Hugging Face's logo

fushh7
/
WeDetect

Zero-Shot Object Detection
Model card Files
xet
Community
1

Update model card for ObjEmbed

#1
by nielsr HF Staff - opened
base: refs/heads/main
←
from: refs/pr/1
Discussion Files changed
+53
-10
nielsr

This PR completely overhauls the model card for the ObjEmbed model, as presented in the paper ObjEmbed: Towards Universal Multimodal Object Embeddings.

The previous model card incorrectly referenced "WeDetect" and contained outdated information.

Key updates include:

  • Metadata:
    • Corrected license to apache-2.0 based on the official GitHub repository.
    • Updated pipeline_tag to object-detection to better reflect the model's capabilities in visual grounding and object understanding.
    • Added library_name: transformers as the model uses the transformers library, as evidenced by its installation instructions.
  • Content:
    • Replaced all "WeDetect" content with a summary of ObjEmbed, its key features (Object-Oriented Representation, Versatility, Efficient Encoding) from the paper abstract and GitHub README.
    • Added direct links to the paper and the official GitHub repository.
    • Included sample usage instructions for Referring Expression Comprehension (REC) and Image Retrieval, directly from the GitHub README.
    • Added the correct BibTeX citation.
 Update model card for ObjEmbed30645759
Ready to merge
This branch is ready to get merged automatically.

Sign up or log in to comment