Filters








182,771 Hits in 5.5 sec

Semantic Adaptation of Multimedia Documents

Azze-eddine Maredj, Noureddine Tonkin
2012 International Journal of Multimedia and Image Processing  
A multimedia document should be presented on different platforms, for this adaptation of its content is necessary.  ...  In this contribution, we make some proposals to improve and extend the semantic approach based on conceptual neighborhoods graphs in order to best preserve the proximity between the adapted and the original  ...  The second type is the a posteriori adaptation, based on the content of the presentation.  ... 
doi:10.20533/ijmip.2042.4647.2012.0012 fatcat:fdlhj3x6vngr7eu2auhr5bo32e

Semi-structured Documents Mining: A Review and Comparison

Amina Madani, Omar Boussaid, Djamel Eddine Zegour
2013 Procedia Computer Science  
In this survey paper, we review popular semi-structured documents mining approaches (structure alone and both structure and content).  ...  The number of semi-structured documents that is produced is steadily increasing. Thus, it will be essential for discovering new knowledge from them.  ...  They propose a generative model able to handle both structure and content which is based on Bayesian networks.  ... 
doi:10.1016/j.procs.2013.09.110 fatcat:sjh47ru4ofcdtezxs6brnfiqta

An Adaptable Connectionist Text-Retrieval System With Relevance Feedback

M.R. Azimi-Sadjadi, J. Salazar, S. Srinivasan, S. Sheedvash
2007 IEEE Transactions on Neural Networks  
Initial model-reference learning is first performed based upon an ensemble set of input-output of an initial reference model.  ...  The first layer is an adaptable layer that performs mapping from query domain to document space. The second and third layers perform document-to-term mapping, search/retrieval, and scoring tasks.  ...  The indexing system processes each document in the database and generates an indexed file based upon certain attributes in the documents.  ... 
doi:10.1109/tnn.2007.895912 pmid:18051180 fatcat:ttgzvcuzqbgapg4fl2jponqn3m

Personalized Text Summarization Based on Important Terms Identification

Robert Moro, M'ria Bielikov'
2012 2012 23rd International Workshop on Database and Expert Systems Applications  
We use annotations added by readers as one of the sources of personalization.  ...  We have experimentally evaluated the proposed method in the domain of learning, obtaining better summaries capable of extracting important concepts explained in the document when considering the relevant  ...  of methods for acquisition, analysis and personalized conveying of information and knowledge, ITMS 26240220039, co-funded by the ERDF.  ... 
doi:10.1109/dexa.2012.47 dblp:conf/dexaw/MoroB12 fatcat:tpgrraop5bddrlnulkpptjuec4

Adaptive Content Mapping for Internet Navigation [chapter]

R.W. Brause, M. Ueberall
2003 Internet-Based Intelligent Information Processing Systems  
The small document specific thesaurus is automatically generated on the base of a general thesaurus and is treated like an abstract of the document.  ...  Based on the methods introduced in the previous sections, we will briefly review current adaptive content mapping methods.  ... 
doi:10.1142/9789812795342_0002 fatcat:fdtxjjqmjvddzjhigxgavbuf7a

Semantic adaptation of multimedia documents

Sébastien Laborie, Jérôme Euzenat, Nabil Layaïda
2010 Multimedia tools and applications  
In this paper, we propose a concrete application of this framework on standard multimedia documents.  ...  For that purpose, we first define an abstract structure that captures the spatiotemporal and hypermedia dimensions of multimedia documents, and we develop an adaptation algorithm which transforms in a  ...  Multimedia Document Generation Other approaches for multimedia document adaptation are based on automatic generation for particular classes of documents.  ... 
doi:10.1007/s11042-010-0552-9 fatcat:k7ntenbuonfnha73b7vqlbocv4

Event-Based Media Enrichment Using an Adaptive Probabilistic Hypergraph Model

Xueliang Liu, Meng Wang, Bao-Cai Yin, Benoit Huet, Xuelong Li
2015 IEEE Transactions on Cybernetics  
In this paper, we present a method combining semantic inference and multimodal analysis for automatically finding media content to illustrate events using an adaptive probabilistic hypergraph model.  ...  The results obtained from validating the approach on an event dataset collected from EventMedia demonstrate the effectiveness of the proposed approach.  ...  a given event, we propose an adaptive probabilistic hypergraph method to rank the content.  ... 
doi:10.1109/tcyb.2014.2374755 pmid:26470061 fatcat:vz7hu5bihjgdtk72bkj2u4yoti

A New Method of Hierarchical Text Clustering Based on Lsa-Hgsom

Jianfeng Wang, Lina Ma, Xinye Li, Yangxiu Zhou, Dong Qiao
2009 Modern Applied Science  
This paper presents a new method of hierarchical text clustering based on combination of latent semantic analysis (LSA) and hierarchical GSOM, which is called LSA-HGSOM method.  ...  However, current existing approaches lack in providing an adaptive hierarchical structure within in a single model.  ...  Therefore, a way of improving text clustering effect is that clustering of documents is based on text conception (or semantic content).  ... 
doi:10.5539/mas.v3n9p72 fatcat:2fmbxxmklzczzawppid6fg2krm

