Indexing images or videos from their content

In light of the explosion of images and videos that are produced, archived and exchanged on the Internet and in private networks, the manual annotation of their content has become an impossible task. To overcome this hurdle, we contribute to developing technologies that allow for indexing and searching images and videos according to the visual elements they contain. For example, the underlying faces, textual content and places can be recognized by our software. Coherent storage and retrieval of information is achieved through the use of standard, yet evolved metadata formats such as MPEG-7 and RDF.

Related technologies: Test bed for the audio-visual MPEG-7 indexing of documentary films, test bed for indexing and searching filming locations, manual annotation software for generating the visual objects ground-truth in videos, same location image matching engine.

Teams

Releases

Recent news

  • Découvrez le CRIM
    13/02/2020

    Acteur clé en TI au Québec ; un lien entre les mondes universitaire et industriel, qui développe, adapte et rend accessibles les technologies et les connaissances, pour répondre aux besoins des organisations.

    +

Upcoming event

  • Seminar R&D : Automated speech-to-text transcription of Indigenous Languages
    28 February 2020 11:00
    CRIM (405, avenue Ogilvy, bureau 101, Montréal)
    A conference of Gilles Boulianne and Vishwa Gupta, Senior Researchers in Automatic Speech Processing, CRIM.
    +

Recent Publications

  • Validating BGP Update Using Blockchain-Based Infrastructure

    +
  • Efficient Inference of Optimal Decision Trees

    +