Objectives, Expectations, & Outcomes

At the end of the workshop, it is expected that participants:

  • Know the state-of-the-art ideas, designs and implementations of CrossMMLA systems
  • Capture, analyze and report multimodal data capture on-the-spot
  • Participate in a research agenda for the future of CrossMMLA

During the workshop:

  1. The morning will open with very short “lightning talks” introducing the CrossMMLA projects that each team will undertake, using the different submissions as building blocks for their MMLA process.
  2. In the morning, participants will work in table-teams formed by an initial “team seed” (participants with submissions used as building blocks of the CrossMMLA project), plus additional participants without a submission, added dynamically to the teams in a “demothon” style. The teams will setup the data gathering technology, perform examples of the learning activities, and gathering of data from them
  3. In the afternoon, teams process the data recorded in the morning, using their selected data analysis/annotation methods (or exploring new ones) to answer their driving research questions
  4. To wrap-up the workshop, each team will present their progress in the CrossMMLA project, and a round table will outline the challenges detected or made apparent during the workshop activities, and will define joint      post-workshop actions interesting for the community (within the framework of the SIG): joint experiments to further develop the mini-projects of the workshop, joint open datasets to be created, joint papers or special issues, funding project proposals, etc.

Aside from the (intangible, but very important) learning of participants about CrossMMLA, and the strengthening of the SoLAR Special Interest Group (SIG) on CrossMMLA, the workshop will have two tangible outcomes:

  1. Based on the contributions of the participants (see workshop format above) we aim to provide a catalogue of shared community knowledge (to be made available through the SIG/workshop website), about the 1-4 contributions above.
  2. Based on the learning activities tested in the workshop, and the rest of the hands-on activities, an open “CrossMMLA dataset” will be made available to the community (through the SIG/Workshop website or other European open science repositories)