DLC-Bench

# Describe Anything: Detailed Localized Image and Video Captioning

**NVIDIA, UC Berkeley, UCSF**

[Long Lian](https://tonylian.com), [Yifan Ding](https://research.nvidia.com/person/yifan-ding), [Yunhao Ge](https://gyhandy.github.io/), [Sifei Liu](https://sifeiliu.net/), [Hanzi Mao](https://hanzimao.me/), [Boyi Li](https://sites.google.com/site/boyilics/home), [Marco Pavone](https://research.nvidia.com/person/marco-pavone), [Ming-Yu Liu](https://mingyuliu.net/), [Trevor Darrell](https://people.eecs.berkeley.edu/~trevor/), [Adam Yala](https://www.adamyala.org/), [Yin Cui](https://ycui.me/)

[[Paper](https://arxiv.org/abs/2504.16072)] | [[Code](https://github.com/NVlabs/describe-anything)] | [[Project Page](https://describe-anything.github.io/)] | [[Video](https://describe-anything.github.io/#video)] | [[HuggingFace Demo](https://huggingface.co/spaces/nvidia/describe-anything-model-demo)] | [[Model/Benchmark/Datasets](https://huggingface.co/collections/nvidia/describe-anything-680825bb8f5e41ff0785834c)] | [[Citation](#citation)]

# Dataset Card for DLC-Bench

Dataset for detailed localized captioning benchmark (DLC-Bench).

## LICENSE
[CC BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/deed.en)

## Intended Usage
This dataset is intended to demonstrate and facilitate the understanding and usage of detailed localized captioning models. It should primarily be used for research purposes.

## Ethical Considerations
NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.

Please report security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/).

# Describe Anything：精细化定位式图像与视频字幕生成
**NVIDIA、加州大学伯克利分校、加州大学旧金山分校**

[Long Lian](https://tonylian.com), [Yifan Ding](https://research.nvidia.com/person/yifan-ding), [Yunhao Ge](https://gyhandy.github.io/), [Sifei Liu](https://sifeiliu.net/), [Hanzi Mao](https://hanzimao.me/), [Boyi Li](https://sites.google.com/site/boyilics/home), [Marco Pavone](https://research.nvidia.com/person/marco-pavone), [Ming-Yu Liu](https://mingyuliu.net/), [Trevor Darrell](https://people.eecs.berkeley.edu/~trevor/), [Adam Yala](https://www.adamyala.org/), [Yin Cui](https://ycui.me/)

[[论文](https://arxiv.org/abs/2504.16072)] | [[代码](https://github.com/NVlabs/describe-anything)] | [[项目主页](https://describe-anything.github.io/)] | [[演示视频](https://describe-anything.github.io/#video)] | [[HuggingFace 演示空间](https://huggingface.co/spaces/nvidia/describe-anything-model-demo)] | [[模型/基准测试集/数据集](https://huggingface.co/collections/nvidia/describe-anything-680825bb8f5e41ff0785834c)] | [[引用](#citation)]

# DLC-Bench 数据集卡片
面向精细化定位式字幕生成基准测试的数据集（DLC-Bench）。

## 许可证
[CC BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/deed.en)

## 预期用途
本数据集旨在展示并促进对精细化定位式字幕生成模型的理解与应用，主要用于科研研究场景。

## 伦理考量
NVIDIA坚信可信人工智能是一项共同责任，我们已建立相应政策与实践规范，以支持各类人工智能应用的开发。开发者在依照服务条款下载或使用本模型时，应与其内部模型团队开展协作，确保该模型符合相关行业与应用场景的要求，并应对可能出现的产品误用问题。

请通过[此链接](https://www.nvidia.com/en-us/support/submit-security-vulnerability/)提交安全漏洞报告或NVIDIA人工智能相关问题。