Publications & Presentations
CLAMS Platform
Core developer and coauthor on publications for CLAMS (Computational Linguistics Applications for Multimedia Services).
2025
2025
Multimodal Interoperability with the CLAMS Platform
MultiMedia Modeling (MMM) 2025 — Demo
2022
The CLAMS Platform at Work: Processing Audiovisual Data from the American Archive of Public Broadcasting
LREC 2022
2020
2019
2019
Indexing the American Archive of Public Broadcasting
Fantastic Futures 2019, Stanford University — Workshop
2019
Automated Creation of Descriptive Metadata for Large Media Archives
Joint Technical Symposium (JTS) 2019, Amsterdam — Presentation
Slates-500 Dataset
Multimodal dataset and evaluation pipeline for complex information extraction from archival video slates.
Slates-500: A Multimodal Dataset for Information Extraction from Archival Video
Under review
Hawaii Chyron Dataset
Dataset for extracting Hawaiian language text from archival broadcast video using OCR and VLMs.
Understanding On-Screen Text: Do AI Tools Struggle with Hawaiian Chyrons?
IASA Journal — In review
2025
Hawaii Chyron Dataset & Archival AI
IASA Conference, Honolulu — Presentation
2025