{"url":"/sota/video-prediction-on-kinetics-600-12-frames","task":{"name":"Video Prediction","url":"/task/video-prediction","note":null},"dataset":{"name":"Kinetics-600 12 frames, 64x64","url":"/dataset/kinetics"},"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":["FVD","IS","Cond","Pred"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"FVD":null,"IS":null,"Cond":null,"Pred":null}},"counts":{"rows":16,"rows_with_code":13,"rows_with_paper_page":16,"rows_dated":16,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"SiD2","metrics":{"Cond":"5","FVD":"2.3","Pred":"11"},"uses_additional_data":false,"paper_date":"2024-10-25","paper":"/paper/simpler-diffusion-sid2-1-5-fid-on-imagenet512","paper_url":"https://arxiv.org/abs/2410.19324v2","paper_title":"Simpler Diffusion (SiD2): 1.5 FID on ImageNet512 with pixel-space diffusion","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"W.A.L.T.-L","metrics":{"FVD":"3.3"},"uses_additional_data":false,"paper_date":"2023-12-11","paper":"/paper/photorealistic-video-generation-with","paper_url":"https://arxiv.org/abs/2312.06662v1","paper_title":"Photorealistic Video Generation with Diffusion Models","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"MAGVIT-v2","metrics":{"FVD":"4.3±0.1"},"uses_additional_data":false,"paper_date":"2023-10-09","paper":"/paper/language-model-beats-diffusion-tokenizer-is","paper_url":"https://arxiv.org/abs/2310.05737v3","paper_title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","code":"https://github.com/jy0205/Pyramid-Flow","n_code_links":3,"syntology":{"n_ran":19,"n_unverified":1,"n_samples":20,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"LARP","metrics":{"Cond":"5","FVD":"5.1","Pred":"11"},"uses_additional_data":false,"paper_date":"2024-10-28","paper":"/paper/larp-tokenizing-videos-with-a-learned-1","paper_url":"https://arxiv.org/abs/2410.21264v1","paper_title":"LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior","code":"https://github.com/hywang66/LARP","n_code_links":1,"syntology":{"n_ran":11,"n_unverified":2,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"MAGVIT (-L-FP)","metrics":{"Cond":"5","FVD":"9.9±0.3","Pred":"11"},"uses_additional_data":false,"paper_date":"2022-12-10","paper":"/paper/magvit-masked-generative-video-transformer","paper_url":"https://arxiv.org/abs/2212.05199v2","paper_title":"MAGVIT: Masked Generative Video Transformer","code":"https://github.com/google-research/magvit","n_code_links":1,"syntology":{"n_ran":9,"n_unverified":1,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"RIN (1000 steps)","metrics":{"FVD":"10.8","IS":"17.7"},"uses_additional_data":false,"paper_date":"2022-12-22","paper":"/paper/scalable-adaptive-computation-for-iterative","paper_url":"https://arxiv.org/abs/2212.11972v2","paper_title":"Scalable Adaptive Computation for Iterative Generation","code":"https://github.com/google-research/pix2seq","n_code_links":2,"syntology":{"n_ran":21,"n_unverified":8,"n_samples":29,"n_pointer_only_licence":1}},{"rank_in_archive_order":7,"model":"RIN (400 steps)","metrics":{"FVD":"11.5","IS":"17.7"},"uses_additional_data":false,"paper_date":"2022-12-22","paper":"/paper/scalable-adaptive-computation-for-iterative","paper_url":"https://arxiv.org/abs/2212.11972v2","paper_title":"Scalable Adaptive Computation for Iterative Generation","code":"https://github.com/google-research/pix2seq","n_code_links":2,"syntology":{"n_ran":21,"n_unverified":8,"n_samples":29,"n_pointer_only_licence":1}},{"rank_in_archive_order":8,"model":"RaMViD","metrics":{"Cond":"5","FVD":"16.46","Pred":"11"},"uses_additional_data":false,"paper_date":"2022-06-15","paper":"/paper/diffusion-models-for-video-prediction-and","paper_url":"https://arxiv.org/abs/2206.07696v3","paper_title":"Diffusion Models for Video Prediction and Infilling","code":"https://github.com/Tobi-r9/RaMViD","n_code_links":1,"syntology":{"n_ran":9,"n_unverified":10,"n_samples":19,"n_pointer_only_licence":0}},{"rank_in_archive_order":9,"model":"MAGVIT (-B-FP)","metrics":{"Cond":"5","FVD":"24.5±0.9","Pred":"11"},"uses_additional_data":false,"paper_date":"2022-12-10","paper":"/paper/magvit-masked-generative-video-transformer","paper_url":"https://arxiv.org/abs/2212.05199v2","paper_title":"MAGVIT: Masked Generative Video Transformer","code":"https://github.com/google-research/magvit","n_code_links":1,"syntology":{"n_ran":9,"n_unverified":1,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"TriVD-GAN-FP","metrics":{"Cond":"5","FVD":"25.74±0.66","IS":"12.54±0.06","Pred":"11"},"uses_additional_data":false,"paper_date":"2020-03-09","paper":"/paper/transformation-based-adversarial-video","paper_url":"https://arxiv.org/abs/2003.04035v3","paper_title":"Transformation-based Adversarial Video Prediction on Large-Scale Data","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":11,"model":"OmniTokenizer-AR","metrics":{"FVD":"32.9"},"uses_additional_data":false,"paper_date":"2024-06-13","paper":"/paper/omnitokenizer-a-joint-image-video-tokenizer","paper_url":"https://arxiv.org/abs/2406.09399v1","paper_title":"OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation","code":"https://github.com/foundationvision/omnitokenizer","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":1}},{"rank_in_archive_order":12,"model":"CCVS","metrics":{"Cond":"5","FVD":"55±1","Pred":"11"},"uses_additional_data":false,"paper_date":"2021-07-16","paper":"/paper/ccvs-context-aware-controllable-video","paper_url":"https://arxiv.org/abs/2107.08037v2","paper_title":"CCVS: Context-aware Controllable Video Synthesis","code":"https://github.com/16lemoing/ccvs","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":5,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":13,"model":"Video VQ-VAE FVD","metrics":{"Cond":"4","FVD":"64.30±2.04","Pred":"12"},"uses_additional_data":false,"paper_date":"2021-03-02","paper":"/paper/predicting-video-with-vqvae-1","paper_url":"https://arxiv.org/abs/2103.01950v1","paper_title":"Predicting Video with VQVAE","code":"https://github.com/mattiasxu/Video-VQVAE","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"DVD-GAN-FP","metrics":{"Cond":"5","FVD":"69.15±0.78","Pred":"11"},"uses_additional_data":false,"paper_date":"2019-07-15","paper":"/paper/efficient-video-generation-on-complex","paper_url":"https://arxiv.org/abs/1907.06571v2","paper_title":"Adversarial Video Generation on Complex Datasets","code":"https://github.com/Harrypotterrrr/DVD-GAN","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"Video Transformer","metrics":{"Cond":"5","FVD":"170±5","Pred":"11"},"uses_additional_data":false,"paper_date":"2019-06-06","paper":"/paper/scaling-autoregressive-video-models","paper_url":"https://arxiv.org/abs/1906.02634v3","paper_title":"Scaling Autoregressive Video Models","code":"https://github.com/rakhimovv/lvt","n_code_links":1,"syntology":null},{"rank_in_archive_order":16,"model":"LVT","metrics":{"Cond":"5","FVD":"224.73","Pred":"11"},"uses_additional_data":false,"paper_date":"2020-06-18","paper":"/paper/latent-video-transformer","paper_url":"https://arxiv.org/abs/2006.10704v1","paper_title":"Latent Video Transformer","code":"https://github.com/rakhimovv/lvt","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":4,"n_samples":5,"n_pointer_only_licence":0}}],"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 7,081 of the 9,623 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":9623,"papers_checked":7081,"papers_extracted_not_yet_verified":217,"boards_without_verdict":27,"papers_not_yet_extracted":2325},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+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":10,"rows_with_any_sample_ran":10,"distinct_papers_with_graph_line":8,"distinct_papers_with_any_sample_ran":8,"samples_over_distinct_papers":{"n_ran":78,"n_unverified":31,"n_samples":109,"n_pointer_only_licence":2,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":108,"n_unverified":40,"n_samples":148,"n_pointer_only_licence":3,"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"}}}