{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/predrnn-a-recurrent-neural-network-for","title":"PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning","arxiv_id":"2103.09504","date":"2021-03-17","proceeding":null,"authors":["Yunbo Wang","Haixu Wu","Jianjin Zhang","Zhifeng Gao","Jianmin Wang","Philip S. Yu","Mingsheng Long"],"abstract":"The predictive learning of spatiotemporal sequences aims to generate future images by learning from the historical context, where the visual dynamics are believed to have modular structures that can be learned with compositional subsystems. This paper models these structures by presenting PredRNN, a new recurrent network, in which a pair of memory cells are explicitly decoupled, operate in nearly independent transition manners, and finally form unified representations of the complex environment. Concretely, besides the original memory cell of LSTM, this network is featured by a zigzag memory flow that propagates in both bottom-up and top-down directions across all layers, enabling the learned visual dynamics at different levels of RNNs to communicate. It also leverages a memory decoupling loss to keep the memory cells from learning redundant features. We further propose a new curriculum learning strategy to force PredRNN to learn long-term dynamics from context frames, which can be generalized to most sequence-to-sequence models. We provide detailed ablation studies to verify the effectiveness of each component. Our approach is shown to obtain highly competitive results on five datasets for both action-free and action-conditioned predictive learning scenarios.","url_abs":"https://arxiv.org/abs/2103.09504v4","url_pdf":"https://arxiv.org/pdf/2103.09504v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"predrnn-a-recurrent-neural-network-for","repo_url":"https://github.com/thuml/predrnn-pytorch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"predrnn-a-recurrent-neural-network-for","repo_url":"https://github.com/chengtan9907/simvpv2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"predrnn-a-recurrent-neural-network-for","repo_url":"https://github.com/ksm26/spatiotemporal-predictions","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"video-prediction","task_name":"Video Prediction"},{"task_slug":"weather-forecasting","task_name":"Weather Forecasting"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-prediction-on-kth","task":"Video Prediction","dataset":"KTH","model":"PredRNN-V2","rank_in_archive_order":21,"of":31,"metrics":{"Cond":"10","LPIPS":"0.139","PSNR":"28.37","Pred":"20","SSIM":"0.839"},"uses_additional_data":false},{"leaderboard":"/sota/video-prediction-on-moving-mnist","task":"Video Prediction","dataset":"Moving MNIST","model":"PredRNN-V2","rank_in_archive_order":28,"of":31,"metrics":{"LPIPS":"0.071","MSE":"48.4","SSIM":"0.891"},"uses_additional_data":false},{"leaderboard":"/sota/weather-forecasting-on-sevir","task":"Weather Forecasting","dataset":"SEVIR","model":"PredRNN","rank_in_archive_order":4,"of":8,"metrics":{"MSE":"3.9014","mCSI":"0.4080"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2103.09504","atlas_url":"https://app.syntology.ai/?focus=2103.09504","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2103.09504"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2103.09504\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2103.09504"},"call":"get_concepts_for_paper(arxiv_id=\"2103.09504\")"}],"by_repo":[{"repo":"thuml/predrnn-pytorch","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"chengtan9907/simvpv2","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2306.11249"],"harvested_for_calls":[{"arxiv_id":"2306.11249","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2306.11249"},"call":"get_harvested_code_for_paper(arxiv_id=\"2306.11249\")"}]},{"repo":"ksm26/spatiotemporal-predictions","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"e0d95e7869c03dbbb40159e7aefe58837175f54b19a73d1509bf268f0934ee28","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}