{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T18:16:24Z","timestamp":1779387384174,"version":"3.53.1"},"reference-count":67,"publisher":"Institution of Engineering and Technology (IET)","issue":"2","license":[{"start":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T00:00:00Z","timestamp":1771200000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T00:00:00Z","timestamp":1771200000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP220103717"],"award-info":[{"award-number":["DP220103717"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["LE220100078"],"award-info":[{"award-number":["LE220100078"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["CAAI Trans on Intel Tech"],"published-print":{"date-parts":[[2026,4]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>The analysis of spatiotemporal data is essential across many fields, such as transportation, meteorology and healthcare. Data gathered in practical applications often suffer from incompleteness due to device failures and network disruptions. Spatiotemporal imputation targets the estimation of missing observations by exploiting intrinsic spatial\u2013temporal dependencies. Although traditional statistical and machine\u2010learning methods depend on restrictive distributional assumptions, graph\u2010 or recurrent\u2010based models accumulate errors through iterative propagation. Diffusion probabilistic models mitigate these issues by sampling directly from a learnt data prior instead of recycling past imputations. However, existing conditional diffusion variants still converge towards overly similar reconstructions, obscuring the genuine uncertainty and heterogeneity of real\u2010world traffic, environmental or clinical streams. Preserving\u2014and faithfully quantifying\u2014this intrinsic diversity is crucial for reliable forecasting and downstream decision\u2010making. We propose TSD, a conditional diffusion framework that integrates disentangled temporal representations and contrastive learning to improve generalisability in spatiotemporal imputation. Specifically, the approach uses disentangled temporal representations as conditional information to guide the reverse process. We also enhance the final loss using a contrastive learning strategy to improve representation quality, mitigating the impact of data missing completely at random (MCAR) and noise on learnt features. Through comprehensive experiments using three distinct real\u2010world datasets, TSD has competitive results compared to leading\u2010edge baselines.<\/jats:p>","DOI":"10.1049\/cit2.70085","type":"journal-article","created":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T15:17:11Z","timestamp":1771255031000},"page":"548-563","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Temporally Disentangled Contrastive Diffusion Model for Spatiotemporal Imputation"],"prefix":"10.1049","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8331-3410","authenticated-orcid":false,"given":"Yakun","family":"Chen","sequence":"first","affiliation":[{"name":"Centre for Learning, Teaching and Technology The Education University of Hong Kong  Hong Kong China"},{"name":"School of Computer Science University of Technology Sydney  Ultimo New South Wales Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3561-3627","authenticated-orcid":false,"given":"Kaize","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Computer Science University of Technology Sydney  Ultimo New South Wales Australia"},{"name":"School of Mathematics, Physics and Computing University of Southern Queensland  Brisbane Queensland Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhangkai","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science University of Technology Sydney  Ultimo New South Wales Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juan","family":"Chen","sequence":"additional","affiliation":[{"name":"Sophos Ltd  Sydney New South Wales Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9582-3445","authenticated-orcid":false,"given":"Xianzhi","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science University of Technology Sydney  Ultimo New South Wales Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julian","family":"McAuley","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering University of California San Diego  La Jolla California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guandong","family":"Xu","sequence":"additional","affiliation":[{"name":"Centre for Learning, Teaching and Technology The Education University of Hong Kong  Hong Kong China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shui","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Computer Science University of Technology Sydney  Ultimo New South Wales Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"265","published-online":{"date-parts":[[2026,2,16]]},"reference":[{"key":"e_1_2_11_2_1","first-page":"1907","volume-title":"28th