</> Code with Papers by Syntology

Datasets › Moving MNIST

Moving MNIST

Introduced by Nitish Srivastava et al. in Unsupervised Learning of Video Representations using LSTMs1 Jan 2015 archive 2025-07-28

The Moving MNIST dataset contains 10,000 video sequences, each consisting of 20 frames. In each video sequence, two digits move independently around the frame, which has a spatial resolution of 64×64 pixels. The digits frequently intersect with each other and bounce off the edges of the frame

Source: Mutual Suppression Network for Video Prediction using Disentangled Features Image Source: http://www.cs.toronto.edu/~nitish/unsupervised_video/

HomepageBenchmarksPapers JSON

Benchmarks archive 2025-07-28

All 1 leaderboard whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Video Prediction Moving MNIST PredFormer MSE 11.62 Video Prediction Transformers without Recurrence or Convolution yyyujintang/predformer 31 Compare

Papers archive 2025-07-28

20 shown of 20 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 194. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
GMG: A Video Prediction Method Based on Global Focus and Motion Guided 1 1 14 Mar 2025 not harvested
Video Prediction Transformers without Recurrence or Convolution 1 1 7 Oct 2024 not harvested
Implicit Stacked Autoregressive Model for Video Prediction 1 1 14 Mar 2023 not harvested
SwinLSTM: Improving Spatiotemporal Prediction Accuracy using Swin Transformer and LSTM 1 1 1 Jan 2023 not harvested
SimVPv2: Towards Simple yet Powerful Spatiotemporal Predictive Learning 2 1 22 Nov 2022 not harvested
MogaNet: Multi-order Gated Aggregation Network 7 10 7 Nov 2022 ran 12 of 15 samples (3 unverified)
Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning 2 1 24 Jun 2022 not harvested
SimVP: Simpler yet Better Video Prediction 3 1 9 Jun 2022 ran 6 of 9 samples (3 unverified; 9 pointer-only for licence)
MSPred: Video Prediction at Multiple Spatio-Temporal Scales with Hierarchical Recurrent Networks 1 1 17 Mar 2022 not harvested
MAU: A Motion-Aware Unit for Video Prediction and Beyond 1 1 1 Dec 2021 not harvested
Video Prediction Recalling Long-term Motion Context via Memory Alignment Learning 1 1 2 Apr 2021 ran 0 of 1 samples (1 unverified; 1 pointer-only for licence)
PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning 3 1 17 Mar 2021 not harvested
Efficient and Information-Preserving Future Frame Prediction and Beyond 1 2 1 May 2020 not harvested
Self-Attention ConvLSTM for Spatiotemporal Prediction 2 1 3 Apr 2020 not harvested
Disentangling Physical Dynamics from Unknown Factors for Unsupervised Video Prediction 3 1 3 Mar 2020 ran 0 of 1 samples (1 unverified)
Eidetic 3D LSTM: A Model for Video Prediction and Beyond 3 1 1 May 2019 not harvested
Memory In Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity from Spatiotemporal Dynamics 4 2 19 Nov 2018 not harvested
PredRNN++: Towards A Resolution of the Deep-in-Time Dilemma in Spatiotemporal Predictive Learning 11 1 17 Apr 2018 ran 0 of 7 samples (7 unverified)
PredRNN: Recurrent Neural Networks for Predictive Learning using Spatiotemporal LSTMs 2 1 1 Dec 2017 not harvested
Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting 23 1 13 Jun 2015 ran 1 of 3 samples (2 unverified; 2 pointer-only for licence)

Dataset loaders archive 2025-07-28

www.tensorflow.org/datasets/catalog/moving_mnisttensorflow/datasetstfjax

1 loader as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

Video Prediction

License archive 2025-07-28

Unknown

Modalities archive 2025-07-28

ImagesVideos

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • Moving MNIST

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections