10000 GitHub - zhengyang5/E-VQA
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

zhengyang5/E-VQA

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

14 Commits
 
 

Repository files navigation

Event-oriented Visual Question Answering: The E-VQA Dataset and Benchmark

This is to introduce a collection of event-oriented visual question answering (E-VQA) dataset, including free-form questions and answers on high-level real-event concepts, which provides contextual information on events as time-sensitive domain knowledge and images. E-VQA consists of 2,690 social media images, 9,008 questions, 5,479 answers, and 1,157 news media articles for references being annotated to 182 real-world events, covering a wide range of topics, such as armed conflicts and attacks, disasters and accidents, law and crime, politics and elections, sports and entertainment, etc.

The codes can be shared to download the news articles and social media posts upon request for non-commercial use.

For any question regarding the dataset, please contact Dr. Zhenguo Yang (zhengyang5-c@my.cityu.edu.hk). Specifically, the researchers interested in the dataset should download and fill up the Dataset Agreement Form and send it back to us. In case any problems about links for downloading the data, please contact me by email.

The dataset can be downloaded via the links.

https://drive.google.com/drive/folders/1TS3Rto1aOqaB02og4qLC4KdnI4bE9GZ1?usp=sharing

通过网盘分享的文件:MMED-410-原始数据 链接: https://pan.baidu.com/s/1RS-iQ_XzEDpv0hhpe5qxZw?pwd=5dfr 提取码: 5dfr

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published
0