Filters








60 Hits in 4.4 sec

Dublin City University Video Track Experiments for TREC 2001

Paul Browne, Cathal Gurrin, Hyowon Lee, Kieran McDonald, Sorin Sav, Alan F. Smeaton, Jiamin Ye
2001 Text Retrieval Conference  
Dublin City University participated in the interactive search task and Shot Boundary Detection task * of the TREC Video Track.  ...  The purpose of this experiment was to compare video browsers and so a method was developed for combining independent users' results for a topic into one set of results.  ...  Introduction This year Dublin City University took part in the video track where we submitted runs for both the interactive search task and the automatic shot boundary task.  ... 
dblp:conf/trec/BrowneGLMSSY01 fatcat:e6g7plwulzfmpmtvwuvykojg2m

The TREC2001 Video Track: Information Retrieval on Digital Video Information [chapter]

Alan F. Smeaton, Paul Over, Cash J. Costello, Arjen P. de Vries, David Doermann, Alexander Hauptmann, Mark E. Rorvig, John R. Smith, Lide Wu
2002 Lecture Notes in Computer Science  
The reason for writing this paper is to highlight the message from the TREC video track that there are now a variety of approaches available for searching and browsing through digital video archives, that  ...  During 2001, the annual TREC activity, which has been benchmarking the performance of information retrieval techniques on a range of media for 10 years, included a "track" or activity which allowed investigation  ...  Dublin City University (Ireland) The group from Dublin City University explored interactive search and retrieval from digital video by employing more than 30 users to perform the search tasks under controlled  ... 
doi:10.1007/3-540-45747-x_20 fatcat:nslbajuasnhidao23jzw45xqp4

The TREC-2002 Video Track Report

Alan F. Smeaton, Paul Over
2002 Text Retrieval Conference  
New in TREC 2002 At the TREC 2001 video track workshop in November 2001, the track set a number of goals for improvement (Smeaton, Over, & Taban, 2002) and in the subsequent months through cooperative  ...  TREC video track.  ... 
dblp:conf/trec/SmeatonO02 fatcat:csw2fkotczf6vfpuocivvs7iga

Building Better Search Engines by Measuring Search Quality

Ellen M. Voorhees, Paul Over, Ian Soboroff
2014 IT Professional Magazine  
For example, users expect web search engines to direct searchers to web sites based on the content of the site rather than the site address, and video search engines someday to return video clips based  ...  Origins of TREC Today we take search for text documents in our native language for granted, but web search engines such as Yahoo, Google, and Bing were not built in a day, nor is web content the only area  ...  A 2009 bibliometric study by library scientists at Dublin City University found 310 (unrefereed) workshop papers had been produced by TRECVID participants between 2003 and 2009 as well as 2,073 peer-reviewed  ... 
doi:10.1109/mitp.2013.105 fatcat:hk3zocjbxjawhfuye4k7gkcvqq

Successful approaches in the TREC video retrieval evaluations

Alexander G. Hauptmann, Michael G. Christel
2004 Proceedings of the 12th annual ACM international conference on Multimedia - MULTIMEDIA '04  
The task involves the search and retrieval of shots from MPEG digitized video recordings using a combination of automatic speech, image and video analysis and information retrieval technologies.  ...  This paper reviews successful approaches in evaluations of video retrieval over the last three years.  ...  NON-INTERACTIVE SEARCH 3.1 Automatic Search at the 1st TREC Video Track in 2001 The first TREC Video Retrieval track in 2001 had an automatic retrieval condition, which implied that the queries could not  ... 
doi:10.1145/1027527.1027681 dblp:conf/mm/HauptmannC04 fatcat:45xpbxgavbcw3c6w6yx42ssla4

