Advanced search
1 file | 747.90 KB

Video copy detection using inclined video tomography and bag-of-visual-words

Author
Organization
Abstract
Techniques for video fingerprinting are helpful in managing vast libraries of video clips. Recent advances have shown that video tomography and Bag-of-Visual-Words (BoVW) can be successfully used for the purpose of video fingerprinting. In this paper, we introduce a novel video signature (i.e., a novel video fingerprint) that takes advantage of both video tomography and BoVW. Specifically, the proposed video signature is created by first extracting inclined tomography images from the video content, and by subsequently applying the BoVW approach to the inclined tomography images obtained. The key to our approach is that we make the angle of inclination of the tomography images dependent on the amount of motion in the video content. That way, the proposed video signature is able to capture both spatial and temporal information. Experimental results obtained for the publicly available TREVID-2009 video set indicate that video copy detection by means of the proposed video signature is robust against spatial and temporal transformations.
Keywords
video identification, video tomography, video copy detection, Bag-of-visual-words

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 747.90 KB

Citation

Please use this url to cite or link to this publication:

Chicago
Min, Hyun-seok, Se Min Kim, Wesley De Neve, and Yong Man Ro. 2012. “Video Copy Detection Using Inclined Video Tomography and Bag-of-visual-words.” In IEEE International Conference on Multimedia and Expo, Proceedings, 562–567. Piscataway, NJ, USA: IEEE.
APA
Min, H., Kim, S. M., De Neve, W., & Ro, Y. M. (2012). Video copy detection using inclined video tomography and bag-of-visual-words. IEEE International Conference on Multimedia and Expo, Proceedings (pp. 562–567). Presented at the IEEE International Conference on Multimedia and Expo (ICME - 2012), Piscataway, NJ, USA: IEEE.
Vancouver
1.
Min H, Kim SM, De Neve W, Ro YM. Video copy detection using inclined video tomography and bag-of-visual-words. IEEE International Conference on Multimedia and Expo, Proceedings. Piscataway, NJ, USA: IEEE; 2012. p. 562–7.
MLA
Min, Hyun-seok, Se Min Kim, Wesley De Neve, et al. “Video Copy Detection Using Inclined Video Tomography and Bag-of-visual-words.” IEEE International Conference on Multimedia and Expo, Proceedings. Piscataway, NJ, USA: IEEE, 2012. 562–567. Print.
@inproceedings{2996826,
  abstract     = {Techniques for video fingerprinting are helpful in managing vast libraries of video clips. Recent advances have shown that video tomography and Bag-of-Visual-Words (BoVW) can be successfully used for the purpose of video fingerprinting. In this paper, we introduce a novel video signature (i.e., a novel video fingerprint) that takes advantage of both video tomography and BoVW. Specifically, the proposed video signature is created by first extracting inclined tomography images from the video content, and by subsequently applying the BoVW approach to the inclined tomography images obtained. The key to our approach is that we make the angle of inclination of the tomography images dependent on the amount of motion in the video content. That way, the proposed video signature is able to capture both spatial and temporal information. Experimental results obtained for the publicly available TREVID-2009 video set indicate that video copy detection by means of the proposed video signature is robust against spatial and temporal transformations.},
  author       = {Min, Hyun-seok and Kim, Se Min and De Neve, Wesley and Ro, Yong Man},
  booktitle    = {IEEE International Conference on Multimedia and Expo, Proceedings},
  isbn         = {9780769547299},
  issn         = {1945-7871},
  keyword      = {video identification,video tomography,video copy detection,Bag-of-visual-words},
  language     = {eng},
  location     = {Melbourne, Australia},
  pages        = {562--567},
  publisher    = {IEEE},
  title        = {Video copy detection using inclined video tomography and bag-of-visual-words},
  url          = {http://dx.doi.org/10.1109/ICME.2012.58},
  year         = {2012},
}

Altmetric
View in Altmetric