A discriminative CNN video representation for event detection

@article{Xu2015ADC,
  title={A discriminative CNN video representation for event detection},
  author={Zhongwen Xu and Yi Yang and Alexander G. Hauptmann},
  journal={2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2015},
  pages={1798-1807}
}
In this paper, we propose a discriminative video representation for event detection over a large scale video dataset when only limited hardware resources are available. The focus of this paper is to effectively leverage deep Convolutional Neural Networks (CNNs) to advance event detection, where only frame level static descriptors can be extracted by the existing CNN toolkits. This paper makes two contributions to the inference of CNN video representation. First, while average pooling and max… CONTINUE READING

From This Paper

Figures, tables, results, and topics from this paper.

Key Quantitative Results

  • Compared to improved Dense Trajectories, which has been recognized as the best video representation for event detection, our new representation improves the Mean Average Precision (mAP) from 27.6% to 36.8% for the TRECVID MEDTest 14 dataset and from 34.0% to 44.6% for the TRECVID MEDTest 13 dataset.

Citations

Publications citing this paper.
SHOWING 1-10 OF 242 CITATIONS, ESTIMATED 46% COVERAGE

242 Citations

02040608020152016201720182019
Citations per Year
Semantic Scholar estimates that this publication has 242 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
SHOWING 1-10 OF 44 REFERENCES

CMU-Informedia at TRECVID 2013 Multimedia Event Detection

  • Z.-Z. Lan, L. Jiang, S.-I. Yu
  • In TRECVID Workshop,
  • 2013
Highly Influential
9 Excerpts

Similar Papers

Loading similar papers…