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

Abstract

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.

Cite

Text

Yuan et al. "Efficient Mining of Repetitions in Large-Scale TV Streams with Product Quantization Hashing." European Conference on Computer Vision, 2012. doi:10.1007/978-3-642-33863-2_27

Markdown

[Yuan et al. "Efficient Mining of Repetitions in Large-Scale TV Streams with Product Quantization Hashing." European Conference on Computer Vision, 2012.](https://mlanthology.org/eccv/2012/yuan2012eccv-efficient/) doi:10.1007/978-3-642-33863-2_27

BibTeX

@inproceedings{yuan2012eccv-efficient,
  title     = {{Efficient Mining of Repetitions in Large-Scale TV Streams with Product Quantization Hashing}},
  author    = {Yuan, Jiangbo and Gravier, Guillaume and Campion, Sébastien and Liu, Xiuwen and Jégou, Hervé},
  booktitle = {European Conference on Computer Vision},
  year      = {2012},
  pages     = {271-280},
  doi       = {10.1007/978-3-642-33863-2_27},
  url       = {https://mlanthology.org/eccv/2012/yuan2012eccv-efficient/}
}