XML Multimedia Retrieval: From Relevant Textual Information to Relevant Multimedia Fragments

Torjmen, Mouna; Pinel-Sauvagnat, Karen

doi:10.1007/978-3-642-00958-7_16

Cited by 5 publications

(7 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we presented our CBA method (Torjmen et al, 2009), which implicitly exploits the XML content and structure for ME retrieval. This method consists in:…”

Section: Cba Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Using textual and structural context for searching Multimedia Elements

Torjmen

Pinel-Sauvagnat

2010

IJBIDM

Self Cite

View full text Add to dashboard Cite

We investigate in this paper the use of XML structure in multimedia retrieval, particularly in context-based image retrieval. We propose two methods to represent multimedia objects: the first one is based on an implicit use of textual and structural context of multimedia objects, whereas the second one is based on an explicit use of both sources. Experimental evaluation is carried out using the INEX MultimediaFragments Task 2006 and 2007. We show that there is a strong vocabulary relation between the query and the multimedia object representation, and that using XML structure improves significantly the effectiveness of multimedia retrieval.

show abstract

“…In this section, we presented our CBA method (Torjmen et al, 2009), which implicitly exploits the XML content and structure for ME retrieval. This method consists in:…”

Section: Cba Methodsmentioning

confidence: 99%

“…• The first one (called CBA) (Torjmen et al, 2009) is based on an implicit use of textual and structural context of MEs. Relevance scores of children, brothers and ancestors nodes of MEs are evaluated with a traditional XML retrieval system, and the impact of each of these sources of evidence on the ME relevance is then studied.…”

Section: Introductionmentioning

confidence: 99%

Using textual and structural context for searching Multimedia Elements

Torjmen

Pinel-Sauvagnat

2010

IJBIDM

Self Cite

View full text Add to dashboard Cite

show abstract

“…Many general-purpose ras proposed in the literature, content-based [13,14]. Mo [25,26] organizing image then applying image search tree. Most of these approac meaning of an image is rare descriptions.…”

Section: Related Workmentioning

confidence: 99%

SVG-to-RDF Image Semantization

Salameh

Tekli

Chbeir

2014

Similarity Search and Applications

View full text Add to dashboard Cite

The goal of this work is to provide an original (semi-automatic) annotation framework titled SVG-to-RDF which converts a collection of raw Scalable vector graphic (SVG) images into a searchable semantic-based RDF graph structure that encodes relevant features and contents. Using a dedicated knowledge base, SVG-to-RDF offers the user possible semantic annotations for each geometric object in the image, based on a combination of shape, color, and position similarity measures. Our method presents several advantages, namely i) achieving complete semantization of image content, ii) allowing semanticbased data search and processing using standard RDF technologies, iii) while being compliant with Web standards (i.e., SVG and RDF) in displaying images and annotation results in any standard Web browser, as well as iv) coping with different application domains. Our solution is of linear complexity in the size of the image and knowledge base structures used. Using our prototype SVG2RDF, several experiments have been conducted on a set of panoramic dental x-ray images to underline our approach's effectiveness, and its applicability to different application domains.

show abstract

“…To compute the final score of each multimedia fragment, we then combine the score of their associated multimedia element (obtained in Section 3.1) with their initial score (obtained in Section 3.2). A simple combination was proposed in Torjmen, Pinel -Sauvagnat, and Boughanem (2009), which is considered in this paper as a baseline for comparison with two others combination methods, described in Section 3.3.2.…”

Section: Multimedia Fragments Retrievalmentioning

confidence: 99%

“…As proposed in Torjmen et al (2009), a simple way to evaluate the score S(mf, q) of each ancestor and descendant of one or more multimedia elements is to linearly combine its initial score obtained by the XFIRM system (S XFIRM (mf, q)) and the scores of the associated multimedia elements:…”

Section: Simple Combinationmentioning

confidence: 99%

Investigating the document structure as a source of evidence for multimedia fragment retrieval

Torjmen-Khemakhem

Pinel-Sauvagnat

2013

Information Processing & Management

Self Cite

View full text Add to dashboard Cite

International audienceMultimedia objects can be retrieved using their context that can be for instance the text surrounding them in documents. This text may be either near or far from the searched objects. Our goal in this paper is to study the impact, in term of effectiveness, of text position relatively to searched objects. The multimedia objects we consider are described in structured documents such as XML ones. The document structure is therefore exploited to provide this text position in documents. Although structural information has been shown to be an effective source of evidence in textual information retrieval, only a few works investigated its interest in multimedia retrieval. More precisely, the task we are interested in this paper is to retrieve multimedia fragments (i.e. XML elements having at least one multimedia object). Our general approach is built on two steps: we first retrieve XML elements containing multimedia objects, and we then explore the surrounding information to retrieve relevant multimedia fragments. In both cases, we study the impact of the surrounding information using the documents structure.Our work is carried out on images, but it can be extended to any other media, since the physical content of multimedia objects is not used. We conducted several experiments in the context of the Multimedia track of the INEX evaluation campaign. Results showed that structural evidences are of high interest to tune the importance of textual context for multimedia retrieval. Moreover, the proposed approach outperforms state of the art approaches

show abstract

XML Multimedia Retrieval: From Relevant Textual Information to Relevant Multimedia Fragments

Cited by 5 publications

References 21 publications

Using textual and structural context for searching Multimedia Elements

Using textual and structural context for searching Multimedia Elements

SVG-to-RDF Image Semantization

Investigating the document structure as a source of evidence for multimedia fragment retrieval

Contact Info

Product

Resources

About