Filters








22,504 Hits in 4.4 sec

Large Scale Evaluations of Multimedia Information Retrieval: The TRECVid Experience [chapter]

Alan F. Smeaton
2005 Lecture Notes in Computer Science  
The main contribution, however, is a set of pointers and a summarisation of the work done as part of TRECVid, the annual benchmarking exercise for video retrieval tasks.  ...  Information Retrieval is a supporting technique which underpins a broad range of content-based applications including retrieval, filtering, summarisation, browsing, classification, clustering, automatic  ...  Acknowledgments The author wishes to acknowledge the considerable input of Paul Over (NIST) and Wessel Kraaij (TNO) who, along with the author, coordinate TRECVid each year.  ... 
doi:10.1007/11526346_2 fatcat:3on37iw4ergejarzhsxljbblhi

Automated text summarisation and evidence-based medicine: A survey of two domains [article]

Abeed Sarker, Diego Molla, Cecile Paris
2017 arXiv   pre-print
We envision that this survey will serve as a first resource for the development of future operational text summarisation techniques for EBM.  ...  We present a survey of EBM, the domain-specific needs for EBM, automated summarisation techniques, and how they have been applied hitherto.  ...  ROUGE is also used for evaluation but shows little variation in performance for distinct combinations of features.  ... 
arXiv:1706.08162v1 fatcat:q7jxiwam75aj3prwmqhr3arcpu

V-ROOM: a virtual meeting system with intelligent structured summarisation

Anne E. James, Antonios G. Nanos, Philip Thompson
2015 Enterprise Information Systems  
The survey results showed that meeting summarisation is one of the most important new features that should be added to virtual meeting systems for enterprises.  ...  This paper describes the development of a virtual meeting system, called V-ROOM. An exploration of facilities required in such a system has been conducted.  ...  Both assisted and automatic summarisation relies heavily on a recognised structure of a meeting.  ... 
doi:10.1080/17517575.2015.1019571 fatcat:fruoqtfbajaulnt6fi5cy2eb3y

ICBR – Multimedia Management System for Intelligent Content Based Retrieval [chapter]

Janko Ćalić, Neill Campbell, Majid Mirmehdi, Barry T. Thomas, Ron Laborde, Sarah Porter, Nishan Canagarajah
2004 Lecture Notes in Computer Science  
This paper presents a system designed for the management of multimedia databases that embarks upon the problem of efficient media processing and representation for automatic semantic classification and  ...  The system demonstrator will be developed as a part of an ICBR project within the 3C Research programme of convergent technology research for digital media processing and communications.  ...  Acknowledgements The work reported in this paper has formed part of the ICBR project within the 3C Research programme of convergent technology research for digital media processing and communications whose  ... 
doi:10.1007/978-3-540-27814-6_70 fatcat:blnfvc3ez5fgxdjcenol3ecky4

Automatic summarising: The state of the art

Karen Spärck Jones
2007 Information Processing & Management  
the range of systems built.  ...  The paper uses several frameworks to organise the review, for summarising itself, for the factors affecting summarising, for systems, and for evaluation.  ...  Introduction In the last decade there has been a surge of interest in automatic summarising.  ... 
doi:10.1016/j.ipm.2007.03.009 fatcat:zzyosnd4ezfi3n23zhl3ahim3m

Towards Personalized and Human-in-the-Loop Document Summarization [article]

Samira Ghodratnama
2021 arXiv   pre-print
We propose novel approaches to tackle these challenges, by: i)enabling automatic intelligent feature engineering, ii) enabling flexible and interactive summarisation, iii) utilising intelligent and personalised  ...  The ubiquitous availability of computing devices and the widespread use of the internet have generated a large amount of data continuously.  ...  Feature Set We explored a broad range of features that are commonly used for summarisation.  ... 
arXiv:2108.09443v2 fatcat:245c3byhg5htrnmbnoofexzh3u

Techniques used and open challenges to the analysis, indexing and retrieval of digital video

Alan F. Smeaton
2007 Information Systems  
NOTICE: this is the author's version of a work that was accepted for publication in Information Systems.  ...  We conclude the paper with a list of grand challenges for researchers working in the area.  ...  remains an untouched work topic. (4) Clearly if we are going to build systems which use semantic features which are automatically detected from video, then the accuracy of the semantic feature detection  ... 
doi:10.1016/j.is.2006.09.001 fatcat:fwbnujz3tnaz7kbvmys3xo7lua

TRECVID

Alan F. Smeaton, Paul Over, Wessel Kraaij
2004 Proceedings of the 12th annual ACM international conference on Multimedia - MULTIMEDIA '04  
features, and the automatic segmentation of TV news broadcasts into nonoverlapping news stories.  ...  TRECVID is an annual exercise which encourages research in information retrieval from digital video by providing a large video test collection, uniform scoring procedures, and a forum for organizations  ...  speech recognition and shot boundary/keyframe data for the track participants for a number of years.  ... 
doi:10.1145/1027527.1027678 dblp:conf/mm/SmeatonOK04 fatcat:pbgph74w3fbdjfn2edastunywi

