https://github.com/google/imageinwords

Data release for the ImageInWords (IIW) paper.
https://github.com/google/imageinwords

dataset dataset-generation detailed-annotations detailed-descriptions evaluation human-annotation i2t image-captioning image-descriptions image-text image-to-text t2i

Last synced: 7 months ago
JSON representation

Data release for the ImageInWords (IIW) paper.

• Host: GitHub
• URL: https://github.com/google/imageinwords
• Owner: google
• Created: 2024-03-06T03:30:17.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2024-11-17T23:21:09.000Z (over 1 year ago)
• Last Synced: 2025-11-23T16:24:53.698Z (7 months ago)
• Topics: dataset, dataset-generation, detailed-annotations, detailed-descriptions, evaluation, human-annotation, i2t, image-captioning, image-descriptions, image-text, image-to-text, t2i
• Language: JavaScript
• Homepage: https://google.github.io/imageinwords/
• Size: 21.4 MB
• Stars: 223
• Watchers: 9
• Forks: 7
• Open Issues: 4
• Metadata Files:
  • Readme: README.md
  • Citation: CITATION.cff

Awesome Lists containing this project

• awesome-multimodal-data-recipe - github.com/google/imageinwords

README

          
ImageInWords: Unlocking Hyper-Detailed Image Descriptions
 


arXiv: https://arxiv.org/abs/2405.02793

Please visit the [webpage](https://google.github.io/imageinwords) for all the information about the IIW project, data, visualizations, and much more. The data can be downloaded directly from the `datasets/` folder, as well as from Huggingface (see below).





Please reach out to iiw-dataset@google.com for thoughts/feedback/questions/collaborations.

License: [CC-BY-4.0](https://creativecommons.org/licenses/by/4.0/)

Other resources


🤗Hugging Face🤗


IIW-Benchmark Eval Dataset


```python

from datasets import load_dataset

# `name` can be one of: IIW-400, DCI_Test, DOCCI_Test, CM_3600, LocNar_Eval

# refer: https://github.com/google/imageinwords/blob/main/datasets/README.md

dataset = load_dataset('google/imageinwords', token=None, name="IIW-400", trust_remote_code=True)

```

Dataset-Explorer


Cite


If you use our data or refer to our work, please include the following citation

```

@misc{garg2024imageinwords,

      title={ImageInWords: Unlocking Hyper-Detailed Image Descriptions}, 

      author={Roopal Garg and Andrea Burns and Burcu Karagol Ayan and Yonatan Bitton and Ceslee Montgomery and Yasumasa Onoe and Andrew Bunner and Ranjay Krishna and Jason Baldridge and Radu Soricut},

      year={2024},

      eprint={2405.02793},

      archivePrefix={arXiv},

      primaryClass={cs.CV}

}

```