{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/swinlstm-improving-spatiotemporal-prediction","title":"SwinLSTM:Improving Spatiotemporal Prediction Accuracy using Swin Transformer and LSTM","arxiv_id":"2308.09891","date":"2023-08-19","proceeding":null,"authors":["Song Tang","Chuang Li","Pu Zhang","RongNian Tang"],"abstract":"Integrating CNNs and RNNs to capture spatiotemporal dependencies is a prevalent strategy for spatiotemporal prediction tasks. However, the property of CNNs to learn local spatial information decreases their efficiency in capturing spatiotemporal dependencies, thereby limiting their prediction accuracy. In this paper, we propose a new recurrent cell, SwinLSTM, which integrates Swin Transformer blocks and the simplified LSTM, an extension that replaces the convolutional structure in ConvLSTM with the self-attention mechanism. Furthermore, we construct a network with SwinLSTM cell as the core for spatiotemporal prediction. Without using unique tricks, SwinLSTM outperforms state-of-the-art methods on Moving MNIST, Human3.6m, TaxiBJ, and KTH datasets. In particular, it exhibits a significant improvement in prediction accuracy compared to ConvLSTM. Our competitive experimental results demonstrate that learning global spatial dependencies is more advantageous for models to capture spatiotemporal dependencies. We hope that SwinLSTM can serve as a solid baseline to promote the advancement of spatiotemporal prediction accuracy. The codes are publicly available at https://github.com/SongTang-x/SwinLSTM.","url_abs":"https://arxiv.org/abs/2308.09891v2","url_pdf":"https://arxiv.org/pdf/2308.09891v2.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":"swinlstm-improving-spatiotemporal-prediction","repo_url":"https://github.com/SongTang-x/SwinLSTM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"video-prediction","task_name":"Video Prediction"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"convlstm","method_name":"ConvLSTM"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"stochastic-depth","method_name":"Stochastic Depth"},{"method_slug":"swin-transformer","method_name":"Swin Transformer"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2308.09891","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.09891"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/SongTang-x/SwinLSTM","reach":null}],"summary":{"ran":4,"unverified":5},"by_repo_kind":{"official":{"samples":9,"ran":4,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"de345690ecacb912","entry":"Mlp","repo":"SongTang-x/SwinLSTM","repo_kind":"official","path":"SwinLSTM_B.py","file_url":"https://github.com/SongTang-x/SwinLSTM/blob/HEAD/SwinLSTM_B.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"de345690ecacb912"}},{"code_sha256_prefix":"f218ccc91f9eeaee","entry":"PatchEmbed","repo":"SongTang-x/SwinLSTM","repo_kind":"official","path":"SwinLSTM_B.py","file_url":"https://github.com/SongTang-x/SwinLSTM/blob/HEAD/SwinLSTM_B.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f218ccc91f9eeaee"}},{"code_sha256_prefix":"eb22dd56aab234c3","entry":"PatchInflated","repo":"SongTang-x/SwinLSTM","repo_kind":"official","path":"SwinLSTM_B.py","file_url":"https://github.com/SongTang-x/SwinLSTM/blob/HEAD/SwinLSTM_B.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eb22dd56aab234c3"}},{"code_sha256_prefix":"b338c06cfc49760e","entry":"WindowAttention","repo":"SongTang-x/SwinLSTM","repo_kind":"official","path":"SwinLSTM_B.py","file_url":"https://github.com/SongTang-x/SwinLSTM/blob/HEAD/SwinLSTM_B.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b338c06cfc49760e"}},{"code_sha256_prefix":"05b172e9f70b625c","entry":"STconvert","repo":"SongTang-x/SwinLSTM","repo_kind":"official","path":"SwinLSTM_B.py","file_url":"https://github.com/SongTang-x/SwinLSTM/blob/HEAD/SwinLSTM_B.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"05b172e9f70b625c"}},{"code_sha256_prefix":"ac06f36c3571c0ab","entry":"SwinLSTM","repo":"SongTang-x/SwinLSTM","repo_kind":"official","path":"SwinLSTM_B.py","file_url":"https://github.com/SongTang-x/SwinLSTM/blob/HEAD/SwinLSTM_B.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ac06f36c3571c0ab"}},{"code_sha256_prefix":"ae5ac128d905625e","entry":"SwinLSTMCell","repo":"SongTang-x/SwinLSTM","repo_kind":"official","path":"SwinLSTM_B.py","file_url":"https://github.com/SongTang-x/SwinLSTM/blob/HEAD/SwinLSTM_B.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ae5ac128d905625e"}},{"code_sha256_prefix":"5a21d51c14cc656c","entry":"SwinTransformerBlock","repo":"SongTang-x/SwinLSTM","repo_kind":"official","path":"SwinLSTM_B.py","file_url":"https://github.com/SongTang-x/SwinLSTM/blob/HEAD/SwinLSTM_B.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5a21d51c14cc656c"}},{"code_sha256_prefix":"476b92802d0c2a12","entry":"SwinTransformerBlocks","repo":"SongTang-x/SwinLSTM","repo_kind":"official","path":"SwinLSTM_B.py","file_url":"https://github.com/SongTang-x/SwinLSTM/blob/HEAD/SwinLSTM_B.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"476b92802d0c2a12"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}