Speaker: Cristóbal Pagán Cánovas (MULTIDATA project coordinator).
Date: May, 19th, 4pm (CET).
In this presentation, we will briefly outline what the project plans to offer, not just the pipeline but also tutorials, manuals, explanatory videos, didactic materials for the use of multimodal data across disciplines, a forum for users, alongside webinars and events on tools for analyzing video datasets, methods for research into multimodal communication, and ideas on how to use video data in the classroom.
The second part of the presentation will demonstrate our pipeline, which includes automatic speech transcription and alignment, acoustic speech analysis, and body keypoint detection for gesture trajectory reconstruction and pose estimation. We will showcase practical examples to illustrate the type of data users can extract from their uploaded videos. No technical expertise is required.
A live chat and oral Q&A session will be available for questions.
Please RSVP: https://introduction-to-MULTIDATA.eventbrite.com
Zoom link: https://umurcia.zoom.us/j/91245535584
Meeting ID: 912 4553 5584