Automatically selecting shots for action movie trailers

Alan F. Smeaton, Bart Lehane, Noel E. O'Connor, Conor Brady, Gary Craig
2006 Proceedings of the 8th ACM international workshop on Multimedia information retrieval - MIR '06  
A set of audiovisual features are extracted that aim to model the characteristics of shots typically present in trailers, and a support vector machine is utilised in order to select the relevant shots.  ...  This paper presents an approach which automatically selects shots from action movies in order to assist in the creation of trailers.  ...  We are grateful for insightful comments and feedback provided by reviewers.  ... 
doi:10.1145/1178677.1178709 dblp:conf/mir/SmeatonLOBC06 fatcat:pohkvvszhrd2nks5pjpcxll4mu

Automatic generation of weather forecast texts using comprehensive probabilistic generation-space models

ANJA BELZ
2007 Natural Language Engineering  
This paper reports experiments in which pcru -a generation framework that combines probabilistic generation methodology with a comprehensive model of the generation space -was used to semi-automatically  ...  The generators were evaluated in terms of output quality, development time and computational efficiency against (i) human forecasters, (ii) a traditional handcrafted pipelined nlg system, and (iii) a halogen-style  ...  Also gratefully acknowledged is the contribution of the (anonymous) enlg'05 reviewer who suggested the basic idea behind greedy roulette-wheel selection.  ... 
doi:10.1017/s1351324907004664 fatcat:b64n4u6tcndojkqoc6t2t7xyhi

High-Level Feature Detection from Video in TRECVid: A 5-Year Retrospective of Achievements [chapter]

Alan F. Smeaton, Paul Over, Wessel Kraaij
2008 Signals and Communication Technology  
In turn (and this is the main reason why they are called features), the high-level features can be used as features by a higher level interpretation module, combining different high-level features in a  ...  Over the last few years, the lexicon size of state-of-the-art systems for content based video access has grown from several tens to several hundreds and there is evidence that high-level features indeed  ...  There are many people and groups of people whom the authors would like to thank for making the TRECVid activity possible.  ... 
doi:10.1007/978-0-387-76569-3_6 fatcat:yywkxkexqfd3rhahj4w4z6raqq

Information retrieval and digital libraries

Karen Spärck Jones
2007 Proceedings of the 2006 international workshop on Research issues in digital libraries - IWRIDL '06  
question asnwering and summarising.  ...  These have demonstrated the value of statistical techniques for retrieval, and have also shown that they have an important, though not exclusive, part to play in other information processing tasks, like  ...  Even so, it is possible to claim some progress in building NLIP systems for a range of tasks over the last decade, i.e. progress in building systems that are performing better both intuitively and against  ... 
doi:10.1145/1364742.1364743 dblp:conf/iwridl/Jones06 fatcat:fq53ig4hfjaw7plutz5secs7mq

Teaching Creativity: The Case for/Against Genetic Algorithms as a Model of Human Creativity

John L. Dennis
2011 The Open Education Journal  
These principles include the memorisation, storage and retrieval of information as well as the combination and recombination of simple elements within a mechanical procedure of trial and error that formulate  ...  the foundation of a cumulative process.  ...  Dennis and a University for Foreigners Research Grant to Aldo Stella. John L.  ... 
doi:10.2174/1874920801104010036 fatcat:2kaf7rgtcretlap22ip3fogy5a

A survey of methods to ease the development of highly multilingual text mining applications

Ralf Steinberger
2011 Language Resources and Evaluation  
In this paper, we gather insights by various multilingual system developers on how to minimise the effort of developing natural language processing applications for many languages.  ...  EMM is a set of complex media monitoring tools that process and analyse up to 100,000 online news articles per day in between twenty and fifty languages.  ...  Building the complex EMM applications was a successful team effort that also includes many less rewarding and less visible tasks.  ... 
doi:10.1007/s10579-011-9165-9 fatcat:mjjrqopbija3tio45n57p5zh44

Detecting cognitive decline using speech only: The ADReSSo Challenge [article]

Saturnino Luz, Fasih Haider, Sofia de la Fuente, Davida Fromm, Brian MacWhinney
2021 medRxiv   pre-print
A combination of acoustic and linguistic features extracted directly from audio recordings, without human intervention, yielded a baseline accuracy of 78.87% for the AD classification task, an MMSE prediction  ...  Building on the success of the ADReSS Challenge at Interspeech 2020, which attracted the participation of 34 teams from across the world, the ADReSSo Challenge targets three difficult automatic prediction  ...  Furthermore, the combination of speech technology and machine learning creates opportunities for automatic screening and diagnosis support systems for dementia.  ... 
doi:10.1101/2021.03.24.21254263 fatcat:ingi44ulpzbgnhqaiqf6e22lby
« Previous Showing results 1 — 15 out of 22,504 results