{"url":"/task/video-prediction","name":"Video Prediction","slug":"video-prediction","description_markdown":null,"categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Time Series","url":"/area/time-series"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":394,"papers_with_code":208,"benchmarks":19,"benchmark_tables_in_archive":19,"benchmark_tables_shown":19,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":25,"subtasks":2,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/video-prediction-on-kth","slug":"video-prediction-on-kth","dataset":"KTH","dataset_url":"/dataset/kth","rows_in_archive":31,"metrics":["FVD","SSIM","PSNR","LPIPS","Cond","Train","Pred","Params (M)","MSE","Diversity"],"first_row_in_archive_order":{"model":"Grid-keypoints","paper_title":"Accurate Grid Keypoint Learning for Efficient Video Prediction","paper_url":"/paper/accurate-grid-keypoint-learning-for-efficient","paper_date":"2021-07-28","arxiv_id":"2107.13170","code_links":[{"title":"xjgaocs/Grid-Keypoint-Learning","url":"https://github.com/xjgaocs/Grid-Keypoint-Learning"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}}},{"leaderboard":"/sota/video-prediction-on-moving-mnist","slug":"video-prediction-on-moving-mnist","dataset":"Moving MNIST","dataset_url":"/dataset/moving-mnist","rows_in_archive":31,"metrics":["MSE","MAE","SSIM","LPIPS","PSNR"],"first_row_in_archive_order":{"model":"PredFormer","paper_title":"Video Prediction Transformers without Recurrence or Convolution","paper_url":"/paper/predformer-transformers-are-effective-spatial","paper_date":"2024-10-07","arxiv_id":"2410.04733","code_links":[{"title":"yyyujintang/predformer","url":"https://github.com/yyyujintang/predformer"}],"syntology":null}},{"leaderboard":"/sota/video-prediction-on-kinetics-600-12-frames","slug":"video-prediction-on-kinetics-600-12-frames","dataset":"Kinetics-600 12 frames, 64x64","dataset_url":"/dataset/kinetics","rows_in_archive":16,"metrics":["FVD","IS","Cond","Pred"],"first_row_in_archive_order":{"model":"SiD2","paper_title":"Simpler Diffusion (SiD2): 1.5 FID on ImageNet512 with pixel-space diffusion","paper_url":"/paper/simpler-diffusion-sid2-1-5-fid-on-imagenet512","paper_date":"2024-10-25","arxiv_id":"2410.19324","code_links":[],"syntology":null}},{"leaderboard":"/sota/video-prediction-on-human36m","slug":"video-prediction-on-human36m","dataset":"Human3.6M","dataset_url":"/dataset/human3-6m","rows_in_archive":9,"metrics":["SSIM","MSE","MAE"],"first_row_in_archive_order":{"model":"IAM4VP","paper_title":"Implicit Stacked Autoregressive Model for Video Prediction","paper_url":"/paper/implicit-stacked-autoregressive-model-for-1","paper_date":"2023-03-14","arxiv_id":"2303.07849","code_links":[{"title":"seominseok0429/Implicit-Stacked-Autoregressive-Model-for-Video-Prediction","url":"https://github.com/seominseok0429/Implicit-Stacked-Autoregressive-Model-for-Video-Prediction"}],"syntology":null}},{"leaderboard":"/sota/video-prediction-on-bair-robot-pushing-1","slug":"video-prediction-on-bair-robot-pushing-1","dataset":"BAIR Robot Pushing","dataset_url":"/dataset/bair-robot-pushing","rows_in_archive":6,"metrics":["FVD"],"first_row_in_archive_order":{"model":"MAGVIT (-L-FP)","paper_title":"MAGVIT: Masked Generative Video Transformer","paper_url":"/paper/magvit-masked-generative-video-transformer","paper_date":"2022-12-10","arxiv_id":"2212.05199","code_links":[{"title":"google-research/magvit","url":"https://github.com/google-research/magvit"}],"syntology":{"n":10,"n_ran":1,"n_unverified":9,"n_pointer_only":0}}},{"leaderboard":"/sota/video-prediction-on-cityscapes-128x128","slug":"video-prediction-on-cityscapes-128x128","dataset":"Cityscapes 