Filters








8,452 Hits in 4.7 sec

Active learning with multiple classifiers for multimedia indexing

Bahjat Safadi, Georges Quénot
2010 Multimedia tools and applications  
We propose and evaluate in this paper a combination of Active Learning and Multiple Classifiers approaches for corpus annotation and concept indexing on highly imbalanced datasets.  ...  On the considered dataset, the best performance is achieved when 15 to 30% of the corpus is annotated for individual descriptors and when 10 to 15% of the corpus is annotated for their fusion.  ...  Acknowledgement This work was partly realized as part of the Quaero Program funded by OSEO, French State agency for innovation.  ... 
doi:10.1007/s11042-010-0599-7 fatcat:agix2s55ozf5vi6ufkwcc6ymzi

Active learning with multiple classifiers for multimedia indexing

Bahjat Safadi, Georges Quenot
2010 2010 International Workshop on Content Based Multimedia Indexing (CBMI)  
We propose and evaluate in this paper a combination of Active Learning and Multiple Classifiers approaches for corpus annotation and concept indexing on highly imbalanced datasets.  ...  On the considered dataset, the best performance is achieved when 15 to 30% of the corpus is annotated for individual descriptors and when 10 to 15% of the corpus is annotated for their fusion.  ...  Acknowledgement This work was partly realized as part of the Quaero Program funded by OSEO, French State agency for innovation.  ... 
doi:10.1109/cbmi.2010.5529910 dblp:conf/cbmi/SafadiQ10 fatcat:yv3wzkirvjf37oxuvv7p5gubo4

BJTU TRECVID 2006 Video Retrieval System

Shikui Wei, Yao Zhao, Zhenfeng Zhu, Nan Liu, Yufeng Zhao, Liang Zhang, Fang Wang
2006 TREC Video Retrieval Evaluation  
In this paper, we describe our experiments of search task for TRECVID 2006.  ...  In automatic video search task, we were able to achieve the median or better performance for most of the topics and even achieve the best average precision for one topic.  ...  The co-training algorithm [7] , a well-known multi-view learning algorithm, is first introduced into the domain of video concept detection by Yan.R et.al [3] .  ... 
dblp:conf/trecvid/Wei0ZLZZW06 fatcat:jnexkf5h3vd6dopocuggulvhyy

Conception and Use of Ontologies for Indexing and Searching by Semantic Contents of Video Courses [article]

Ghalia Merzougui, Mahieddine Djoudi, Amel Behaz
2012 arXiv   pre-print
In this paper, we present a model of pedagogical knowledge of current videos. This knowledge is used throughout the process of indexing and semantic search segments instructional videos.  ...  Nowadays, the video documents like educational courses available on the web increases significantly.  ...  To evaluate our system, we have two approaches: -The first concerns the evaluation of the structure of the index.  ... 
arXiv:1201.5102v1 fatcat:iwz6d4pspngotfmwbmqqy653je

A factorized model for multiple SVM and multi-label classification for large scale multimedia indexing

Bahjat Safadi, Georges Quenot
2015 2015 13th International Workshop on Content-Based Multimedia Indexing (CBMI)  
: Multimedia indexing and retrieval, support vector machine, multi-learner approach, class imbalance.  ...  The method is based on the use of multiple SVMs (MSVM) for dealing with the class imbalance and on some adaptations of this approach in order to allow for an efficient implementation using optimized linear  ...  ACKNOWLEDGEMENTS This work was partly realized as part of the Quaero Program funded by OSEO, French State agency for innovation.  ... 
doi:10.1109/cbmi.2015.7153610 dblp:conf/cbmi/SafadiQ15 fatcat:yoviodf2ircldl73zkdd54gwqa

"Multi-screen in One" System Design of Education Video Oriented U-learning

Xiao Jun, Wang Lamei, Zhu Xiaoxiao
2014 EAI Endorsed Transactions on Future Intelligent Educational Environments  
Supported by the key technology of "multi-screen in one", the multimedia asset management system and personalized video resource recommendation system are established and applied to Shanghai Lifelong Learning  ...  On the research of the transcoding and the adaptive distribution and scheduling of education video with multiplatform compatibility, this paper proposes the overall technological solution of "multi-screen  ...  Acknowledgements This paper was supported by Engineering Technology Research Centre of Shanghai Science and Technology Research Program (13DZ2252200), and also supported by Innovation Program of Shanghai  ... 
doi:10.4108/fiee.1.1.e5 fatcat:r3ppnbwnu5fznfylo4k7kjbiqu

Tagging diversity in personal learning environments

Yiwei Cao, Dejan Kovachev, Ralf Klamma, Matthias Jarke, Rynson W. H. Lau
2015 Journal of Computers in Education  
We have exemplified these behaviors by the design, realization, and evaluation of a PLE for classical Chinese poetry.  ...  Tagging is a prevalent practice in the Web 2.0. It has been widely used to annotate different media like video.  ...  ''Orchestration of diverse tagging approaches'' section pertains to concepts and design of various tagging approaches, including community-based, semantic, multi-granular, and expert-amateur tagging approaches  ... 
doi:10.1007/s40692-015-0027-0 fatcat:o3qe5dfrd5bydaapm3kbmn6kii

A synergistic strategy for combining thesaurus-based and corpus-based approaches in building ontology for multilingual search engines

