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

  • 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

    +