128x128","dataset_url":"/dataset/cityscapes","rows_in_archive":5,"metrics":["FVD","SSIM","PSNR","LPIPS","Cond.","Train","Pred"],"first_row_in_archive_order":{"model":"GHVAEs","paper_title":"Greedy Hierarchical Variational Autoencoders for Large-Scale Video Prediction","paper_url":"/paper/greedy-hierarchical-variational-autoencoders","paper_date":"2021-03-06","arxiv_id":"2103.04174","code_links":[],"syntology":null}},{"leaderboard":"/sota/video-prediction-on-synpickvp","slug":"video-prediction-on-synpickvp","dataset":"SynpickVP","dataset_url":"/dataset/synpick","rows_in_archive":5,"metrics":["LPIPS","MSE","PSNR","SSIM"],"first_row_in_archive_order":{"model":"MSPred","paper_title":"MSPred: Video Prediction at Multiple Spatio-Temporal Scales with Hierarchical Recurrent Networks","paper_url":"/paper/video-prediction-at-multiple-scales-with","paper_date":"2022-03-17","arxiv_id":"2203.09303","code_links":[{"title":"AIS-Bonn/MSPred","url":"https://github.com/AIS-Bonn/MSPred"}],"syntology":null}},{"leaderboard":"/sota/video-prediction-on-cmu-mocap-2","slug":"video-prediction-on-cmu-mocap-2","dataset":"CMU Mocap-2","dataset_url":null,"rows_in_archive":4,"metrics":["Test Error"],"first_row_in_archive_order":{"model":"Latent SDE","paper_title":"Scalable Gradients for Stochastic Differential Equations","paper_url":"/paper/scalable-gradients-for-stochastic","paper_date":"2020-01-05","arxiv_id":"2001.01328","code_links":[{"title":"google-research/torchsde","url":"https://github.com/google-research/torchsde"},{"title":"xwinxu/bayesian-sde","url":"https://github.com/xwinxu/bayesian-sde"},{"title":"xwinxu/bayesde","url":"https://github.com/xwinxu/bayesde"},{"title":"JFagin/latent_SDE","url":"https://github.com/JFagin/latent_SDE"}],"syntology":{"n":5,"n_ran":1,"n_unverified":4,"n_pointer_only":2}}},{"leaderboard":"/sota/video-prediction-on-cityscapes-1","slug":"video-prediction-on-cityscapes-1","dataset":"Cityscapes","dataset_url":"/dataset/cityscapes","rows_in_archive":3,"metrics":["LPIPS","MS-SSIM"],"first_row_in_archive_order":{"model":"DMVFN","paper_title":"A Dynamic Multi-Scale Voxel Flow Network for Video Prediction","paper_url":"/paper/a-dynamic-multi-scale-voxel-flow-network-for","paper_date":"2023-03-17","arxiv_id":"2303.09875","code_links":[{"title":"megvii-research/CVPR2023-DMVFN","url":"https://github.com/megvii-research/CVPR2023-DMVFN"}],"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/video-prediction-on-kitti","slug":"video-prediction-on-kitti","dataset":"KITTI","dataset_url":"/dataset/kitti","rows_in_archive":3,"metrics":["LPIPS","MS-SSIM"],"first_row_in_archive_order":{"model":"DMVFN","paper_title":"A Dynamic Multi-Scale Voxel Flow Network for Video Prediction","paper_url":"/paper/a-dynamic-multi-scale-voxel-flow-network-for","paper_date":"2023-03-17","arxiv_id":"2303.09875","code_links":[{"title":"megvii-research/CVPR2023-DMVFN","url":"https://github.com/megvii-research/CVPR2023-DMVFN"}],"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/video-prediction-on-vimeo90k","slug":"video-prediction-on-vimeo90k","dataset":"Vimeo90K","dataset_url":"/dataset/vimeo90k-1","rows_in_archive":3,"metrics":["LPIPS","MS-SSIM"],"first_row_in_archive_order":{"model":"OPT","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/video-prediction-on-cmu-mocap-1","slug":"video-prediction-on-cmu-mocap-1","dataset":"CMU Mocap-1","dataset_url":null,"rows_in_archive":2,"metrics":["Test Error"],"first_row_in_archive_order":{"model":"ODE2VAE-KL","paper_title":"ODE$^2$VAE: Deep generative second order ODEs with Bayesian neural