{"url":"/sota/video-prediction-on-moving-mnist","task":{"name":"Video Prediction","url":"/task/video-prediction","note":null},"dataset":{"name":"Moving MNIST","url":"/dataset/moving-mnist"},"category":"Computer Vision","categories":["Computer Vision","Time Series"],"category_note":null,"description":null,"description_from":null,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["MSE","MAE","SSIM","LPIPS","PSNR"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"MSE":"lower","MAE":"lower","SSIM":"higher","LPIPS":null,"PSNR":"higher"}},"counts":{"rows":31,"rows_with_code":31,"rows_with_paper_page":31,"rows_dated":31,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"PredFormer","metrics":{"MAE":"41.96","MSE":"11.62","PSNR":"39.89","SSIM":"0.9742"},"uses_additional_data":false,"paper_date":"2024-10-07","paper":"/paper/predformer-transformers-are-effective-spatial","paper_url":"https://arxiv.org/abs/2410.04733v3","paper_title":"Video Prediction Transformers without Recurrence or Convolution","code":"https://github.com/yyyujintang/predformer","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"SimVP+gSTA-Sx10","metrics":{"MAE":"49.8","MSE":"15.05","SSIM":"0.967"},"uses_additional_data":false,"paper_date":"2022-11-22","paper":"/paper/simvp-towards-simple-yet-powerful","paper_url":"https://arxiv.org/abs/2211.12509v4","paper_title":"SimVPv2: Towards Simple yet Powerful Spatiotemporal Predictive Learning","code":"https://github.com/chengtan9907/OpenSTL","n_code_links":2,"syntology":null},{"rank_in_archive_order":3,"model":"IAM4VPx5","metrics":{"MAE":"49.2","MSE":"15.3","SSIM":"0.966"},"uses_additional_data":false,"paper_date":"2023-03-14","paper":"/paper/implicit-stacked-autoregressive-model-for-1","paper_url":"https://arxiv.org/abs/2303.07849v1","paper_title":"Implicit Stacked Autoregressive Model for Video Prediction","code":"https://github.com/seominseok0429/Implicit-Stacked-Autoregressive-Model-for-Video-Prediction","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"MogaNet (SimVP 10x)","metrics":{"MAE":"51.84","MSE":"15.67","SSIM":"0.9661"},"uses_additional_data":false,"paper_date":"2022-11-07","paper":"/paper/efficient-multi-order-gated-aggregation","paper_url":"https://arxiv.org/abs/2211.03295v3","paper_title":"MogaNet: Multi-order Gated Aggregation Network","code":"https://github.com/chengtan9907/OpenSTL","n_code_links":7,"syntology":{"n_ran":12,"n_unverified":3,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"VAN (SimVP 10x)","metrics":{"MAE":"53.57","MSE":"16.21","SSIM":"0.9646"},"uses_additional_data":false,"paper_date":"2022-11-07","paper":"/paper/efficient-multi-order-gated-aggregation","paper_url":"https://arxiv.org/abs/2211.03295v3","paper_title":"MogaNet: Multi-order Gated Aggregation Network","code":"https://github.com/chengtan9907/OpenSTL","n_code_links":7,"syntology":{"n_ran":12,"n_unverified":3,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"HorNet (SimVP 10x)","metrics":{"MAE":"55.7","MSE":"17.4","SSIM":"0.9624"},"uses_additional_data":false,"paper_date":"2022-11-07","paper":"/paper/efficient-multi-order-gated-aggregation","paper_url":"https://arxiv.org/abs/2211.03295v3","paper_title":"MogaNet: Multi-order Gated Aggregation Network","code":"https://github.com/chengtan9907/OpenSTL","n_code_links":7,"syntology":{"n_ran":12,"n_unverified":3,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"ConvNeXt (SimVP 10x)","metrics":{"MAE":"55.76","MSE":"17.58","SSIM":"0.9617"},"uses_additional_data":false,"paper_date":"2022-11-07","paper":"/paper/efficient-multi-order-gated-aggregation","paper_url":"https://arxiv.org/abs/2211.03295v3","paper_title":"MogaNet: Multi-order Gated Aggregation