Leyla Zhuhadar
2016 Figshare  
In this article we illustrate a methodology for building cross-language search engine. A synergisticapproach between thesaurus-based approach and corpus-based approach is proposed.  ...  First, a bilingualontology thesaurus is designed with respect to two languages: English and Spanish, where a simplebilingual listing of terms, phrases, concepts, and subconcepts is built.  ...  This approach helps alleviate some of the problems in E-learning that are due to the volume of data that can be overwhelming for a learner.  ... 
doi:10.6084/m9.figshare.3423686.v1 fatcat:h7un4wlxyfg67avecgk7ub36qu

Towards an Adaptive Learning System Based on a New Learning Object Granularity Approach

Amal Battou, Ali El, Chihab Cherkaoui, Driss Mammass
2011 International Journal of Advanced Computer Science and Applications  
For that purpose, we present the learning objects approach and the related technologies.  ...  After that, we present some learning object granularity approaches in the literature before presenting our granularity approach.  ...  For the first approach, it defines the granularity of the LO based on the number of concept and idea combined in this LO.  ... 
doi:10.14569/ijacsa.2011.020902 fatcat:nzljzxsthnc6ja22ljqq5rctju

Quaero at TRECVID 2012: Semantic Indexing

Bahjat Safadi, Nadia Derbas, Abdelkader Hamadi, Franck Thollard, Georges Quénot, Jonathan Delhumeau, Hervé Jégou, Tobias Gehrig, Hazim Kemal Ekenel, Rainer Stifelhagen
2012 TREC Video Retrieval Evaluation  
For the semantic indexing task, our approach uses a six-stages processing pipelines for computing scores for the likelihood of a video shot to contain a target concept.  ...  These scores are then used for producing a ranked list of images or shots that are the most likely to contain the target concept.  ...  Acknowledgments This work was partly realized as part of the Quaero Programme funded by OSEO, French State agency for innovation.  ... 
dblp:conf/trecvid/SafadiDHTQDJGES12 fatcat:hiwgnldouvebxeth442fofr6ce

The Design of WASPEC: A Fully Personalised Moodle System Using Semantic Web Technologies

Ufuoma Chima Apoki
2021 Computers  
In this paper, we propose a framework for personalised learning, Weighted Agent System for Personalised E-learning Curriculum (WASPEC) implemented with Moodle, which is independent of the learning management  ...  Personalisation in e-learning systems has become a major research area in recent times, as online learning is gradually evolving to become a major part of formal education.  ...  where any kind of data (sounds, documents, videos, pictures) can be stored.  ... 
doi:10.3390/computers10050059 doaj:6c2776bd559a44669f61b1bf34479391 fatcat:2chwlvxslret3lsp57s6mpjdrq

Semantic Annotation and Search for Educational Resources Supporting Distance Learning
English

Mrs Nithya C, Mr K. Saravanan
2014 International Journal of Engineering Trends and Technoloy  
In the prototype development, the platform uses existing video resources for education articles.  ...  Most of the video resources are currently annotated in an isolated way, which means that they lack semantic connections.  ...  Sansu-Wolke is designed to help the learner in navigating learning resources using Linked Data, so its first task is to connect the learner with appropriate concepts in the Semantic Web.  ... 
doi:10.14445/22315381/ijett-v8p252 fatcat:c4avcx7dpvfg7jhnapowfnoqau

Formalization of Learning Objects for Image-based Language Learning in Mobile Environments

Oleg Starostenko, Claudia Perez-Lezama, V. Alarcon-Aquino, J. Alfredo Sanchez
2014 Procedia - Social and Behavioral Sciences  
and some approaches for retrieval and visualization of multimedia documents in mobile environments.  ...  from inception to implementation, establishing tasks and roles of all actors involved in the development, learning, interaction, evaluation and feedback processes.  ...  Acknowledgements This research has been partly supported by European Grant #247083: Security, Services, Networking and Performance of Next Generation IP-based Multimedia Wireless Networks  ... 
doi:10.1016/j.sbspro.2014.01.864 fatcat:l32ekx7xpba5ndxt44xxg34quu

A New Approach based on a Multi-ontologies and Multi-agents System to Generate Customized Learning Paths in an E-Learning Platform

Jaber El Bouhdidi, Mohamed Ghailani, Otman Abdoun, Abdelhadi Fennan
2010 International Journal of Computer Applications  
In this paper we propose a model of E-Learning based on a process of coupling of ontologies and multi-agent systems for a synergy of their strengths.  ...  Currently the Multi-Agents System (MAS) have discussed several areas such as in the field of education.  ...  To improve the relevance of research services, we propose in this paper an approach based on using ontology to classify targets in a hierarchical goals and an ontology of educational resources for document  ... 
doi:10.5120/1646-2214 fatcat:ruxlkhwmsjhf3mx5bjzzdree7a

Design And Development Of Context-Aware Recommendation Strategy For E-Learning

Shaina Raza, Syed Raza Bashir, Muhammad Tahir Hameed, Muhammad Jawwad Zaheer
2015 VFAST Transactions on Software Engineering  
The existing approaches in this regard focus on learners' ratings, history, behavior and interests, rather ignored the knowledge gain and learning outcomes by the learners.  ...  Secondly, the design and development of context-aware methodology for recommending LOs to the learners is proposed. Third contribution of the research is a mapping algorithm.  ...  A general description of the proposed framework is shown in the figure1. Context in RS in e-learning. The concept of "context" in RS for e-learning differs substantially from other fields.  ... 
doi:10.21015/vtse.v7i2.340 fatcat:g2srjkrg7nhnhpiko5sigkj54a
« Previous Showing results 1 — 15 out of 8,452 results