networks","paper_url":"/paper/ode2vae-deep-generative-second-order-odes","paper_date":"2019-05-27","arxiv_id":"1905.10994","code_links":[{"title":"cagatayyildiz/ODE2VAE","url":"https://github.com/cagatayyildiz/ODE2VAE"}],"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/video-prediction-on-davis-2017","slug":"video-prediction-on-davis-2017","dataset":"DAVIS 2017","dataset_url":"/dataset/davis-2017","rows_in_archive":2,"metrics":["LPIPS","MS-SSIM"],"first_row_in_archive_order":{"model":"DMVFN","paper_title":"A Dynamic Multi-Scale Voxel Flow Network for Video Prediction","paper_url":"/paper/a-dynamic-multi-scale-voxel-flow-network-for","paper_date":"2023-03-17","arxiv_id":"2303.09875","code_links":[{"title":"megvii-research/CVPR2023-DMVFN","url":"https://github.com/megvii-research/CVPR2023-DMVFN"}],"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/video-prediction-on-colored-dsprites","slug":"video-prediction-on-colored-dsprites","dataset":"Colored dSprites","dataset_url":"/dataset/sprites","rows_in_archive":1,"metrics":["MSE"],"first_row_in_archive_order":{"model":"MGP-VAE (with geodesic loss)","paper_title":"Disentangling Multiple Features in Video Sequences using Gaussian Processes in Variational Autoencoders","paper_url":"/paper/disentangling-representations-using-gaussian","paper_date":"2020-01-08","arxiv_id":"2001.02408","code_links":[{"title":"SUTDBrainLab/MGP-VAE","url":"https://github.com/SUTDBrainLab/MGP-VAE"}],"syntology":null}},{"leaderboard":"/sota/video-prediction-on-kth-64x64-cond10-pred30","slug":"video-prediction-on-kth-64x64-cond10-pred30","dataset":"KTH 64x64 cond10 pred30","dataset_url":null,"rows_in_archive":1,"metrics":["FVD"],"first_row_in_archive_order":{"model":"SRVP","paper_title":"Stochastic Latent Residual Video Prediction","paper_url":"/paper/stochastic-latent-residual-video-prediction-1","paper_date":"2020-02-21","arxiv_id":"2002.09219","code_links":[{"title":"edouardelasalles/srvp","url":"https://github.com/edouardelasalles/srvp"}],"syntology":{"n":12,"n_ran":2,"n_unverified":10,"n_pointer_only":0}}},{"leaderboard":"/sota/video-prediction-on-mpi-sintel","slug":"video-prediction-on-mpi-sintel","dataset":"MPI Sintel","dataset_url":"/dataset/mpi-sintel","rows_in_archive":1,"metrics":["LPIPS","PSNR","SSIM","ST-RRED"],"first_row_in_archive_order":{"model":"MCnet [villegas2017mcnet]","paper_title":"Temporal View Synthesis of Dynamic Scenes through 3D Object Motion Estimation with Multi-Plane Images","paper_url":"/paper/temporal-view-synthesis-of-dynamic-scenes","paper_date":"2022-08-19","arxiv_id":"2208.09463","code_links":[{"title":"NagabhushanSN95/DeCOMPnet","url":"https://github.com/NagabhushanSN95/DeCOMPnet"}],"syntology":null}},{"leaderboard":"/sota/video-prediction-on-something-something-v2","slug":"video-prediction-on-something-something-v2","dataset":"Something-Something V2","dataset_url":"/dataset/something-something-v2","rows_in_archive":1,"metrics":["FVD"],"first_row_in_archive_order":{"model":"MAGVIT","paper_title":"MAGVIT: Masked Generative Video Transformer","paper_url":"/paper/magvit-masked-generative-video-transformer","paper_date":"2022-12-10","arxiv_id":"2212.05199","code_links":[{"title":"google-research/magvit","url":"https://github.com/google-research/magvit"}],"syntology":{"n":10,"n_ran":1,"n_unverified":9,"n_pointer_only":0}}},{"leaderboard":"/sota/video-prediction-on-sprites","slug":"video-prediction-on-sprites","dataset":"Sprites","dataset_url":"/dataset/sprites","rows_in_archive":1,"metrics":["MSE"],"first_row_in_archive_order":{"model":"MGP-VAE (with geodesic loss)","paper_title":"Disentangling Multiple Features in Video Sequences using Gaussian