ACM Home Page
Please provide us with feedback. Feedback
MediaMill: exploring news video archives based on learned semantics
Full text PdfPdf (4.55 MB)
Source International Multimedia Conference archive
Proceedings of the 13th annual ACM international conference on Multimedia table of contents
Hilton, Singapore
DEMONSTRATION SESSION: Technical demonstration 1: media understanding and browsing table of contents
Pages: 225 - 226  
Year of Publication: 2005
ISBN:1-59593-044-2
Authors
Cees G. M. Snoek  University of Amsterdam, Amsterdam, The Netherlands
Marcel Worring  University of Amsterdam, Amsterdam, The Netherlands
Jan van Gemert  University of Amsterdam, Amsterdam, The Netherlands
Jan-Mark Geusebroek  University of Amsterdam, Amsterdam, The Netherlands
Dennis Koelma  University of Amsterdam, Amsterdam, The Netherlands
Giang P. Nguyen  University of Amsterdam, Amsterdam, The Netherlands
Ork de Rooij  University of Amsterdam, Amsterdam, The Netherlands
Frank Seinstra  University of Amsterdam, Amsterdam, The Netherlands
Sponsors
ACM: Association for Computing Machinery
SIGGRAPH: ACM Special Interest Group on Computer Graphics and Interactive Techniques
SIGMULTIMEDIA: ACM Special Interest Group on Multimedia
Publisher
ACM  New York, NY, USA
Bibliometrics
Downloads (6 Weeks): n/a,   Downloads (12 Months): n/a,   Citation Count: 10
Additional Information:

abstract   references   cited by   index terms   collaborative colleagues  

Tools and Actions: Request Permissions Request Permissions    Review this Article  
DOI Bookmark: Use this link to bookmark this Article: http://doi.acm.org/10.1145/1101149.1101188
What is a DOI?

ABSTRACT

In this technical demonstration we showcase the MediaMill system. A search engine that facilitates access to news video archives at a semantic level. The core of the system is an unprecedented lexicon of 100 automatically detected semantic concepts. Based on this lexicon we demonstrate how users can obtain highly relevant retrieval results using query-by-concept. In addition, we show how the lexicon of concepts can be exploited for novel applications using advanced semantic visualizations. Several aspects of the MediaMill system are evaluated as part of our TRECVID 2005 efforts.


REFERENCES

Note: OCR errors may be found in this Reference List extracted from the full text article. ACM has opted to expose the complete List rather than only correct and linked references.

 
1
Blinkx Video Search, August 2005. http://www.blinkx.tv/.
 
2
 
3
Google Video Search, August 2005. http://video.google.com/.
 
4
G. Nguyen and M. Worring. Similarity based visualization of image collections. In Int'l Worksh. on Audio-Visual Content and Information Visualization in Digital Libraries, 2005.
 
5
A. Smeaton. Large scale evaluations of multimedia information retrieval: The TRECVid experience. In CIVR, volume 3569 of LNCS, pages 19--27. Springer-Verlag, 2005.
 
6
C. Snoek. The Authoring Metaphor to Machine Understanding of Multimedia. PhD thesis, Universiteit van Amsterdam, October 2005.

CITED BY  11

Collaborative Colleagues:
Cees G. M. Snoek: colleagues
Marcel Worring: colleagues
Jan van Gemert: colleagues
Jan-Mark Geusebroek: colleagues
Dennis Koelma: colleagues
Giang P. Nguyen: colleagues
Ork de Rooij: colleagues
Frank Seinstra: colleagues