wenzhengzeng

/

D2VLM-Models

like 0

This PR improves the model card by adding relevant metadata and links to the official research paper and code repository.

Specifically, it adds:

• pipeline_tag: video-text-to-text for better categorization.
• library_name: transformers to enable automated code snippets.
• Links to the paper Factorized Learning for Temporally Grounded Video-Language Models and the GitHub repository.
• A BibTeX citation for the research paper.