Creating a novel semantic video search engine through enrichment textual and temporal features of subtitled YouTube media fragments

Farhadi, Babak; Ghaznavi‐Ghoushchi, M. B.

doi:10.1109/iccke.2013.6682857

Cited by 9 publications

(10 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Semantic Search approaches [13] [25] [17] can use any of the following approaches: First Approach (Contextual Search): A contextual Approach is to disambiguate and to make queries to provide single meaning. [1] [27] [15] Second Approach (Reasoning Search): The focus is on reasoning. It finds new information from the given facts.…”

Section: Search Processmentioning

confidence: 99%

Literature Survey: Analysis on Semantic Web Information Retrieval Methodologies

Ezhilarasi¹,

Kalavathy²

2018

Proceedings of the International Conference for Phoenixes on Emerging Current Trends in Engineering and Management (PECTEAM 201

View full text Add to dashboard Cite

The Semantic web is the extension of an existing web that defines a standard by which, information is given in well-defined meaning and enables the machines to understand information. Many kinds of research are going in semantic web space. Researchers follow different approaches to retrieve data from the semantic web. This paper is to investigate the existing situation of the Semantic Web with the focus on effective information retrieval. Based on the architecture of semantic search engine, list of parameters (like ranking algorithm, reasoning mechanism) is framed to carry out a systematic analysis of different techniques proposed by the researchers. This survey identifies around 20 unique models that retrieve the data from the semantic web and information systems. Summary of the selected semantic search models is specified and compared them by means of "classification parameters" defined. This comparison identifies common insight, unique features and also open issues. This study can be used as a guide for future application development and research.

show abstract

Section: Search Processmentioning

confidence: 99%

Literature Survey: Analysis on Semantic Web Information Retrieval Methodologies

Ezhilarasi¹,

Kalavathy²

2018

Proceedings of the International Conference for Phoenixes on Emerging Current Trends in Engineering and Management (PECTEAM 201

View full text Add to dashboard Cite

show abstract

“…We individualize requests to the SPARQL Protocol And RDF Query Language (SPARQL) endpoints of each benchmark dataset and three related kinds of Uniform Resource Identifiers (URI) which all reflect the identical resource, in the sense that the plain resource URI is the identifier of a non-information resource [14] such as "WWW2012", while the related RDF and HTML document URI are identifiers for information resources, or representations in different formats about WWW2012 (see Figure 4). We used the SPARQL GUI in [2,3,4] for testing out SPARQL queries on LOD benchmark datasets which we created by loading in RDF from files and/or remote URIs.…”

Section: Benchmark Datasetsmentioning

confidence: 99%

“…The semantic web has suffered from a chicken-and-egg problem in the past, whereby it has been difficult to gather semantically rich data for semantic web applications to use; however users of the social web are creating semantically rich data every second. In the reverse direction, different heterogeneous platforms and social web clients can benefit from having interoperable semantic representations of social data to provide integrated views on this data and improved data exchange [2,3,4]. The social semantic web can be a platform for both personal and professional collaborative exchange with reusable community contributions.…”

Section: Introductionmentioning

confidence: 99%

A Novel Connectivity-based Reinforcement Learning Algorithm for Ranking Linked Data on the Social Semantic Web

Farhadi¹

2017

IJCA

Self Cite

View full text Add to dashboard Cite

“…In [10] and [11] we've used the unifier and generator modules for creating an on-line semantic video search engine in the field of subtitled general YouTube media fragments. Therefore, all the experimental results and evaluations have included in subtitled "with-all-categories YouTube" videos area.…”

Section: Related Work 21 Overview On All the Previous Work Related mentioning

confidence: 99%

Creating a Semantic Academic Lecture Video Search Engine via Enrichment Textual and Temporal Features of Subtitled YouTube EDU Media Fragments

Farhadi¹

2014

IJCA

Self Cite

View full text Add to dashboard Cite

In this paper, we propose a new framework to annotating subtitled YouTube EDU media fragments using textual features such as exert all the basic portions extracted from the web-based natural language processors of in relation to subtitles and temporal features such as duration of the media fragments where proper entities are spotted. We've created the SY-E-MFSE (Subtitled YouTube EDU Media Fragment Search Engine) as a framework to cruising on the subtitled YouTube EDU videos resident in the Linked Open Data (LOD) cloud. For realizing this purpose, we propose Unifier Module of Outcomes of Web-Based Natural Language Processors (UM-OWNLP) for extracting the essential portions of the 10 NLP tools that are based on the web, from subtitles associated to YouTube videos in order to generate media fragments annotated with resources from the LOD cloud. Then, we propone Unifier Module of Outcomes of WebBased Named Entity (NE) Booster Processors (UM-OWNEBP) containing the six web Application Programming Interfaces (API) to boost outcomes of NEs obtained from UM-OWNLP. We've presented 'UM-OWNLP ontology' to support all the 10 NLP web-based tools ontological features and representing them in a steadfast framework. KeywordsSubtitled YouTube EDU video, textual metadata, semantic web, video annotation, web-based natural language processor.

show abstract

Creating a novel semantic video search engine through enrichment textual and temporal features of subtitled YouTube media fragments

Cited by 9 publications

References 4 publications

Literature Survey: Analysis on Semantic Web Information Retrieval Methodologies

Literature Survey: Analysis on Semantic Web Information Retrieval Methodologies

A Novel Connectivity-based Reinforcement Learning Algorithm for Ranking Linked Data on the Social Semantic Web

Creating a Semantic Academic Lecture Video Search Engine via Enrichment Textual and Temporal Features of Subtitled YouTube EDU Media Fragments

Contact Info

Product

Resources

About