EgoThink/EgoThink
收藏Hugging Face2023-12-06 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/EgoThink/EgoThink
下载链接
链接失效反馈官方服务:
资源简介:
---
dataset_info:
- config_name: Activity
features:
- name: image
dtype: image
- name: question
dtype: string
- name: answer
dtype: string
splits:
- name: test
num_bytes: 131502064
num_examples: 100
download_size: 131504614
dataset_size: 131502064
- config_name: Forecasting
features:
- name: image
dtype: image
- name: question
dtype: string
- name: answer
dtype: string
splits:
- name: test
num_bytes: 139301212
num_examples: 100
download_size: 139306138
dataset_size: 139301212
- config_name: Localization_location
features:
- name: image
dtype: image
- name: question
dtype: string
- name: answer
dtype: string
splits:
- name: test
num_bytes: 65819364
num_examples: 50
download_size: 65823441
dataset_size: 65819364
- config_name: Localization_spatial
features:
- name: image
dtype: image
- name: question
dtype: string
- name: answer
dtype: string
splits:
- name: test
num_bytes: 72483368
num_examples: 50
download_size: 72487326
dataset_size: 72483368
- config_name: Object_affordance
features:
- name: image
dtype: image
- name: question
dtype: string
- name: answer
dtype: string
splits:
- name: test
num_bytes: 62217423
num_examples: 50
download_size: 62219658
dataset_size: 62217423
- config_name: Object_attribute
features:
- name: image
dtype: image
- name: question
dtype: string
- name: answer
dtype: string
splits:
- name: test
num_bytes: 62068692
num_examples: 50
download_size: 62071978
dataset_size: 62068692
- config_name: Object_existence
features:
- name: image
dtype: image
- name: question
dtype: string
- name: answer
dtype: string
splits:
- name: test
num_bytes: 70741543
num_examples: 50
download_size: 70745667
dataset_size: 70741543
- config_name: Planning_assistance
features:
- name: image
dtype: image
- name: question
dtype: string
- name: answer
dtype: string
splits:
- name: test
num_bytes: 63263412
num_examples: 50
download_size: 63263987
dataset_size: 63263412
- config_name: Planning_navigation
features:
- name: image
dtype: image
- name: question
dtype: string
- name: answer
dtype: string
splits:
- name: test
num_bytes: 57345130
num_examples: 50
download_size: 57346307
dataset_size: 57345130
- config_name: Reasoning_comparing
features:
- name: image
dtype: image
- name: question
dtype: string
- name: answer
dtype: string
splits:
- name: test
num_bytes: 67879362
num_examples: 50
download_size: 67882224
dataset_size: 67879362
- config_name: Reasoning_counting
features:
- name: image
dtype: image
- name: question
dtype: string
- name: answer
dtype: string
splits:
- name: test
num_bytes: 68442367
num_examples: 50
download_size: 68446064
dataset_size: 68442367
- config_name: Reasoning_situated
features:
- name: image
dtype: image
- name: question
dtype: string
- name: answer
dtype: string
splits:
- name: test
num_bytes: 52522065
num_examples: 50
download_size: 52525750
dataset_size: 52522065
configs:
- config_name: Activity
data_files:
- split: test
path: Activity/test-*
- config_name: Forecasting
data_files:
- split: test
path: Forecasting/test-*
- config_name: Localization_location
data_files:
- split: test
path: Localization_location/test-*
- config_name: Localization_spatial
data_files:
- split: test
path: Localization_spatial/test-*
- config_name: Object_affordance
data_files:
- split: test
path: Object_affordance/test-*
- config_name: Object_attribute
data_files:
- split: test
path: Object_attribute/test-*
- config_name: Object_existence
data_files:
- split: test
path: Object_existence/test-*
- config_name: Planning_assistance
data_files:
- split: test
path: Planning_assistance/test-*
- config_name: Planning_navigation
data_files:
- split: test
path: Planning_navigation/test-*
- config_name: Reasoning_comparing
data_files:
- split: test
path: Reasoning_comparing/test-*
- config_name: Reasoning_counting
data_files:
- split: test
path: Reasoning_counting/test-*
- config_name: Reasoning_situated
data_files:
- split: test
path: Reasoning_situated/test-*
license: apache-2.0
task_categories:
- visual-question-answering
language:
- en
tags:
- First-person
- VLMs
- Egocentric
size_categories:
