Filters








30,210 Hits in 7.1 sec

New frontiers for intelligent content-based retrieval

Ana B. Benitez, John R. Smith, Minerva M. Yeung, Chung-Sheng Li, Rainer W. Lienhart
2001 Storage and Retrieval for Media Databases 2001  
We argue that these elements are essential to producing effective systems for retrieving audio-visual content at semantic levels matching those of human perception and cognition.  ...  We also discuss how some of the principal ideas from these fields lead to new opportunities and capabilities for content-based retrieval systems.  ...  MPEG-7 description tools describe different aspects of multimedia material such as the features, structure, semantics, and models of multimedia content 21, 22 .  ... 
doi:10.1117/12.410922 dblp:conf/spieSR/BenitezS01 fatcat:fkxmkib2tndilixw66ydjs64pa

Integrating Structure and Semantics into Audio-visual Documents [chapter]

Raphaël Troncy
2003 Lecture Notes in Computer Science  
In this paper, we propose an architecture which describes formally the content of the videos and which constrains the structure of their descriptions.  ...  Describing audio-visual documents amounts to consider documentary aspects (the structure) as well as conceptual aspects (the content).  ...  In section 4 we discuss which language is suitable for describing both the structure and the semantics of audio-visual materials, and for performing some reasoning on these descriptions.  ... 
doi:10.1007/978-3-540-39718-2_36 fatcat:yx5mv5b6gfei3i3ulwb2pmtera

Use of the MPEG-7 standard as metadata framework for a location scouting system - An evaluation study

Valérie Gouaillier, Langis Gagnon, Sylvain Paquette, Philippe Poullaouec-Gonidec
2005 International Conference on Dublin Core and Metadata Applications  
We also discuss the advantages and shortcomings of MPEG-7 for this application.  ...  Not only should the metadata schema allow conventional queries, but it must also be suited for advanced search functionalities such as similaritybased image retrieval.  ...  Acknowledgements This work is financially supported by the Conseil régional de développement de la Montérégie (CRDM), CRIM, CPEUM and Natural Science and Engineering Research Council of Canada (NSERC).  ... 
dblp:conf/dc/GouaillierGPP05 fatcat:havnayyfejhsxbjovxd4o3rlju

Modelling image semantic descriptions from web 2.0 documents using a hybrid approach

Lailatul Qadri Zakaria, Wendy Hall, Paul Lewis
2009 Proceedings of the 11th International Conference on Information Integration and Web-based Applications & Services - iiWAS '09  
Tagging is a modest way to annotate such documents and fails to capture a full semantic description of the document content.  ...  The approach consists of three main components, natural language processing, image analysis and a shared knowledge base.  ...  captured in text descriptions using a natural language approach.  ... 
doi:10.1145/1806338.1806395 dblp:conf/iiwas/ZakariaHL09 fatcat:tvqyhguacbdexkoakbiu44agre

A Semiotic Framework for the Semantics of Digital Multimedia Learning Objects

Michael May
2007 14th International Conference of Image Analysis and Processing - Workshops (ICIAPW 2007)  
The relevance of semiotics for extending multimedia description schemes will be shown relative to in existing strategies for indexing and retrieval.  ...  The semiotic framework presented is intended to support a compositional semantics of flexible digital multimedia objects. Besides semiotics insights from Formal Concept Analysis is utilized.  ...  : multimedia content description for indexing and retrieval of composite multimedia objects and metadata descriptions of learning objects for digital repositories share a series of semantic problems that  ... 
doi:10.1109/iciapw.2007.8 fatcat:6v4rmd45ffhdpeprtlbegq52fa

Towards integrating semantics of multi-media resources and processes in e-Learning

Weihong Huang, Emmanuel Eze, David Webster
2006 Multimedia Systems  
The proposed semantic e-Learning framework enables intelligent operations of heterogeneous multi-media contents based on a generic semantic context intermediation model.  ...  This framework supports intelligent e-Learning with a knowledge network for knowledge object visualization, an enhanced Kolb's learning cycle [31] to guide learning practices, and a learning health care  ...  Acknowledgements The authors are grateful to the anonymous reviewers of this paper for their insightful and valuable comments to make this paper a more solid literature piece.  ... 
doi:10.1007/s00530-005-0009-6 fatcat:fty3jvlbvrfwlgsgsgvd3d2mqq

Building a multilingual ontology for education domain using monto method

Merlin Florrence
2020 Computer Science and Information Technologies  
It is important to provide multilingual information of those domains to facilitate multi-language users.  ...  New algorithms are proposed for merging and mapping multilingual ontologies.  ...  Input, Building MO, Ontology mediation, Retrieval and Visualization of ontology.  ... 
doi:10.11591/csit.v1i2.p47-53 fatcat:ggy4zofcrnc5ro4ox5nanylcce

BRIDGING THE SEMANTIC GAP: EXPLORING DESCRIPTIVE VOCABULARY FOR IMAGE STRUCTURE

Caroline Beebe
2007 Advances in Classification Research Online  
Bridging the semantic gap: Exploring descriptive vocabulary for image structure. 18th Annual ASIS SIG/CR Classification Research Workshop  ...  Bridging the semantic gap: Exploring descriptive vocabulary for image structure. 18th Annual ASIS SIG/CR Classification Research Workshop computed to indicate inter-rater reliability.  ...  CBIR indexes expand the notion of physical description to include the pre-semantic physicality of the pixel relationships, or the physical visual structure.  ... 
doi:10.7152/acro.v18i1.12866 fatcat:oah3mqsuijaqznixgx5zstqpm4