Processes in Variational Autoencoders","paper_url":"/paper/disentangling-representations-using-gaussian","paper_date":"2020-01-08","arxiv_id":"2001.02408","code_links":[{"title":"SUTDBrainLab/MGP-VAE","url":"https://github.com/SUTDBrainLab/MGP-VAE"}],"syntology":null}},{"leaderboard":"/sota/video-prediction-on-youtube-8m","slug":"video-prediction-on-youtube-8m","dataset":"YouTube-8M","dataset_url":"/dataset/youtube-8m","rows_in_archive":1,"metrics":["Average PSNR"],"first_row_in_archive_order":{"model":"SDCNet","paper_title":"SDC-Net: Video prediction using spatially-displaced convolution","paper_url":"/paper/sdc-net-video-prediction-using-spatially","paper_date":"2018-09-01","arxiv_id":null,"code_links":[{"title":"NVIDIA/semantic-segmentation","url":"https://github.com/NVIDIA/semantic-segmentation/tree/sdcnet/sdcnet"}],"syntology":null}}],"datasets":[{"url":"/dataset/mnist","name":"MNIST","full_name":"","num_papers_in_archive":7651},{"url":"/dataset/cityscapes","name":"Cityscapes","full_name":"","num_papers_in_archive":3702},{"url":"/dataset/kitti","name":"KITTI","full_name":"","num_papers_in_archive":3661},{"url":"/dataset/kinetics","name":"Kinetics","full_name":"Kinetics Human Action Video Dataset","num_papers_in_archive":1341},{"url":"/dataset/human3-6m","name":"Human3.6M","full_name":"","num_papers_in_archive":783},{"url":"/dataset/davis","name":"DAVIS","full_name":"Densely Annotated VIdeo Segmentation","num_papers_in_archive":734},{"url":"/dataset/davis-2017","name":"DAVIS 2017","full_name":"DAVIS 2017","num_papers_in_archive":308},{"url":"/dataset/something-something-v2","name":"Something-Something V2","full_name":"","num_papers_in_archive":290},{"url":"/dataset/kth","name":"KTH","full_name":"KTH Action dataset","num_papers_in_archive":279},{"url":"/dataset/vimeo90k-1","name":"Vimeo90K","full_name":"","num_papers_in_archive":220},{"url":"/dataset/mpi-sintel","name":"MPI Sintel","full_name":"","num_papers_in_archive":198},{"url":"/dataset/moving-mnist","name":"Moving MNIST","full_name":"","num_papers_in_archive":194},{"url":"/dataset/kinetics-600","name":"Kinetics-600","full_name":"","num_papers_in_archive":148},{"url":"/dataset/youtube-8m","name":"YouTube-8M","full_name":"","num_papers_in_archive":147},{"url":"/dataset/sprites","name":"Sprites","full_name":"2D Video Game Character Sprites","num_papers_in_archive":52},{"url":"/dataset/phyre","name":"PHYRE","full_name":"PHYsical REasoning","num_papers_in_archive":35},{"url":"/dataset/bair-robot-pushing","name":"BAIR Robot Pushing","full_name":"","num_papers_in_archive":27},{"url":"/dataset/robotic-pushing","name":"Robotic Pushing","full_name":"","num_papers_in_archive":12},{"url":"/dataset/earthnet2021","name":"EarthNet2021","full_name":"EarthNet2021: Earth Surface Forecasting","num_papers_in_archive":10},{"url":"/dataset/synpick","name":"SynPick","full_name":"","num_papers_in_archive":7},{"url":"/dataset/qst","name":"QST","full_name":"Quick Sky Time","num_papers_in_archive":3},{"url":"/dataset/cloudcast","name":"CloudCast","full_name":"CloudCast: A Satellite-Based Dataset and Baseline for Forecasting Clouds","num_papers_in_archive":1},{"url":"/dataset/iisc-vine","name":"IISc VINE","full_name":"Indian Institute of Science VIdeo Naturalness Evaluation","num_papers_in_archive":1},{"url":"/dataset/moving-symbols","name":"Moving Symbols","full_name":"","num_papers_in_archive":1},{"url":"/dataset/shanghai2020","name":"Shanghai2020","full_name":"Shanghai-2020 Dataset","num_papers_in_archive":0}],"subtasks":[{"url":"/task/earth-surface-forecasting","name":"Earth Surface Forecasting"},{"url":"/task/predict-future-video-frames","name":"Predict