Design, implementation and testing of an interactive video retrieval system

Georgina Gaughan, Alan F. Smeaton, Cathal Gurrin, Hyowon Lee, Kieran McDonald
2003 Proceedings of the 5th ACM SIGMM international workshop on Multimedia information retrieval - MIR '03  
To do this we will look at the strategy we used in designing the system, and we discuss and evaluate the experiments used to determine the value and effectiveness of one system incorporating both feature  ...  The system is fully MPEG-7 compliant and uses XML for exchange of information within the overall architecture.  ...  The authors would like to thank the Informatics Research Initiative of Enterprise Ireland and the Irish Research Council for Science, Engineering and Technology for support.  ... 
doi:10.1145/973264.973269 dblp:conf/mir/GaughanSGLM03 fatcat:rdrkuxhchzghpfqgrwit7az4tq

Evaluation campaigns and TRECVid

Alan F. Smeaton, Paul Over, Wessel Kraaij
2006 Proceedings of the 8th ACM international workshop on Multimedia information retrieval - MIR '06  
The TREC Video Retrieval Evaluation (TRECVid) is an international benchmarking activity to encourage research in video information retrieval by providing a large test collection, uniform scoring procedures  ...  Throughout its existence, TRECVid has benchmarked both interactive and automatic/manual searching for shots from within a video corpus, automatic detection of a variety of semantic and low-level video  ...  each master shot (Dublin City Uni- versity) -Feature annotation tools (IBM, Carnegie Mellon University) -Feature annotation (20+ research groups) for 39 features in 50 hours of video -Low level  ... 
doi:10.1145/1178677.1178722 dblp:conf/mir/SmeatonOK06 fatcat:oecxegqkqzb3zmkge4y62vbpga

Dublin City University and Partners' Participation in the INS and VTT Tracks at TRECVid 2016

Mark Marsden, Eva Mohedano, Kevin McGuinness, Andrea Calafell, Xavier Giró-i-Nieto, Noel E. O'Connor, Jiang Zhou, Lucas Azevedo, Tobias Daudert, Brian Davis, Manuela Hürlimann, Haithem Afli (+5 others)
2016 TREC Video Retrieval Evaluation  
Dublin City University participated with a consortium of colleagues from NUI Galway and Universitat Politècnica de Catalunya in two tasks in TRECVid 2016, Instance Search (INS) and Video to Text (VTT).  ...  For the VTT task we ran 1,000 concept detectors from the VGG-16 deep CNN on 10 keyframes per video and submitted 4 runs for caption re-ranking, based on BM25, Fusion, word2vec and a fusion of baseline  ...  Introduction A team of researchers from Dublin City University (Insight and ADAPT Research Centres), National University of Ireland, Galway (Insight Research Centre) and Universitat Politècnica de Catalunya  ... 
dblp:conf/trecvid/MarsdenMMCNOZAD16 fatcat:q7ga4yi3hrgepgumpmhuwuvdei

Video Collaborative Annotation Forum: Establishing Ground-Truth Labels on Large Multimedia Datasets

Ching-Yung Lin, Belle L. Tseng, John R. Smith
2003 TREC Video Retrieval Evaluation  
IBM MPEG-7 Annotation Tool, for collaborative multimedia annotation task in a distributed environment. The VideoAnnEx assists authors in the task of annotating video sequences with MPEG-7 metadata.  ...  This large set of valuable ground-truth data is publicly available to the research community, especially for multimedia indexing and retrieval, semantic understanding, and supervised machine learning fields  ...  Tsing-Hua Univ.) , Yunlong Zhao (National University of Singapore), Esin Guldogan (Tampere University of Technology), Zeeshan Rasheed (the University of Central Florida), Uri Lurgel (the University of  ... 
dblp:conf/trecvid/LinTS03 fatcat:cyqfun3dc5fdtp5cwmjvgpn6wq

Content-based video retrieval: Three example systems from TRECVid

Alan F. Smeaton, Peter Wilkins, Marcel Worring, Ork de Rooij, Tat-Seng Chua, Huanbo Luan
2008 International journal of imaging systems and technology (Print)  
Content-based video retrieval techniques are not yet scalable enough to allow interactive searching on Internet-scale, but the techniques are proving robust and effective for smaller collections.  ...  However, user-assigned tags have limitations for retrieval and often we want access where the content of the video itself is directly matched against a user's query rather than against some manually assigned  ...  This section is included as background and is followed by an overview of each of three representative video retrieval systems developed by Dublin City University/K-Space, by the University of Amsterdam  ... 
doi:10.1002/ima.20150 fatcat:zq4xgfb5lfgfpaohrnpir4wnw4