Network","code":"https://github.com/chengtan9907/OpenSTL","n_code_links":7,"syntology":{"n_ran":12,"n_unverified":3,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"SwinLSTM","metrics":{"MSE":"17.7","SSIM":"0.962"},"uses_additional_data":false,"paper_date":"2023-01-01","paper":"/paper/swinlstm-improving-spatiotemporal-prediction-1","paper_url":"http://openaccess.thecvf.com//content/ICCV2023/html/Tang_SwinLSTM_Improving_Spatiotemporal_Prediction_Accuracy_using_Swin_Transformer_and_LSTM_ICCV_2023_paper.html","paper_title":"SwinLSTM: Improving Spatiotemporal Prediction Accuracy using Swin Transformer and LSTM","code":"https://github.com/SongTang-x/SwinLSTM","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"Uniformer (SimVP 10x)","metrics":{"MAE":"57.52","MSE":"18.01"},"uses_additional_data":false,"paper_date":"2022-11-07","paper":"/paper/efficient-multi-order-gated-aggregation","paper_url":"https://arxiv.org/abs/2211.03295v3","paper_title":"MogaNet: Multi-order Gated Aggregation Network","code":"https://github.com/chengtan9907/OpenSTL","n_code_links":7,"syntology":{"n_ran":12,"n_unverified":3,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"MLP-Mixer (SimVP 10x)","metrics":{"MAE":"59.86","MSE":"18.85"},"uses_additional_data":false,"paper_date":"2022-11-07","paper":"/paper/efficient-multi-order-gated-aggregation","paper_url":"https://arxiv.org/abs/2211.03295v3","paper_title":"MogaNet: Multi-order Gated Aggregation Network","code":"https://github.com/chengtan9907/OpenSTL","n_code_links":7,"syntology":{"n_ran":12,"n_unverified":3,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"GMG","metrics":{"MAE":"60.7413","MSE":"19.0741","PSNR":"24.4606","SSIM":"0.9586"},"uses_additional_data":false,"paper_date":"2025-03-14","paper":"/paper/gmg-a-video-prediction-method-based-on-global","paper_url":"https://arxiv.org/abs/2503.11297v1","paper_title":"GMG: A Video Prediction Method Based on Global Focus and Motion Guided","code":"https://github.com/duyhlzu/GMG","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"Swin (SimVP 10x)","metrics":{"MAE":"59.84","MSE":"19.11"},"uses_additional_data":false,"paper_date":"2022-11-07","paper":"/paper/efficient-multi-order-gated-aggregation","paper_url":"https://arxiv.org/abs/2211.03295v3","paper_title":"MogaNet: Multi-order Gated Aggregation Network","code":"https://github.com/chengtan9907/OpenSTL","n_code_links":7,"syntology":{"n_ran":12,"n_unverified":3,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":13,"model":"ViT (SimVP 10x)","metrics":{"MAE":"61.65","MSE":"19.74","SSIM":"0.9539"},"uses_additional_data":false,"paper_date":"2022-11-07","paper":"/paper/efficient-multi-order-gated-aggregation","paper_url":"https://arxiv.org/abs/2211.03295v3","paper_title":"MogaNet: Multi-order Gated Aggregation Network","code":"https://github.com/chengtan9907/OpenSTL","n_code_links":7,"syntology":{"n_ran":12,"n_unverified":3,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"TAU","metrics":{"MAE":"60.3","MSE":"19.8","SSIM":"0.957"},"uses_additional_data":false,"paper_date":"2022-06-24","paper":"/paper/temporal-attention-unit-towards-efficient","paper_url":"https://arxiv.org/abs/2206.12126v3","paper_title":"Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning","code":"https://github.com/chengtan9907/simvpv2","n_code_links":2,"syntology":null},{"rank_in_archive_order":15,"model":"Poolformer (SimVP 10x)","metrics":{"MAE":"64.31","MSE":"20.96"},"uses_additional_data":false,"paper_date":"2022-11-07","paper":"/paper/efficient-multi-order-gated-aggregation","paper_url":"https://arxiv.org/abs/2211.03295v3","paper_title":"MogaNet: Multi-order Gated Aggregation Network","code":"https://github.com/chengtan9907/OpenSTL","n_code_links":7,"syntology":{"n_ran":12,"n_unverified":3,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":16,"model":"ConvMixer (SimVP 