International Joint Conference on Artificial Intelligence","author":"Wu Z.","year":"2019"},{"key":"e_1_2_11_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2020.2968894"},{"key":"e_1_2_11_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2020.3001195"},{"key":"e_1_2_11_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462\u2010022\u201010304\u20103"},{"key":"e_1_2_11_6_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14956"},{"key":"e_1_2_11_7_1","doi-asserted-by":"publisher","DOI":"10.1049\/cit2.12085"},{"key":"e_1_2_11_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10618\u2010019\u201000619\u20101"},{"key":"e_1_2_11_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3444690"},{"key":"e_1_2_11_10_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598\u2010018\u201024271\u20109"},{"key":"e_1_2_11_11_1","first-page":"1","volume-title":"International Conference on Learning Representations","author":"Cini A.","year":"2022"},{"key":"e_1_2_11_12_1","first-page":"1","article-title":"Brits: Bidirectional Recurrent Imputation for Time Series","volume":"31","author":"Cao W.","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_11_13_1","doi-asserted-by":"crossref","unstructured":"J.Wang W.Du W.Cao et\u00a0al. \u201cDeep Learning for Multivariate Time Series Imputation: A Survey \u201d preprint arXiv:2402.04059 (2024):10696\u201310704 https:\/\/doi.org\/10.24963\/ijcai.2024\/1187.","DOI":"10.24963\/ijcai.2024\/1187"},{"key":"e_1_2_11_14_1","first-page":"1","article-title":"Naomi: Non\u2010Autoregressive Multiresolution Sequence Imputation","volume":"32","author":"Liu Y.","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_11_15_1","first-page":"6840","article-title":"Denoising Diffusion Probabilistic Models","volume":"33","author":"Ho J.","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_11_16_1","first-page":"24804","article-title":"Csdi: Conditional Score\u2010Based Diffusion Models for Probabilistic Time Series Imputation","volume":"34","author":"Tashiro Y.","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_11_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE55515.2023.00150"},{"key":"e_1_2_11_18_1","first-page":"8780","article-title":"Diffusion Models Beat Gans on Image Synthesis","volume":"34","author":"Dhariwal P.","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_11_19_1","first-page":"8162","volume-title":"International Conference on Machine Learning","author":"Nichol A. Q.","year":"2021"},{"key":"e_1_2_11_20_1","unstructured":"S.Li Y.Chen andH.Xiong \u201cChannel\u2010Aware Contrastive Conditional Diffusion for Multivariate Probabilistic Time Series Forecasting \u201d preprint arXiv:2410.02168 (2024)."},{"issue":"1","key":"e_1_2_11_21_1","first-page":"3","article-title":"STL: A Seasonal\u2010Trend Decomposition Procedure Based on Loess","volume":"6","author":"Cleveland R. B.","year":"1990","journal-title":"Journal of Official Statistics"},{"key":"e_1_2_11_22_1","volume-title":"Forecasting: Principles and Practice","author":"Hyndman R. J.","year":"2018"},{"key":"e_1_2_11_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2020.2985720"},{"key":"e_1_2_11_24_1","first-page":"22419","volume-title":"Advances in Neural Information Processing Systems","author":"Wu H.","year":"2021"},{"key":"e_1_2_11_25_1","first-page":"4837","volume-title":"Advances in Neural Information Processing Systems","author":"Sen R.","year":"2019"},{"key":"e_1_2_11_26_1","first-page":"1","volume-title":"International Conference on Learning Representations","author":"Woo G.","year":"2022"},{"key":"e_1_2_11_27_1","first-page":"1597","volume-title":"International Conference on Machine Learning","author":"Chen T.","year":"2020"},{"key":"e_1_2_11_28_1","first-page":"21357","article-title":"Contragan: Contrastive Learning for Conditional Image Generation","volume":"33","author":"Kang M.","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_11_29_1","first-page":"8116","volume-title":"AAAI Conference on Artificial Intelligence","author":"Kang M.","year":"2021"},{"key":"e_1_2_11_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679532"},{"key":"e_1_2_11_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.120201"},{"key":"e_1_2_11_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3387317"},{"key":"e_1_2_11_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2629592"},{"key":"e_1_2_11_34_1","first-page":"1","volume-title":"International Conference on Learning Representations. ICLR","author":"Li Y.","year":"2018"},{"key":"e_1_2_11_35_1","doi-asserted-by":"publisher","DOI":"10.1175\/1520\u20100434(2000)015<0559:dotcrp>2.0.co;2"},{"key":"e_1_2_11_36_1","doi-asserted-by":"publisher","DOI":"10.1002\/sim.4067"},{"key":"e_1_2_11_37_1","first-page":"1","article-title":"Temporal Regularized Matrix Factorization