BOLD5000, A public fMRI dataset of 5000 images

17 sec read

Official website and download
Full text paper link

Good news for brain imaging researchers. There is a new dataset available for you to play with.

BOLD5000 is a large-scale, slow event-related fMRI dataset collected on 4 subjects, each observing 5,254 images over 15 scanning sessions. The images are selected from three computer vision datasets.

  1. 1,000 images from Scene Images (with scene categories based on SUN categories)
  2. 2,000 images from the COCO dataset
  3. 1,916 images from the ImageNet dataset
BOLD5000 image data
BOLD5000 image data



写作助手,把中式英语变成专业英文


AI writing papers with real references


Want to receive new post notification? 有新文章通知我

第七十三期fNIRS Journal Club通知2026/7/11, 10am 赵庆柏教授

创造性思维是人类高级认知的重要体现,也是教育、创新与团队协作等领域关注的核心问题。近年来,功能性近红外光谱(fNIRS)凭借其良好的生态效度和多人同步测量优势,为创造性思维及其社会互动神经机制的研究提
Wanling Zhu
13 sec read

第七十二期fNIRS Journal Club视频 曹家铭博士

Youtube: https://youtu.be/9mY_m7C8Z8s 优酷:https://v.youku.com/v_show/id_XNjU0MTE5NjMwNA==.html 随着近年来深
Wanling Zhu
16 sec read

第七十二期fNIRS Journal Club通知2026/6/6, 10am 曹家铭博士

随着近年来深度学习在DOT/fNIRS重建中的应用,研究者往往需要大规模地生成仿真数据,高性能的仿真和处理软件则显得尤为重要。来自澳门大学的曹家铭教授将介绍一款针对DOT的高性能光子仿真Python包
Wanling Zhu
10 sec read

Leave a Reply

Your email address will not be published. Required fields are marked *