The Three Obstructions: Improvements in Analysis & Interface for Multimodal Retrieval
Co-sponsored by the Berkeley Institute for Data Science and the School of Information
This talk considers three necessary improvements to existing models and workflows for analysis of film and television, taking as an example Lars von Trier’s 1994 supernatural mystery The Kingdom. Modern multimodal models offer compelling affordances for analyzing linguistic, sonic, and visual aspects of narrative cinema and television. The promise of measuring abstract concepts such as “horror” or “comfort” across these modalities is compelling, but we face three specific obstructions that hinder this work: scalable interface, semantic scene unification, and multilingual capabilities.
Speaker
Peter Leonard
Peter Leonard is an academic librarian with fifteen years’ experience in research universities, including Columbia, Yale, and Stanford. He founded the Yale Digital Humanities Lab, where he also taught in the Department of Statistics and Data Science. He received his Ph.D. in Scandinavian literature from the University of Washington, and was awarded a Fulbright Fellowship to Uppsala University in support of his doctoral research on Swedish fiction. His postdoctoral work on text-mining Nordic literature was funded by Google. He currently serves on the scientific advisory board for Sweden’s national digital humanities infrastructure.
Contact
If you have questions about this event, please contact Lilli Wessling Hart at lilli@berkeley.edu.
Accessibility
If you require an accommodation for effective communication (ASL interpreting, CART captioning, alternative media formats, etc.) or information about mobility access in order to fully participate in this event, please contact Lilli Wessling Hart at lilli@berkeley.edu with as much advance notice as possible and at least 7–10 days in advance of the event.