Future Video Frames"}],"parent_tasks":[{"url":"/task/video","name":"Video"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":208,"tagged_in_all":394,"items":[{"url":"/paper/convolutional-lstm-network-a-machine-learning","title":"Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting","date":"2015-06-13","arxiv_id":"1506.04214","repositories_listed":23,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":2}},{"url":"/paper/deep-predictive-coding-networks-for-video","title":"Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning","date":"2016-05-25","arxiv_id":"1605.08104","repositories_listed":17,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":2}},{"url":"/paper/predrnn-towards-a-resolution-of-the-deep-in","title":"PredRNN++: Towards A Resolution of the Deep-in-Time Dilemma in Spatiotemporal Predictive Learning","date":"2018-04-17","arxiv_id":"1804.06300","repositories_listed":11,"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/video-to-video-synthesis","title":"Video-to-Video Synthesis","date":"2018-08-20","arxiv_id":"1808.06601","repositories_listed":10,"syntology":null},{"url":"/paper/efficient-multi-order-gated-aggregation","title":"MogaNet: Multi-order Gated Aggregation Network","date":"2022-11-07","arxiv_id":"2211.03295","repositories_listed":7,"syntology":{"n":15,"n_ran":12,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/video-diffusion-models","title":"Video Diffusion Models","date":"2022-04-07","arxiv_id":"2204.03458","repositories_listed":5,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/the-something-something-video-database-for","title":"The \"something something\" video database for learning and evaluating visual common sense","date":"2017-06-13","arxiv_id":"1706.04261","repositories_listed":5,"syntology":null},{"url":"/paper/deep-multi-scale-video-prediction-beyond-mean","title":"Deep multi-scale video prediction beyond mean square error","date":"2015-11-17","arxiv_id":"1511.05440","repositories_listed":5,"syntology":{"n":10,"n_ran":2,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/scalable-gradients-for-stochastic","title":"Scalable Gradients for Stochastic Differential Equations","date":"2020-01-05","arxiv_id":"2001.01328","repositories_listed":4,"syntology":{"n":5,"n_ran":1,"n_unverified":4,"n_pointer_only":2}},{"url":"/paper/sme-net-sparse-motion-estimation-for","title":"SME-Net: Sparse Motion Estimation for Parametric Video Prediction Through Reinforcement Learning","date":"2019-10-01","arxiv_id":null,"repositories_listed":4,"syntology":null},{"url":"/paper/memory-in-memory-a-predictive-neural-network","title":"Memory In Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity from Spatiotemporal Dynamics","date":"2018-11-19","arxiv_id":"1811.07490","repositories_listed":4,"syntology":null},{"url":"/paper/stochastic-adversarial-video-prediction","title":"Stochastic Adversarial Video Prediction","date":"2018-04-04","arxiv_id":"1804.01523","repositories_listed":4,"syntology":{"n":16,"n_ran":4,"n_unverified":12,"n_pointer_only":3}},{"url":"/paper/deep-learning-for-precipitation-nowcasting-a","title":"Deep Learning for Precipitation Nowcasting: A Benchmark and A New Model","date":"2017-06-12","arxiv_id":"1706.03458","repositories_listed":4,"syntology":{"n":10,"n_ran":9,"n_unverified":1,"n_pointer_only":5}},{"url":"/paper/learning-a-driving-simulator","title":"Learning a Driving Simulator","date":"2016-08-03","arxiv_id":"1608.01230","repositories_listed":4,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/generalized-predictive-model-for-autonomous","title":"GenAD: Generalized Predictive Model