10x)","metrics":{"MAE":"67.37","MSE":"22.3"},"uses_additional_data":false,"paper_date":"2022-11-07","paper":"/paper/efficient-multi-order-gated-aggregation","paper_url":"https://arxiv.org/abs/2211.03295v3","paper_title":"MogaNet: Multi-order Gated Aggregation Network","code":"https://github.com/chengtan9907/OpenSTL","n_code_links":7,"syntology":{"n_ran":12,"n_unverified":3,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":17,"model":"CrevNet+ST-LSTM","metrics":{"MSE":"22.3","SSIM":"0.949"},"uses_additional_data":false,"paper_date":"2020-05-01","paper":"/paper/efficient-and-information-preserving-future","paper_url":"https://openreview.net/forum?id=B1eY_pVYvB","paper_title":"Efficient and Information-Preserving Future Frame Prediction and Beyond","code":"https://github.com/rrxi/CrevNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"SimVP","metrics":{"MSE":"23.8","SSIM":"0.948"},"uses_additional_data":false,"paper_date":"2022-06-09","paper":"/paper/simvp-simpler-yet-better-video-prediction-1","paper_url":"https://arxiv.org/abs/2206.05099v1","paper_title":"SimVP: Simpler yet Better Video Prediction","code":"https://github.com/chengtan9907/simvpv2","n_code_links":3,"syntology":{"n_ran":6,"n_unverified":3,"n_samples":9,"n_pointer_only_licence":9}},{"rank_in_archive_order":19,"model":"PhyDNet","metrics":{"MAE":"70.3","MSE":"24.4","SSIM":"0.947"},"uses_additional_data":false,"paper_date":"2020-03-03","paper":"/paper/disentangling-physical-dynamics-from-unknown","paper_url":"https://arxiv.org/abs/2003.01460v2","paper_title":"Disentangling Physical Dynamics from Unknown Factors for Unsupervised Video Prediction","code":"https://github.com/chengtan9907/simvpv2","n_code_links":3,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":20,"model":"MAU","metrics":{"MSE":"27.6","SSIM":"0.937"},"uses_additional_data":false,"paper_date":"2021-12-01","paper":"/paper/mau-a-motion-aware-unit-for-video-prediction","paper_url":"http://proceedings.neurips.cc/paper/2021/hash/e25cfa90f04351958216f97e3efdabe9-Abstract.html","paper_title":"MAU: A Motion-Aware Unit for Video Prediction and Beyond","code":"https://github.com/ZhengChang467/MAU","n_code_links":1,"syntology":null},{"rank_in_archive_order":21,"model":"MSPred","metrics":{"LPIPS":"0.024","MSE":"34.44","PSNR":"26.82","SSIM":"0.975"},"uses_additional_data":false,"paper_date":"2022-03-17","paper":"/paper/video-prediction-at-multiple-scales-with","paper_url":"https://arxiv.org/abs/2203.09303v4","paper_title":"MSPred: Video Prediction at Multiple Spatio-Temporal Scales with Hierarchical Recurrent Networks","code":"https://github.com/AIS-Bonn/MSPred","n_code_links":1,"syntology":null},{"rank_in_archive_order":22,"model":"CrevNet+ConvLSTM","metrics":{"MSE":"38.5","SSIM":"0.928"},"uses_additional_data":false,"paper_date":"2020-05-01","paper":"/paper/efficient-and-information-preserving-future","paper_url":"https://openreview.net/forum?id=B1eY_pVYvB","paper_title":"Efficient and Information-Preserving Future Frame Prediction and Beyond","code":"https://github.com/rrxi/CrevNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":23,"model":"E3D-LSTM","metrics":{"MAE":"86.4","MSE":"41.3","SSIM":"0.910"},"uses_additional_data":false,"paper_date":"2019-05-01","paper":"/paper/eidetic-3d-lstm-a-model-for-video-prediction","paper_url":"https://openreview.net/forum?id=B1lKS2AqtX","paper_title":"Eidetic 3D LSTM: A Model for Video Prediction and Beyond","code":"https://github.com/chengtan9907/simvpv2","n_code_links":3,"syntology":null},{"rank_in_archive_order":24,"model":"LMC","metrics":{"LPIPS":"0.047","MSE":"41.5","SSIM":"0.924"},"uses_additional_data":false,"paper_date":"2021-04-02","paper":"/paper/video-prediction-recalling-long-term-motion","paper_url":"https://arxiv.org/abs/2104.00924v1","paper_title":"Video Prediction Recalling Long-term Motion Context via Memory Alignment