中科院计算所视觉信息处理与学习组

您所在的位置 / 资源

资源

数据库

  • 1. CAS-PEAL-R1 Face Dataset

    This dataset contains images of 1,040 subjects, with variations in Pose, Expression, Accessories, and Lighting (that's why it is called PEAL). Especially, for each subjects, images under 21 poses are collected. It is publicly available for research purpose only. See the link for more details and how to request it.

  • 2. ACT4^2 Dataset

    The ACT42 dataset provides synchronized data of human daily action, aiming to facilitate the research of action analysis across multiple views and multiple sources. There are 14 classes of representative daily actions recorded through both ordinary RGB and Depth channels simultaneously.?The daily actions considered in this dataset are: Collapse, Drink, MakePhonecall, MopFloor, PickUp, PutOn, ReadBook, SitDown, SitUp, Stumble, TakeOff, ThrowAway, TwistOpen and WipeClean.

  • 3. COX Face Dataset

    COX Face Dataset is designed for the problem of Video-to-Still (V2S), Still-to-Video (S2V) and Video-to-Video (V2V) face recognition. The dataset contains 1,000 subjects, with each subject 1 high quality still image and 3 video sequences captured simulating video surveillance scenario. Specifically, in this dataset, the still images are collected under controlled environment, thus of high quality and resolution, in frontal view, with normal lighting and neutral expression. On the contrary, the video frames are of low resolution and low quality, with blur, and captured under poor lighting, in non-frontal view.

视觉信息处理和学习组
  • 单位地址:北京海淀区中关村科学院南路6号
  • 邮编:100190
  • 联系电话:010-62600514
  • Email:yi.cheng@vipl.ict.ac.cn
  • Valse公众号

  • 深度学习大讲堂

版权所有 @ 中科院计算所视觉信息处理与学习组 京ICP备05002829号 京公网安备1101080060