Filters








6 Hits in 3.9 sec

Answering English Queries in Automatically Transcribed Arabic Speech

Abdusalam F. A. Nwesri, S. M. M. Tahaghoghi, Falk Scholer
2007 6th IEEE/ACIS International Conference on Computer and Information Science (ICIS 2007)  
Using the TRECVID video collection and queries, we show that normalisation, stopwordremoval, and light stemming increase retrieval precision, but that heavy stemming and trigrams have a negative effect  ...  There are several well-known approaches to parsing Arabic text in preparation for indexing and retrieval.  ...  Downloaded on November 8, 2009 at 22:31 from IEEE Xplore. Restrictions apply. Authorized licensed use limited to: RMIT University. Downloaded on November 8, 2009 at 22:31 from IEEE Xplore.  ... 
doi:10.1109/icis.2007.61 dblp:conf/ACISicis/NwesriTS07 fatcat:u7vfwxraereejafmvngcglgwpm

Video shot boundary detection: Seven years of TRECVid activity

Alan F. Smeaton, Paul Over, Aiden R. Doherty
2010 Computer Vision and Image Understanding  
It is a problem which has attracted much attention since video became available in digital form as it is an essential pre-processing step to almost all video analysis, indexing, summarisation, search,  ...  Automatic SBD was one of the tracks of activity within the annual TRECVid benchmarking exercise, each year from 2001 to 2007 inclusive.  ...  TRECVid is a large-scale, worldwide benchmarking activity running annually, whose goal is to encourage research into tasks related to content-based information retrieval on digital video.  ... 
doi:10.1016/j.cviu.2009.03.011 fatcat:w5kluejxi5bfrfrwq7jku7jgda

Modeling Human Judgment of Digital Imagery for Multimedia Retrieval

T. Volkmer, J.A. Thom, S.M.M. Tahaghoghi
2007 IEEE transactions on multimedia  
The application of machine learning techniques to image and video search has been shown to boost the performance of multimedia retrieval systems, and promises to lead to more generalized semantic search  ...  We apply latent class modeling to the annotation data collected during the TRECVID 2005 Annotation Forum, and demonstrate how to use this statistic to clearly classify each image on the basis of varying  ...  ACKNOWLEDGMENT The authors thank all participants of the TRECVID Annotation Forum who have made this evaluation possible. They also thank the Intelligent Information Analysis Group at the IBM T.J.  ... 
doi:10.1109/tmm.2007.900153 fatcat:wpanwisakrbmnizpdwretm7vsa

INEX 2005 Multimedia Track [chapter]

Roelof van Zwol, Gabriella Kazai, Mounia Lalmas
2006 Lecture Notes in Computer Science  
The track is set to continue at INEX 2006.  ...  In this first exploratory year the focus of the evaluation experiment was to test approaches for the retrieval of XML fragments using a combination of content-based text and image retrieval techniques.  ...  runs utwente Cirquid Project (CWI and U. of Twente) 6 3 5 qmul Queen Mary University of London 5 3 1 utrecht Utrecht University 4 3 5 rmit RMIT University 3 3 5 qutau Queensland University  ... 
doi:10.1007/978-3-540-34963-1_38 fatcat:ug7jzl5bxbcgzgmdu5rvduyb7i

Content-based video copy detection

Juan Manuel Barrios
2009 Proceedings of the seventeen ACM international conference on Multimedia - MM '09  
In particular, Content-Based Video Copy Detection (CBVCD) addresses the need to retrieve videos in a collection that are copies of some original document.  ...  Esta tesis ha sido evaluada usando la colección MUSCLE-VCD-2007 y participando en las evaluaciones TRECVID 2010 y 2011. El desempeño logrado en estas evaluaciones es satisfactorio.  ...  Multimedia Information Retrieval (MIR) is the research area that aims at searching and retrieving semantic information from multimedia documents [Lew et al., 2006] .  ... 
doi:10.1145/1631272.1631539 dblp:conf/mm/Barrios09 fatcat:kpjhi2p3orcsrfi444ewana33i

INEX 2005 Multimedia Track [chapter]

Roelof Zwol, Gabriella Kazai, Mounia Lalmas
Lecture Notes in Computer Science  
The track is set to continue at INEX 2006.  ...  In this first exploratory year the focus of the evaluation experiment was to test approaches for the retrieval of XML fragments using a combination of content-based text and image retrieval techniques.  ...  runs utwente Cirquid Project (CWI and U. of Twente) 6 3 5 qmul Queen Mary University of London 5 3 1 utrecht Utrecht University 4 3 5 rmit RMIT University 3 3 5 qutau Queensland University  ... 
doi:10.1007/11766278_38 fatcat:t7rfv4zmqjainoie7ynlcw6v5e