Large-scale, Fast and Accurate Shot Boundary Detection through Spatio-temporal Convolutional Neural Networks

@article{Hassanien2017LargescaleFA,
  title={Large-scale, Fast and Accurate Shot Boundary Detection through Spatio-temporal Convolutional Neural Networks},
  author={Ahmed Hassanien and Mohamed A. Elgharib and Ahmed A. S. Seleim and Mohamed Hefeeda and Wojciech Matusik},
  journal={CoRR},
  year={2017},
  volume={abs/1705.03281}
}
Shot boundary detection (SBD) is an important preprocessing step for video manipulation. Here, each segment of frames is classified as either sharp, gradual or no transition. Current SBD techniques analyze hand-crafted features and attempt to optimize both detection accuracy and processing speed. However, the heavy computations of optical flow prevents this. To achieve this aim, we present an SBD technique based on spatio-temporal Convolutional Neural Networks (CNN). Since current datasets are… CONTINUE READING
Tweets
This paper has been referenced on Twitter 25 times. VIEW TWEETS

Citations

Publications citing this paper.

References

Publications referenced by this paper.
SHOWING 1-10 OF 24 REFERENCES

A genetic algorithm and fuzzy logic approach for video shot boundary detection

  • D. M. Thounaojam, T. Khelchandra, K. M. Singh, S. Roy
  • Computational intelligence and neuroscience,
  • 2016
Highly Influential
4 Excerpts

Similar Papers

Loading similar papers…