Comparative Evaluation of Cross-language Information Retrieval Systems [chapter]

Carol Peters
2005 Lecture Notes in Computer Science  
the research community with an infrastructure for testing and evaluating systems operating in multilingual contexts and a common platform for the comparison of methodologies and results.  ...  With the increasing importance of the "Global Information Society" and as the world's depositories of online collections proliferate, there is a growing need for systems that enable access to information  ...  This track is being coordinated by Dublin City University and the University of Maryland. Cross-Language Retrieval in Image Collections.  ... 
doi:10.1007/978-3-540-31842-2_16 fatcat:4ad3pwr6pnhr5n6v3gwzsqd4cu

VideOlympics: Real-Time Evaluation of Multimedia Retrieval Systems

Cees G.M. Snoek, Marcel Worring, Ork de Rooij, Koen E.A. van de Sande, Rong Yan, Alexander G. Hauptmann
2008 IEEE Multimedia  
We thank Paul Over from NIST for providing the search topics. Finally, we thank Fabchannel for producing the video trailer.  ...  Acknowledgments We thank the searchers and the audience for participation. We thank Johan Oomen and Claartje Kok for the local arrangements at Beeld en Geluid.  ...  The Fraunhofer Institute provided a camera shot segmentation for this video archive, yielding a total of 79,484 unique shots. For each individual shot, Dublin City University extracted keyframes.  ... 
doi:10.1109/mmul.2008.21 fatcat:jzmhjgnf5jflhjwpeshvxcrmsa

TRECVID 2005 - An Overview

Paul Over, Tzveta Ianeva, Wessel Kraaij, Alan F. Smeaton
2005 TREC Video Retrieval Evaluation  
at Dublin City University (DCU) for formating the master shot reference definition and selecting keyframes.  ...  Richard Wright at the BBC Archive made the rushes data available and Gary Marchionini and the Open Video Project at the University of North Carolina at Chapel Hill helped us get the NASA videos in MPEG  ...  City University of Hong Kong experimented with methods for structuring and characterizing video content by using motion to infer intention.  ... 
dblp:conf/trecvid/OverIKS05 fatcat:czlfoelhrnaxnnhwr74antamqi

Report on the 25th European conference on information retrieval research (ECIR-03)

Fabrizio Sebastiani
2003 SIGIR Forum  
The next edition of ECIR (http://ecir04.sunderland.ac.uk/) will take place at the University of Sunderland, UK, from April 5 to 7, 2004, and will be organized by Sharon McDonald and John Tait.  ...  Koster (University of Nijmegen, NL), Peter Ingwersen (Royal School of Library and Information Science, DK), and Alan Smeaton (Dublin City University, IE).  ...  of interest recently in view of the rather uninspiring results obtained in the TREC Web track by systems making use of link-based information.  ... 
doi:10.1145/959258.959261 fatcat:5tvmjt4xkfhirjaeygixjjk3lu

Dublin City University Video Track Experiments for TREC 2003

Paul Browne, Csaba Czirjek, Georgina Gaughan, Cathal Gurrin, Gareth J. F. Jones, Hyowon Lee, Seán Marlow, Kieran McDonald, Noel Murphy, Noel E. O'Connor, Neil O'Hare, Alan F. Smeaton (+1 others)
2003 TREC Video Retrieval Evaluation  
In this paper, we describe our experiments for both the News Story Segmentation task and Interactive Search task for TRECVID 2003.  ...  Our Search task experiment compared a video retrieval system based on text, image and relevance feedback with a text-only video retrieval system in order to identify which was more effective.  ...  We used the questionnaire developed over several years by the TREC Interactive track (TREC Interactive Track, 2003) .  ... 
dblp:conf/trecvid/BrowneCGGJ0MMMO03 fatcat:yotndamkd5gy3a3wov2hg7nzjy
« Previous Showing results 1 — 15 out of 60 results