- n<1K
---
# EgoThink (Can Vision-Language Models Think from a First-Person Perspective?)
[**🌐 Homepage**](https://adacheng.github.io/EgoThink/) | [**🤗 Dataset**](https://huggingface.co/datasets/EgoThink/EgoThink) | [**🤗 Paper**](https://huggingface.co/papers/2311.15596) | [**📖 arXiv**](https://arxiv.org/abs/2311.15596) | [**GitHub**](https://github.com/AdaCheng/EgoThink)
## Contact
- Sijie Cheng: csj23@mails.tsinghua.edu.cn
## Citation
```bibtex
@article{cheng2023can,
title={Can Vision-Language Models Think from a First-Person Perspective?},
author={Cheng, Sijie and Guo, Zhicheng and Wu, Jingwen and Fang, Kechen and Li, Peng and Liu, Huaping and Liu, Yang},
journal={arXiv preprint arXiv:2311.15596},
year={2023}
}
```
dataset_info:
- 配置名称:Activity
特征:
- 名称:image(图像),数据类型:图像
- 名称:question(问题),数据类型:字符串
- 名称:answer(答案),数据类型:字符串
划分集:
- 名称:test(测试集),字节数:131502064,样本数:100
下载大小:131504614 字节
数据集大小:131502064 字节
- 配置名称:Forecasting(预测)
特征:
- 名称:image(图像),数据类型:图像
- 名称:question(问题),数据类型:字符串
- 名称:answer(答案),数据类型:字符串
划分集:
- 名称:test(测试集),字节数:139301212,样本数:100
下载大小:139306138 字节
数据集大小:139301212 字节
- 配置名称:Localization_location(位置定位)
特征:
- 名称:image(图像),数据类型:图像
- 名称:question(问题),数据类型:字符串
- 名称:answer(答案),数据类型:字符串
划分集:
- 名称:test(测试集),字节数:65819364,样本数:50
下载大小:65823441 字节
数据集大小:65819364 字节
- 配置名称:Localization_spatial(空间定位)
特征:
- 名称:image(图像),数据类型:图像
- 名称:question(问题),数据类型:字符串
- 名称:answer(答案),数据类型:字符串
划分集:
- 名称:test(测试集),字节数:72483368,样本数:50
下载大小:72487326 字节
数据集大小:72483368 字节
- 配置名称:Object_affordance(物体可供性,Object affordance)
特征:
- 名称:image(图像),数据类型:图像
- 名称:question(问题),数据类型:字符串
- 名称:answer(答案),数据类型:字符串
划分集:
- 名称:test(测试集),字节数:62217423,样本数:50
下载大小:62219658 字节
数据集大小:62217423 字节
- 配置名称:Object_attribute(对象属性)
特征:
- 名称:image(图像),数据类型:图像
- 名称:question(问题),数据类型:字符串
- 名称:answer(答案),数据类型:字符串
划分集:
- 名称:test(测试集),字节数:62068692,样本数:50
下载大小:62071978 字节
数据集大小:62068692 字节
- 配置名称:Object_existence(对象存在性)
特征:
- 名称:image(图像),数据类型:图像
- 名称:question(问题),数据类型:字符串
- 名称:answer(答案),数据类型:字符串
划分集:
- 名称:test(测试集),字节数:70741543,样本数:50
下载大小:70745667 字节
数据集大小:70741543 字节
- 配置名称:Planning_assistance(规划辅助)
特征:
- 名称:image(图像),数据类型:图像
- 名称:question(问题),数据类型:字符串
- 名称:answer(答案),数据类型:字符串
划分集:
- 名称:test(测试集),字节数:63263412,样本数:50
下载大小:63263987 字节
数据集大小:63263412 字节
- 配置名称:Planning_navigation(规划导航)
特征:
- 名称:image(图像),数据类型:图像
- 名称:question(问题),数据类型:字符串
- 名称:answer(答案),数据类型:字符串
划分集:
- 名称:test(测试集),字节数:57345130,样本数:50
下载大小:57346307 字节
数据集大小:57345130 字节
- 配置名称:Reasoning_comparing(比较推理)