Content-based similar document image retrieval using fusion of CNN features [article]

Mao Tan, Si-Ping Yuan, Yong-Xin Su
2017 arXiv   pre-print
While conventional document image retrieval approaches depend on complex OCR-based text recognition and text similarity detection, this paper proposes a new content-based approach, in which more attention  ...  Finally, the document images are ranked based on feature similarity to a provided query image.  ...  [7] obtained a style representation of an input image and generated results on the basis of the VGGNet, which is a CNN that rivals human performance on a common visual object recognition benchmark task  ... 
arXiv:1703.08013v3 fatcat:icnmoywu5jhdtcvf5mgyrk7bgu

Migrant Health Policies in the European Union: A Comparative Policy Analysis

2020 Health Services Research  
There is an undeniable relationship between migration and health (Nagy, 2011) .  ...  Inequities in health are perpetuated by several factors that include, but are not limited to, immigration status, lack of knowledge of health system access points, appropriateness of health care services  ...  This distinctive organizing frame was used to derive meaningful comparisons and understanding of variation across the policy cases based solely on content analysis of the language of a policy document.  ... 
doi:10.1111/1475-6773.13415 fatcat:z5s6vea4njd47j4cavq6kwoesu

A Web-based Framework For On-line Collaborative Learning

Lidan Shou, Bin Cui, Gang Chen, Jinxiang Dong
2006 2006 10th International Conference on Computer Supported Cooperative Work in Design  
This paper presents a framework for design of on-line courses and collaborative learning based on Web technologies.  ...  It provides the following features: construction of structured learning materials in a distributed environment; personalization of course contents in the run-time that adapts to the progress of individual  ...  The preference matrix is also defined as an m X t matrix where pij indicates the normalized value of the estimated preference level on topic j for user i.  ... 
doi:10.1109/cscwd.2006.253028 dblp:conf/cscwd/ShouCCD06 fatcat:rymjodahabct5d6odfmzbk6x2u

Learning to rank for hybrid recommendation

Jiankai Sun, Shuaiqiang Wang, Byron J. Gao, Jun Ma
2012 Proceedings of the 21st ACM international conference on Information and knowledge management - CIKM '12  
However, predicting ratings is an intermediate step towards their ultimate goal of generating rankings or recommendation lists.  ...  Most existing recommender systems can be classified into two categories: collaborative filtering and content-based filtering.  ...  Given a set of users U , a set of items I, a rating matrix R with respect to U and I, and a loss function s, the problem of ranking-based hybrid recommendation is to generate a ranking function f from  ... 
doi:10.1145/2396761.2398610 dblp:conf/cikm/SunWGM12 fatcat:je6gcoyunba53arzkm3ks4ydki

XA2C: a framework for manipulating XML data

Gilbert Tekli, Richard Chbeir, Jacques Fayolle
2011 International Journal of Web Information Systems  
architecture and an XML-oriented visual functional composition language based on colored petri nets allowing functional compositions.  ...  Value -This paper presents a detailed description of an XML-oriented manipulation framework implementing the XCDL language.  ...  The adaptation mechanism in multimedia content adaptation is normally based on the properties of the document containing the data which has a well known structure and is well defined to contain multimedia  ... 
doi:10.1108/17440081111165884 fatcat:45fxcdn3lbckxh5pgyx6gtukay

Designing Adaptive Hypermedia for Internet Portals: A Personalization Strategy Featuring Case Base Reasoning with Compositional Adaptation [chapter]

Syed Sibte Raza Abidi
2002 Lecture Notes in Computer Science  
yield a 'representative' user model and the case adaptation techniques can be used for dynamic adaptive personalization of generic hypermedia-based information content.  ...  We propose that the Case Based Reasoning (CBR) paradigm offers an interesting alternative to developing adaptive hypermedia systems, such that the inherent analogy-based reasoning strategy can inductively  ...  An adaptive hypermedia system involves two distinct activities: (a) development of a user model and (b) adaptation of static generic information content to user-specific personalized content [2] .  ... 
doi:10.1007/3-540-36131-6_7 fatcat:5cyeatlhhnfarjxuuqobfjumni

Mobile Recommender Systems Methods: An Overview [article]

Djallel Bouneffouf
2013 arXiv   pre-print
The information that mobiles can access becomes very wide nowadays, and the user is faced with a dilemma: there is an unlimited pool of information available to him but he is unable to find the exact information  ...  Therefore, many of the general concepts of recommendation based on the content come from information retrieval van Meteren and van Someren.  ...  Extending the CF with the properties of CBF these techniques are used to make clustering on a group of profiles based on the content.  ... 
arXiv:1305.1745v1 fatcat:5vs5euqjkfeubfudsoyw5rskii
« Previous Showing results 1 — 15 out of 182,771 results