Optimizing user expectations for video semantic filtering and abstraction

@article{Lin2005OptimizingUE,
  title={Optimizing user expectations for video semantic filtering and abstraction},
  author={Ching-Yung Lin and Belle L. Tseng},
  journal={2005 IEEE International Symposium on Circuits and Systems},
  year={2005},
  pages={1250-1253 Vol. 2}
}
We describe a novel automatic system that generates personalized videos based on semantic filtering or summarization techniques. This system uses a new set of more than one hundred visual semantic detectors that automatically detect video concepts in faster than realtime. Based on personal profiles, the system generates either video summaries from video databases or filtered video contents from live broadcasting videos. The prototype experiments have shown the effectiveness and stabilities of… CONTINUE READING

Figures, Results, and Topics from this paper.

Key Quantitative Results

  • show these CDS models can improve the state-of-the-art IBM visual semantic detectors by 21% in mean average precision and more than 10 times better in detection speed.

References

Publications referenced by this paper.
SHOWING 1-10 OF 12 REFERENCES

Understanding and modeling user interests in consumer videos

  • 2004 IEEE International Conference on Multimedia and Expo (ICME) (IEEE Cat. No.04TH8763)
  • 2004
VIEW 1 EXCERPT

Content-adaptive utility-based video adaptation

  • 2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698)
  • 2003
VIEW 1 EXCERPT

Involving Users in the Design of User Interfaces for TV Recommender Systems,

J. van Barneveld, M. van Setten
  • Proc. of the UW Workshop on Personalization in Future TV,
  • 2003
VIEW 1 EXCERPT