Copy detection

Copy detection allows to check if a signal is a copy of an original source, even if the copy has been significantly altered: quality corruption, addition of sound s, picture-in-picture inclusion in another video, etc.

We have developed effective techniques, in both precision and speed, for tackling this problem with respect to audio and video signals. These techniques obtained the best result for audio and video copy detection at TRECVID2009 international evaluation and  the 2nd best result in TRECVID 2011.

These techniques have been applied in a wide variety of situations, from duplicate document detection, known advertisement detection, song identification, to film reels editing for movie post-production.

Related technologies: copy detection, known and unknown advertisement detection 

Teams

Releases

Recent news

  • The Joy of Reading, by De Marque
    18/04/2018

    Before the web existed, we worked a lot in schools and were motivated to offer content in digital form, specifically francophone and Quebecois content, because what existed at the time was mainly in English...

    +

Upcoming event

  • R-D Seminar - Towards coherent, fluent and context-appropriate Natural Language Generation systems
    24 April 2018 11:00
    CRIM (405, avenue Ogilvy, bureau 101, Montréal)
    A presentation by Jad Kabbara, scholarship student within the Speech and Text team at CRIM, and Ph.D. candidate at the School of Computer Science at McGill University.
    +

Recent Publications

  • Towards Automatic Feature Extraction for Activity Recognition from Wearable Sensors: A Deep Learning Approach

    +
  • État des lieux des technologies web

    +