Mediamill: Searching Multimedia Archives Based on Learned Semantics

Cees G. M. Snoek, Dennis C. Koelma, Jeroen van Rest, Nellie Schipper, Frank J. Seinstra, Andrew H. C. Thean, Marcel Worring

Abstract

Video is about to conquer the Internet. Real-time delivery of video content is technically possible to any desktop and mobile device, even with modest connections. The main problem hampering massive (re)usage of video content today is the lack of effective content-based tools that provide semantic access. In this contribution, we discuss systems for both video analysis and video retrieval that facilitate semantic access to video sources. Both systems were evaluated in the 2004 TRECVID benchmark as top performers in their task
BibTeX
@inproceedings{snoek2005mediamill,
  author = {Cees G. M. Snoek and Dennis C. Koelma and Jeroen van Rest and Nellie Schipper and Frank J. Seinstra and Andrew H. C. Thean and Marcel Worring},
  title = {{Mediamill: Searching Multimedia Archives Based on Learned Semantics}},
  booktitle = {ICME},
  year = {2005},
  doi = {10.1109/icme.2005.1521736},
}

Loading related content...

Figure