CLAMS Project¶
Computational Linguistics Applications for Multimedia Services
The CLAMS project, funded by the Andrew W. Mellon Foundation, is an open-source Artificial Intelligence (AI) and machine learning (ML) platform for cultural heritage institutions. It provides a framework for developing and implementing ML-based tools to analyze multimedia content, such as video, audio, and text. By automating content analysis and information extraction, CLAMS provides archivists with an AI-assisted environment for metadata refinement, which in turn improves access, search, and exploration of archival audiovisual material.
CLAMS tools aim to generate metadata and knowledge from A/V material that may be hidden or invisible to archivists and database indexes. CLAMS is also designed to be used by computer scientists and developers of content analysis tools within an interoperable platform for custom workflows and pipelines.
The project is under active development. Contact us for any concerns or suggestions at admin@clams.ai.
Primary Components¶
An interchange format for multimodal annotations (text, audio, image/video)
Software Development Kits for building CLAMS applications
Information about the CLAMS workflow engine.
A public registry of free and open-source CLAMS apps.
Citing CLAMS¶
Information on how to cite the CLAMS project in your research.
Publications¶
If you use CLAMS in your research, please cite the following publications:
CLAMS: A Python Library for Multimodal Annotation and Processing (Conference paper, doi:10.1007/978-3-031-93160-4_12)
CLAMS: A Multimodal Annotation and Processing Framework for CLARIAH Media Resources (Original framework paper, doi:10.18653/v1/W19-2512)