: 99%

ImageFARMER: Introducing a Data Mining Framework for the Creation of Large-scale Content-based Image Retrieval Systems

Banda¹,

Angryk²,

Martens³

2013

IJCA

View full text Add to dashboard Cite

show abstract

“…Also, and are similar to each other in that they are accessed by users and , but not by and . Similar ideas have been successfully applied to image retrieval to improve the accuracy of similarity measurement [12], [13], [25].…”

Section: A Audio Similaritymentioning

confidence: 99%

Music Recommendation Based on Acoustic Features and User Access Patterns

Shao

Ogihara

Wang

et al. 2009

IEEE Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

Abstract-Music recommendation is receiving increasing attention as the music industry develops venues to deliver music over the Internet. The goal of music recommendation is to present users lists of songs that they are likely to enjoy. Collaborative-filtering and content-based recommendations are two widely used approaches that have been proposed for music recommendation. However, both approaches have their own disadvantages: collaborative-filtering methods need a large collection of user history data and content-based methods lack the ability of understanding the interests and preferences of users. To overcome these limitations, this paper presents a novel dynamic music similarity measurement strategy that utilizes both content features and user access patterns. The seamless integration of them significantly improves the music similarity measurement accuracy and performance. Based on this strategy, recommended songs are obtained by a means of label propagation over a graph representing music similarity. Experimental results on a real data set collected from http://www.newwisdom.net demonstrate the effectiveness of the proposed approach.

show abstract

“…Consequently, one of the major challenges in CBIR is how to compensate for the semantic gap using the low-level features. Several different similarity functions using low-level features have been proposed and examined [12,19,28]. Nevertheless, as Santini et al argued in [20], the only perceptual similarity that can meaningfully be used is pre-attentive similarity, not semantic similarity.…”

Section: Introductionmentioning

confidence: 99%

Rank-based distance metric learning: An application to image retrieval

Lee

Jin

Jain

2008

2008 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

show abstract

Learning from User Behavior in Image Retrieval: Application of Market Basket Analysis

Abstract: This article describes an approach to learn feature weights for content-based image retrieval (CBIR)

Cited by 46 publications

References 28 publications

ImageFARMER: Introducing a Data Mining Framework for the Creation of Large-scale Content-based Image Retrieval Systems

ImageFARMER: Introducing a Data Mining Framework for the Creation of Large-scale Content-based Image Retrieval Systems

Music Recommendation Based on Acoustic Features and User Access Patterns

Rank-based distance metric learning: An application to image retrieval

Contact Info

Product

Resources

About