The 'Sound Safari' workshop is designed to offer a hands-on exploration of multimodal models and their applications in cataloging, information retrieval, and Artificial Intelligence. It enables attendees to delve into avant-garde AI-based technologies that convert images into both sound and textual descriptions. Through physical exploration and practical engagement, our goal is to nurture a deep-seated analysis of the consequences of these technologies, the emerging narratives they weave, spotlighting biases and the hurdles posed by non-standard images, and their ramifications for the automated cataloging of archives.
Furthermore, this workshop is dedicated to uncovering the wealth of interdisciplinary collaboration. It invites participants from diverse fields to contribute with their distinct viewpoints, thereby enriching the discourse and widening our collective insight into AI's significance within the realm of archival science.
Structured to be highly interactive, the workshop is divided into three parts: an introductory overview of multimodal models and their practical uses; a fieldwork excursion, wherein participants will walk around the conference environment to capture images, which they will then convert into sound, text and images again via AI models; culminating in a time for sharing and discussing the insights and outcomes derived from these activities.
To ensure participants can fully engage in the workshop, they are kindly asked to bring their laptops.