for Autonomous Driving","date":"2024-03-14","arxiv_id":"2403.09630","repositories_listed":3,"syntology":{"n":8,"n_ran":6,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/switch-ema-a-free-lunch-for-better-flatness","title":"Switch EMA: A Free Lunch for Better Flatness and Sharpness","date":"2024-02-14","arxiv_id":"2402.09240","repositories_listed":3,"syntology":null},{"url":"/paper/language-model-beats-diffusion-tokenizer-is","title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","date":"2023-10-09","arxiv_id":"2310.05737","repositories_listed":3,"syntology":{"n":20,"n_ran":12,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/video-prediction-models-as-rewards-for","title":"Video Prediction Models as Rewards for Reinforcement Learning","date":"2023-05-23","arxiv_id":"2305.14343","repositories_listed":3,"syntology":{"n":15,"n_ran":6,"n_unverified":9,"n_pointer_only":1}},{"url":"/paper/simvp-simpler-yet-better-video-prediction-1","title":"SimVP: Simpler yet Better Video Prediction","date":"2022-06-09","arxiv_id":"2206.05099","repositories_listed":3,"syntology":{"n":9,"n_ran":6,"n_unverified":3,"n_pointer_only":9}},{"url":"/paper/predrnn-a-recurrent-neural-network-for","title":"PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning","date":"2021-03-17","arxiv_id":"2103.09504","repositories_listed":3,"syntology":null},{"url":"/paper/disentangling-physical-dynamics-from-unknown","title":"Disentangling Physical Dynamics from Unknown Factors for Unsupervised Video Prediction","date":"2020-03-03","arxiv_id":"2003.01460","repositories_listed":3,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/video-action-classification-using-prednet","title":"PredNet and Predictive Coding: A Critical Review","date":"2019-06-14","arxiv_id":"1906.11902","repositories_listed":3,"syntology":null},{"url":"/paper/eidetic-3d-lstm-a-model-for-video-prediction","title":"Eidetic 3D LSTM: A Model for Video Prediction and Beyond","date":"2019-05-01","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/towards-accurate-generative-models-of-video-a","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","date":"2018-12-03","arxiv_id":"1812.01717","repositories_listed":3,"syntology":null},{"url":"/paper/robustness-via-retrying-closed-loop-robotic","title":"Robustness via Retrying: Closed-Loop Robotic Manipulation with Self-Supervised Learning","date":"2018-10-06","arxiv_id":"1810.03043","repositories_listed":3,"syntology":null},{"url":"/paper/stochastic-video-generation-with-a-learned","title":"Stochastic Video Generation with a Learned Prior","date":"2018-02-21","arxiv_id":"1802.07687","repositories_listed":3,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":2}},{"url":"/paper/stochastic-variational-video-prediction","title":"Stochastic Variational Video Prediction","date":"2017-10-30","arxiv_id":"1710.11252","repositories_listed":3,"syntology":null},{"url":"/paper/self-supervised-visual-planning-with-temporal","title":"Self-Supervised Visual Planning with Temporal Skip Connections","date":"2017-10-15","arxiv_id":"1710.05268","repositories_listed":3,"syntology":null},{"url":"/paper/video-frame-synthesis-using-deep-voxel-flow","title":"Video Frame Synthesis using Deep Voxel Flow","date":"2017-02-08","arxiv_id":"1702.02463","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/rethinking-urban-mobility-prediction-a-super","title":"Rethinking Urban Mobility Prediction: A Super-Multivariate Time Series Forecasting Approach","date":"2023-12-04","arxiv_id":"2312.01699","repositories_listed":2,"syntology":null}],"syntology_records":17,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}