特征:
- 名称:image(图像),数据类型:图像
- 名称:question(问题),数据类型:字符串
- 名称:answer(答案),数据类型:字符串
划分集:
- 名称:test(测试集),字节数:67879362,样本数:50
下载大小:67882224 字节
数据集大小:67879362 字节
- 配置名称:Reasoning_counting(计数推理)
特征:
- 名称:image(图像),数据类型:图像
- 名称:question(问题),数据类型:字符串
- 名称:answer(答案),数据类型:字符串
划分集:
- 名称:test(测试集),字节数:68442367,样本数:50
下载大小:68446064 字节
数据集大小:68442367 字节
- 配置名称:Reasoning_situated(情境推理)
特征:
- 名称:image(图像),数据类型:图像
- 名称:question(问题),数据类型:字符串
- 名称:answer(答案),数据类型:字符串
划分集:
- 名称:test(测试集),字节数:52522065,样本数:50
下载大小:52525750 字节
数据集大小:52522065 字节
configs:
- 配置名称:Activity
数据文件:
- 划分集:test(测试集)
路径:Activity/test-*
- 配置名称:Forecasting
数据文件:
- 划分集:test(测试集)
路径:Forecasting/test-*
- 配置名称:Localization_location
数据文件:
- 划分集:test(测试集)
路径:Localization_location/test-*
- 配置名称:Localization_spatial
数据文件:
- 划分集:test(测试集)
路径:Localization_spatial/test-*
- 配置名称:Object_affordance
数据文件:
- 划分集:test(测试集)
路径:Object_affordance/test-*
- 配置名称:Object_attribute
数据文件:
- 划分集:test(测试集)
路径:Object_attribute/test-*
- 配置名称:Object_existence
数据文件:
- 划分集:test(测试集)
路径:Object_existence/test-*
- 配置名称:Planning_assistance
数据文件:
- 划分集:test(测试集)
路径:Planning_assistance/test-*
- 配置名称:Planning_navigation
数据文件:
- 划分集:test(测试集)
路径:Planning_navigation/test-*
- 配置名称:Reasoning_comparing
数据文件:
- 划分集:test(测试集)
路径:Reasoning_comparing/test-*
- 配置名称:Reasoning_counting
数据文件:
- 划分集:test(测试集)
路径:Reasoning_counting/test-*
- 配置名称:Reasoning_situated
数据文件:
- 划分集:test(测试集)
路径:Reasoning_situated/test-*
许可证:apache-2.0
任务类别:
- 视觉问答(Visual Question Answering, VQA)
语言:
- 英语(en)
标签:
- 第一人称(First-person)
- 视觉语言模型(Vision-Language Models, VLMs)
- 自我中心视角(Egocentric)
样本规模分类:
- n<1K(样本数少于1000)
# EgoThink(视觉语言模型能否以第一人称视角进行思考?)
[**🌐 主页**](https://adacheng.github.io/EgoThink/) | [**🤗 数据集**](https://huggingface.co/datasets/EgoThink/EgoThink) | [**🤗 论文**](https://huggingface.co/papers/2311.15596) | [**📖 arXiv**](https://arxiv.org/abs/2311.15596) | [**GitHub**](https://github.com/AdaCheng/EgoThink)
## 联系方式
- 程思杰:csj23@mails.tsinghua.edu.cn
## 引用
bibtex
@article{cheng2023can,
title={Can Vision-Language Models Think from a First-Person Perspective?},
author={Cheng, Sijie and Guo, Zhicheng and Wu, Jingwen and Fang, Kechen and Li, Peng and Liu, Huaping and Liu, Yang},
journal={arXiv preprint arXiv:2311.15596},
year={2023}
}
提供机构:
EgoThink
原始信息汇总
数据集概述
数据集链接
- Homepage: 数据集主页
- Dataset: Hugging Face 数据集
- Paper: Hugging Face 论文
- arXiv: arXiv 论文预印本
- GitHub: GitHub 代码仓库
搜集汇总
数据集介绍

以上内容由遇见数据集搜集并总结生成



