graviti
ProductOpen DatasetsApps MarketSolutionsResourcesCompany
194
0
0
Moving MNIST
General
Discussion
Code
Activities
c77a3268-8cd1-11eb-88ae-0e1f58d5e9a9
e1ec964·
Jun 20, 2021 2:29 PM
·1Commits

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}
}
🎉Many thanks to Graviti Open Datasets for contributing the dataset
Basic Information
Application ScenariosNot Available
AnnotationsNot Available
TasksNot Available
LicenseUnknown
Updated on2021-01-20 04:40:11
Metadata
Data TypeNot Available
Data Volume10K
Annotation Amount0
File Size0B
Copyright Owner
University of Toronto
Annotator
Unknown
More Support Options