The WEAVE Toolkit accompanies and supports the activities of cultural communities content aggregation and access. It consists of several open and reusable tools and technologies employing a mix of AI techniques, machine learning, natural language processing, big data analysis and innovative interface engineering. The tools allow professionals to more effectively store, manage and access 3D assets that have been digitised, and to annotate videos more efficiently. Additionally users can curate easily virtual galleries and virtual exhibitions that can contain a diverse mix of content (including 3D), and can in this way showcase the connection between tangible and intangible heritage. The curated galleries and virtual exhibitions can be accessed by end-users on different devices in more immersive and interactive ways.
WEAVE 3D Asset manager is a tool for handling high-quality 3D assets. It allows for storing large 3D models of up to 10GB in size. It supports 9 3D file formats like .gltf, .fbx, .obj… Behind the scenes it processes these models into a standard format that can be loaded and shown in viewers efficiently. This consists of different model resolutions and details.
The viewer works in web browsers using the WebGL API. It uses different model details and resolutions from the 3D asset manager for better user experience. The published 3D models in the WEAVE 3D Asset manager can be embedded into other web pages using the viewer.
The proposed tool is a web-based real-time multimodal video annotator based on keyboard, touch and voice inputs designed to assist the creative and exploratory processes. This tool supports the capture of multimodal annotations while, and after, recording video. The annotation types available to be used can be text, ink strokes, audio, or user-configured marks.
- A 3D model importer feature was developed and integrated.
- A 3D model Viewer was also created for MotionNotes.
- Finally, the 3D annotation feature will also be available.
WEAVExperience (WEAVEx) is a web-based tool for managing the content of different types (including 3D) and allowing the user to create holistic documentation of the cultural communities’ heritage through digital community spaces and curating digital stories and experiences.
The content that the users can work with is both coming from Europeana (which they can collect using the CultureMoves browser extension), or from their own collection (which they can upload via the tool).
Effectively WEAVEx is opening up existing collections and making them available in new ways (e.g. accessible via mobile devices, new forms of visualisation, ability to creatively link different content, etc).
Metadata enrichment tools
Three main metadata enrichment tools are made available to be used before the process of aggregating content to Europeana. These tools are:
- NERD Annotator
- Perform Named Entity Recognition and Disambiguation (NERD)
- Better performance on longer texts with rich context
- Plug-n-play solution, no fine-tuning needed
- Context-based Topic Analysis Tool
- Utilizing state-of-the-art BERT-based deep learning models (for word and sentence embeddings/representations)
- Cultural Heritage domain pre-training, improving topic coherence and context analysis
- Linked-Data Annotator
- Link text to Thesaurus/Vocabulary terms
- Smart String Matchings utilizing state-of-the-art NLP technologies
- Improved time performance
- Use existing thesaurus/vocabulary or create custom from a list of keywords and the respective URIs