Efficient Mining of Repetitions in Large-Scale TV Streams with Product Quantization Hashing

  • Jiangbo Yuan
  • Guillaume Gravier
  • Sébastien Campion
  • Xiuwen Liu
  • Hervé Jégou
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7583)


Duplicates or near-duplicates mining in video sequences is of broad interest to many multimedia applications. How to design an effective and scalable system, however, is still a challenge to the community. In this paper, we present a method to detect recurrent sequences in large-scale TV streams in an unsupervised manner and with little a priori knowledge on the content. The method relies on a product k-means quantizer that efficiently produces hash keys adapted to the data distribution for frame descriptors. This hashing technique combined with a temporal consistency check allows the detection of meaningful repetitions in TV streams. When considering all frames (about 47 millions) of a 22-day long TV broadcast, our system detects all repetitions in 15 minutes, excluding the computation of the frame descriptors. Experimental results show that our approach is a promising way to deal with very large video databases.


Hash Function Neighbor Search Hash Table Locality Sensitive Hash Hash Code 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Naturel, X., Gros, P.: Detecting repeats for video structuring. Multimedia Tools and Applications 38, 233–252 (2007)CrossRefGoogle Scholar
  2. 2.
    Manson, G., Berrani, S.A.: Automatic tv broadcast structuring. International Journal of Digital Multimedia Broadcasting, 16 pages (2010)Google Scholar
  3. 3.
    Ibrahim, Z.A.A., Gros, P.: Tv stream structuring. ISRN Signal Processing, 17 pages (2011)Google Scholar
  4. 4.
    Gauch, J.M., Shivadas, A.: Finding and identifying unknown commercials using repeated video sequence detection. Computer Vision and Image Understanding 103, 80–88 (2006)CrossRefGoogle Scholar
  5. 5.
    Yang, X., Tian, Q., Member, S., Xue, P.: Efficient short video repeat identification with application to news video structure analysis. IEEE Transactions on Multimedia 9, 600–609 (2007)CrossRefGoogle Scholar
  6. 6.
    Yuan, J., Wang, W., Meng, J., Wu, Y., Li, D.: Mining repetitive clips through finding continuous paths. In: ACM MM 2007, pp. 289–292. ACM, New York (2007)Google Scholar
  7. 7.
    Dong, W., Charikar, M., Li, K.: Efficient k-nearest neighbor graph construction for generic similarity measures. In: WWW (2011)Google Scholar
  8. 8.
    Wang, J., Wang, J., Zeng, G., Tu, Z., Li, S.: Scalable k-nn graph construction for visual descriptors. In: Conf. on Vision and Pattern Recognition (2012)Google Scholar
  9. 9.
    Goh, K.S.: Audio-visual event detection based on mining of semantic audio-visual labels. In: Proceedings of SPIE, vol. 5307, pp. 292–299 (2003)Google Scholar
  10. 10.
    Berrani, S., Manson, G., Lechat, P.: A non-supervised approach for repeated sequence detection in tv broadcast streams. Signal Processing Image Communication 23, 525–537 (2008)CrossRefGoogle Scholar
  11. 11.
    Pua, K.M., Gauch, J.M., Gauch, S.E., Miadowicz, J.Z.: Real time repeated video sequence identification. Computer Vision and Image Understanding 93, 310–327 (2004)CrossRefGoogle Scholar
  12. 12.
    Döhring, I., Lienhart, R.: Mining tv broadcasts for recurring video sequences. In: ACM CIVR 2009, pp. 28:1–28:8. ACM, New York (2009)Google Scholar
  13. 13.
    Paulevé, L., Jégou, H., Amsaleg, L.: Locality sensitive hashing: a comparison of hash function types and querying mechanisms. Pattern Recognition Letters (2010)Google Scholar
  14. 14.
    Jégou, H., Douze, M., Schmid, C.: Product quantization for nearest neighbor search. PAMI 33, 117–128 (2011)CrossRefGoogle Scholar
  15. 15.
    Oliva, A., Torralba, A.B.: Modeling the shape of the scene: A holistic representation of the spatial envelope. IJCV 42, 145–175 (2001)zbMATHCrossRefGoogle Scholar
  16. 16.
    Douze, M., Jégou, H., Singh, H., Amsaleg, L., Schmid, C.: Evaluation of GIST descriptors for web-scale image search. In: CIVR (2009)Google Scholar
  17. 17.
    Naturel, X., Gravier, G., Gros, P.: Fast Structuring of Large Television Streams Using Program Guides. In: Marchand-Maillet, S., Bruno, E., Nürnberger, A., Detyniecki, M. (eds.) AMR 2006. LNCS, vol. 4398, pp. 222–231. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  18. 18.
    Charikar, M.S.: Similarity estimation techniques from rounding algorithms. In: Proc. of 34th STOC, pp. 380–388. ACM (2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Jiangbo Yuan
    • 1
  • Guillaume Gravier
    • 2
  • Sébastien Campion
    • 2
  • Xiuwen Liu
    • 1
  • Hervé Jégou
    • 2
  1. 1.Florida State UniversityTallahasseeUSA
  2. 2.INRIA-IRISARennes CedexFrance

Personalised recommendations