for High\u2010Dimensional Time Series Prediction","volume":"29","author":"Yu H. F.","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_11_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2019.03.003"},{"key":"e_1_2_11_39_1","first-page":"5689","volume-title":"International Conference on Machine Learning","author":"Yoon J.","year":"2018"},{"key":"e_1_2_11_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/tcyb.2021.3053599"},{"key":"e_1_2_11_41_1","first-page":"1651","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Fortuin V.","year":"2020"},{"key":"e_1_2_11_42_1","article-title":"Diffusion\u2010Based Time Series Imputation and Forecasting With Structured State Space Models","author":"Alcaraz J. L.","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"e_1_2_11_43_1","unstructured":"S.Zhang S.Wang H.Miao H.Chen C.Fan andJ.Zhang \u201cScore\u2010CDM: Score\u2010Weighted Convolutional Diffusion Model for Multivariate Time Series Imputation \u201d preprint arXiv:2405.13075 (2024)."},{"key":"e_1_2_11_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671751"},{"key":"e_1_2_11_45_1","first-page":"1","volume-title":"25th International Joint Conference on Artificial Intelligence","author":"Yi X.","year":"2016"},{"key":"e_1_2_11_46_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1008618"},{"key":"e_1_2_11_47_1","first-page":"8857","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Rasul K.","year":"2021"},{"key":"e_1_2_11_48_1","doi-asserted-by":"publisher","DOI":"10.1198\/016214506000001437"},{"key":"e_1_2_11_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4684-9403-7_2"},{"key":"e_1_2_11_50_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467\u20109892.1982.tb00349.x"},{"key":"e_1_2_11_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7"},{"key":"e_1_2_11_52_1","first-page":"1","volume-title":"International Conference on Learning Representations","author":"Liu S.","year":"2022"},{"key":"e_1_2_11_53_1","first-page":"3094","volume-title":"28th International Joint Conference on Artificial Intelligence","author":"Luo Y.","year":"2019"},{"key":"e_1_2_11_54_1","first-page":"64","volume-title":"International Conference on Neural Information Processing","author":"Chen Y.","year":"2022"},{"key":"e_1_2_11_55_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-46677-9_13"},{"key":"e_1_2_11_56_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107217"},{"key":"e_1_2_11_57_1","first-page":"458","volume-title":"12th ACM International Conference on Future Energy Systems","author":"Kuppannagari S. R.","year":"2021"},{"key":"e_1_2_11_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3359275"},{"key":"e_1_2_11_59_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103462"},{"key":"e_1_2_11_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3690624.3709222"},{"key":"e_1_2_11_61_1","first-page":"8857","volume-title":"International Conference on Machine Learning","author":"Rasul K.","year":"2021"},{"key":"e_1_2_11_62_1","unstructured":"T.Yan H.Zhang T.Zhou Y.Zhan andY.Xia \u201cScoreGrad: Multivariate Probabilistic Time Series Forecasting With Continuous Energy\u2010Based Generative Models \u201d preprint arXiv:2106.10121 (2021)."},{"key":"e_1_2_11_63_1","first-page":"23009","article-title":"Generative Time Series Forecasting With Diffusion, Denoise, and Disentanglement","volume":"35","author":"Li Y.","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_11_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589132.3625614"},{"key":"e_1_2_11_65_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-46661-8_44"},{"key":"e_1_2_11_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3370918"},{"key":"e_1_2_11_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3371592"},{"key":"e_1_2_11_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2024.3389966"}],"container-title":["CAAI Transactions on Intelligence Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/cit2.70085","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/full-xml\/10.1049\/cit2.70085","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/cit2.70085","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T17:57:27Z","timestamp":1779386247000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/cit2.70085"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,16]]},"references-count":67,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["10.1049\/cit2.70085"],"URL":"https:\/\/doi.org\/10.1049\/cit2.70085","archive":["Portico"],"relation":{},"ISSN":["2468-6557","2468-2322"],"issn-type":[{"value":"2468-6557","type":"print"},{"value":"2468-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,16]]},"assertion":[{"value":"2024-09-06","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-22","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-16","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}