FuseCap: Leveraging Large Language Models for Enriched Fused Image Captions
A framework designed to generate semantically rich image captions.
Resources
π» Project Page: For more details, visit the official project page.
π Read the Paper: You can find the paper here.
π Demo: Try out our BLIP-based model demo trained using FuseCap.
π Code Repository: The code for FuseCap can be found in the GitHub repository.
ποΈ Datasets: The fused captions datasets can be accessed from here.
Running the model
Our BLIP-based model can be run using the following code,
import requests
from PIL import Image
from transformers import BlipProcessor, BlipForConditionalGeneration
import torch
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
processor = BlipProcessor.from_pretrained("noamrot/FuseCap")
model = BlipForConditionalGeneration.from_pretrained("noamrot/FuseCap").to(device)
img_url = 'https://huggingface.co./spaces/noamrot/FuseCap/resolve/main/bike.jpg'
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')
text = "a picture of "
inputs = processor(raw_image, text, return_tensors="pt").to(device)
out = model.generate(**inputs, num_beams = 3)
print(processor.decode(out[0], skip_special_tokens=True))
Upcoming Updates
The official codebase, datasets and trained models for this project will be released soon.
BibTeX
@inproceedings{rotstein2024fusecap,
title={Fusecap: Leveraging large language models for enriched fused image captions},
author={Rotstein, Noam and Bensa{\"\i}d, David and Brody, Shaked and Ganz, Roy and Kimmel, Ron},
booktitle={Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},
pages={5689--5700},
year={2024}
}
- Downloads last month
- 2,866