{"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/video-prediction-by-efficient-transformers","title":"Video Prediction by Efficient Transformers","arxiv_id":"2212.06026","date":"2022-12-12","proceeding":null,"authors":["Xi Ye","Guillaume-Alexandre Bilodeau"],"abstract":"Video prediction is a challenging computer vision task that has a wide range of applications. In this work, we present a new family of Transformer-based models for video prediction. Firstly, an efficient local spatial-temporal separation attention mechanism is proposed to reduce the complexity of standard Transformers. Then, a full autoregressive model, a partial autoregressive model and a non-autoregressive model are developed based on the new efficient Transformer. The partial autoregressive model has a similar performance with the full autoregressive model but a faster inference speed. The non-autoregressive model not only achieves a faster inference speed but also mitigates the quality degradation problem of the autoregressive counterparts, but it requires additional parameters and loss function for learning. Given the same attention mechanism, we conducted a comprehensive study to compare the proposed three video prediction variants. Experiments show that the proposed video prediction models are competitive with more complex state-of-the-art convolutional-LSTM based models. The source code is available at https://github.com/XiYe20/VPTR.","url_abs":"https://arxiv.org/abs/2212.06026v1","url_pdf":"https://arxiv.org/pdf/2212.06026v1.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":"video-prediction-by-efficient-transformers","repo_url":"https://github.com/xiye20/vptr","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":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"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":"speed","method_name":"SPEED"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2212.06026","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.06026"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xiye20/vptr","reach":null}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":7,"ran":0,"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":"10e5c408b4899768","entry":"cal_lossD","repo":"xiye20/vptr","repo_kind":"official","path":"train_AutoEncoder.py","file_url":"https://github.com/xiye20/vptr/blob/HEAD/train_AutoEncoder.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":"10e5c408b4899768"}},{"code_sha256_prefix":"c27d3a5b0dce37a6","entry":"cal_lossG","repo":"xiye20/vptr","repo_kind":"official","path":"train_AutoEncoder.py","file_url":"https://github.com/xiye20/vptr/blob/HEAD/train_AutoEncoder.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":"c27d3a5b0dce37a6"}},{"code_sha256_prefix":"e4f3fb8ec618dd59","entry":"cal_lossT","repo":"xiye20/vptr","repo_kind":"official","path":"train_FAR.py","file_url":"https://github.com/xiye20/vptr/blob/HEAD/train_FAR.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":"e4f3fb8ec618dd59"}},{"code_sha256_prefix":"66eff5521312d746","entry":"cal_lossT","repo":"xiye20/vptr","repo_kind":"official","path":"train_NAR.py","file_url":"https://github.com/xiye20/vptr/blob/HEAD/train_NAR.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":"66eff5521312d746"}},{"code_sha256_prefix":"9e264a7feb78f892","entry":"single_iter","repo":"xiye20/vptr","repo_kind":"official","path":"train_AutoEncoder.py","file_url":"https://github.com/xiye20/vptr/blob/HEAD/train_AutoEncoder.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":"9e264a7feb78f892"}},{"code_sha256_prefix":"b6bf56e6a660e0b4","entry":"single_iter","repo":"xiye20/vptr","repo_kind":"official","path":"train_FAR.py","file_url":"https://github.com/xiye20/vptr/blob/HEAD/train_FAR.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":"b6bf56e6a660e0b4"}},{"code_sha256_prefix":"d82e894dd15729d2","entry":"single_iter","repo":"xiye20/vptr","repo_kind":"official","path":"train_NAR.py","file_url":"https://github.com/xiye20/vptr/blob/HEAD/train_NAR.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":"d82e894dd15729d2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}