Learning","code":"https://github.com/sangmin-git/LMC-Memory","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":25,"model":"SA-ConvLSTM","metrics":{"MAE":"94.7","MSE":"43.9","SSIM":"0.913"},"uses_additional_data":false,"paper_date":"2020-04-03","paper":"/paper/self-attention-convlstm-for-spatiotemporal","paper_url":"https://ojs.aaai.org//index.php/AAAI/article/view/6819","paper_title":"Self-Attention ConvLSTM for Spatiotemporal Prediction","code":"https://github.com/tsugumi-sys/SAM-ConvLSTM-Pytorch","n_code_links":2,"syntology":null},{"rank_in_archive_order":26,"model":"MIM*","metrics":{"MAE":"101.1","MSE":"44.2","SSIM":"0.910"},"uses_additional_data":false,"paper_date":"2018-11-19","paper":"/paper/memory-in-memory-a-predictive-neural-network","paper_url":"http://arxiv.org/abs/1811.07490v3","paper_title":"Memory In Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity from Spatiotemporal Dynamics","code":"https://github.com/chengtan9907/simvpv2","n_code_links":4,"syntology":null},{"rank_in_archive_order":27,"model":"Causal LSTM","metrics":{"MAE":"106.8","MSE":"46.5","SSIM":"0.898"},"uses_additional_data":false,"paper_date":"2018-04-17","paper":"/paper/predrnn-towards-a-resolution-of-the-deep-in","paper_url":"http://arxiv.org/abs/1804.06300v2","paper_title":"PredRNN++: Towards A Resolution of the Deep-in-Time Dilemma in Spatiotemporal Predictive Learning","code":"https://github.com/thuml/predrnn-pytorch","n_code_links":11,"syntology":{"n_ran":0,"n_unverified":7,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":28,"model":"PredRNN-V2","metrics":{"LPIPS":"0.071","MSE":"48.4","SSIM":"0.891"},"uses_additional_data":false,"paper_date":"2021-03-17","paper":"/paper/predrnn-a-recurrent-neural-network-for","paper_url":"https://arxiv.org/abs/2103.09504v4","paper_title":"PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning","code":"https://github.com/chengtan9907/simvpv2","n_code_links":3,"syntology":null},{"rank_in_archive_order":29,"model":"MIM","metrics":{"MAE":"116.5","MSE":"52.0","SSIM":"0.874"},"uses_additional_data":false,"paper_date":"2018-11-19","paper":"/paper/memory-in-memory-a-predictive-neural-network","paper_url":"http://arxiv.org/abs/1811.07490v3","paper_title":"Memory In Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity from Spatiotemporal Dynamics","code":"https://github.com/chengtan9907/simvpv2","n_code_links":4,"syntology":null},{"rank_in_archive_order":30,"model":"PredRNN","metrics":{"MAE":"126.1","MSE":"56.8","SSIM":"0.867"},"uses_additional_data":false,"paper_date":"2017-12-01","paper":"/paper/predrnn-recurrent-neural-networks-for-1","paper_url":"https://papers.nips.cc/paper/6689-predrnn-recurrent-neural-networks-for-predictive-learning-using-spatiotemporal-lstms","paper_title":"PredRNN: Recurrent Neural Networks for Predictive Learning using Spatiotemporal LSTMs","code":"https://github.com/chengtan9907/simvpv2","n_code_links":2,"syntology":null},{"rank_in_archive_order":31,"model":"ConvLSTM","metrics":{"MAE":"182.9","MSE":"103.3","SSIM":"0.707"},"uses_additional_data":false,"paper_date":"2015-06-13","paper":"/paper/convolutional-lstm-network-a-machine-learning","paper_url":"http://arxiv.org/abs/1506.04214v2","paper_title":"Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting","code":"https://github.com/ndrplz/ConvLSTM_pytorch","n_code_links":23,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":2}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":15,"rows_with_any_sample_ran":12,"distinct_papers_with_graph_line":6,"distinct_papers_with_any_sample_ran":3,"samples_over_distinct_papers":{"n_ran":19,"n_unverified":17,"n_samples":36,"n_pointer_only_licence":12,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":127,"n_unverified":44,"n_samples":171,"n_pointer_only_licence":12,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}