Moving MNIST
2D Box Tracking
MNIST
|...
许可协议: Unknown

Overview

Unsupervised Learning of Video Representations using LSTMs

Long-term Future Prediction imgimgimgimgimgimgimgimgimgimg

A test set for evaluating sequence prediction/reconstruction

Moving MNIST [782Mb] contains 10,000 sequences each of length 20 showing 2 digits moving in a 64 x 64 frame.

The results in the updated arxiv paper use this test set to report numbers. For future prediction, the metric is cross entropy loss for predicting the last 10 frames for each sequence conditioned on the first 10 frames.

Citation

Please use the following citation when referencing the dataset:

@inproceedings{srivastava2015unsupervised,
  title={Unsupervised learning of video representations using lstms},
  author={Srivastava, Nitish and Mansimov, Elman and Salakhudinov, Ruslan},
  booktitle={International conference on machine learning},
  pages={843--852},
  year={2015}
}
数据概要
数据格式
Image,
数据量
10K
文件大小
781.25MB
发布方
University of Toronto
The University of Toronto is a public research university in Toronto, Ontario, Canada, situated on the grounds that surround Queen's Park. Academically, the University of Toronto is noted for influential movements and curricula in literary criticism and communication theory, known collectively as the Toronto School.
数据集反馈
| 121 | 数据量 10K | 大小 781.25MB
Moving MNIST
2D Box Tracking
MNIST
许可协议: Unknown

Overview

Unsupervised Learning of Video Representations using LSTMs

Long-term Future Prediction imgimgimgimgimgimgimgimgimgimg

A test set for evaluating sequence prediction/reconstruction

Moving MNIST [782Mb] contains 10,000 sequences each of length 20 showing 2 digits moving in a 64 x 64 frame.

The results in the updated arxiv paper use this test set to report numbers. For future prediction, the metric is cross entropy loss for predicting the last 10 frames for each sequence conditioned on the first 10 frames.

Citation

Please use the following citation when referencing the dataset:

@inproceedings{srivastava2015unsupervised,
  title={Unsupervised learning of video representations using lstms},
  author={Srivastava, Nitish and Mansimov, Elman and Salakhudinov, Ruslan},
  booktitle={International conference on machine learning},
  pages={843--852},
  year={2015}
}
数据集反馈
0
立即开始构建AI
graviti
wechat-QR
长按保存识别二维码,关注Graviti公众号