CLIP-Actor: Text-Driven Recommendation and Stylization for Animating Human Meshes [article]

Kim Youwang, Kim Ji-Yeon, Tae-Hyun Oh
2022 arXiv   pre-print
Given a natural language prompt, CLIP-Actor suggests a text-conforming human motion in a coarse-to-fine manner.  ...  We demonstrate that CLIP-Actor produces plausible and human-recognizable style 3D human mesh in motion with detailed geometry and texture solely from a natural language prompt.  ...  CLIP-Actor focuses on textual and visual semantics in a whole sentence and can tackle various natural language descriptions.  ... 
arXiv:2206.04382v2 fatcat:txb5tg5fbjdp7jtebhb2cc4e6e

Toward a Structural and Semantic Metadata Framework for Efficient Browsing and Searching of Web Videos

Hyun-Hee Kim
2017 Journal of the Korean Society for Library and Information Science  
Although MPEG-7 supports multimedia structural and semantic descriptions, it is not currently suitable for describing multimedia content on the Web.  ...  This study proposed a structural and semantic framework for the characterization of events and segments in Web videos that permits content-based searches and dynamic video summarization.  ...  The content description represents the structure and semantics of AV content.  ... 
doi:10.4275/kslis.2017.51.1.227 fatcat:3zlaebvw5vasph462xxjeea6vy

MUMIS – ADVANCED INFORMATION EXTRACTION FOR MULTIMEDIA INDEXING AND SEARCHING

T. DECLERCK, H. CUNNINGHAM, H. SAGGION, J. KUPER, D. REIDSMA, P. WITTENBURG
2003 Digital Media Processing for Multimedia Interactive Services  
This paper describes the role advanced natural language processing (NLP) and especially information extraction (IE) can play for multimedia applications.  ...  A novelty of the approach is to exploit multiple sources of information relating to video content.  ...  The solution consists in applying advanced natural language processing (NLP) on different sources (structured, semi-structured, free, etc.), modalities (text, speech), and languages (English, German, Dutch  ... 
doi:10.1142/9789812704337_0100 fatcat:sh27b4apabeutg3sleooi76yde

Creating Rich Metadata in the TV Broadcast Archives Environment: The PrestoSpace Project

A. Messina, L. Boch, G. Dimino, W. Bailer, P. Schallauer, W. Allasia, M. Groppo, M. Vigilante, R. Basili
2006 2006 Second International Conference on Automated Production of Cross Media Content for Multi-Channel Distribution (AXMEDIS'06)  
Automatic tools include audiovisual content analysis and semantic analysis of text extracted by automatic speech recognition (ASR).  ...  This paper describes the part of the European PrestoSpace project dedicated to the study and development of a Metadata Access and Delivery (MAD) system for television broadcast archives.  ...  It is planned to integrate a semantic engine for processing natural language queries.  ... 
doi:10.1109/axmedis.2006.20 dblp:conf/axmedis/MessinaBDBSAGVB06 fatcat:t7oaqiwvojhghdu6g7bqpadnr4

A reduced yet extensible audio-visual description language

Rapha�l Troncy, Jean Carrive
2004 Proceedings of the 2004 ACM symposium on Document engineering - DocEng '04  
This language is centered on the notions of descriptor and structure with a well-defined semantics.  ...  We introduce then our proposition: an audio-visual specific description language, modular, reduced, but designed to be extensible.  ...  These textual descriptions can be used for retrieving relevant video sequences or for enhancing their content to produce new rich media documents.  ... 
doi:10.1145/1030397.1030415 dblp:conf/doceng/TroncyC04 fatcat:dsex64gm65cq7cm665jvf7tu5a

MediaNet: a multimedia information network for knowledge representation

Ana B. Benitez, John R. Smith, Shih-Fu Chang, John R. Smith, Chinh Le, Sethuraman Panchanathan, C.-C. Jay Kuo
2000 Internet Multimedia Management Systems  
In constructing the MediaNet framework, we have built on the basic principles of semiotics and semantic networks in addition to utilizing the audio-visual content description framework being developed  ...  as part of the MPEG-7 multimedia content description standard.  ...  CONCLUSIONS We have presented MediaNet, which is a knowledge representation framework that uses multimedia content for representing semantic and perceptual information.  ... 
doi:10.1117/12.403791 fatcat:kd3y5yvsyjh3tixih76fftprha

An MPEG-7 query language and a user preference model that allow semantic retrieval and filtering of multimedia content

Chrisa Tsinaraki, Stavros Christodoulakis
2007 Multimedia Systems  
The MP7QL has the MPEG-7 as data model and allows for querying every aspect of an MPEG-7 multimedia content description.  ...  It allows the users to express the conditions that should hold for the multimedia content returned to them regarding semantics, low-level visual and audio features and media-related aspects.  ...  natural language interface generator [17] that allows locating multimedia information of interest using natural language queries.  ... 
doi:10.1007/s00530-007-0091-z fatcat:sssi5upjwbf5fomxe2z425bfqm
« Previous Showing results 1 — 15 out of 30,210 results