{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T17:39:19Z","timestamp":1779385159835,"version":"3.53.1"},"reference-count":136,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12227901"],"award-info":[{"award-number":["12227901"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Stable Support for Youth Team in Basic Research Field, CAS","award":["YSBR-005"],"award-info":[{"award-number":["YSBR-005"]}]},{"name":"Academic Leaders Cultivation Program, USTC"},{"name":"Guangzhou-HKUST (GZ) Joint Funding Program","award":["2024A03J0620"],"award-info":[{"award-number":["2024A03J0620"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tpami.2026.3652303","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:00:30Z","timestamp":1768255230000},"page":"5474-5492","source":"Crossref","is-referenced-by-count":1,"title":["NuwaDynamics+: A Causality-Aware Generative Framework for Spatio-Temporal Representation Learning"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0602-169X","authenticated-orcid":false,"given":"Kun","family":"Wang","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5855-6847","authenticated-orcid":false,"given":"Yifan","family":"Duan","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0795-3790","authenticated-orcid":false,"given":"Hao","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3508-756X","authenticated-orcid":false,"given":"Jian","family":"Zhao","sequence":"additional","affiliation":[{"name":"China Telecom Institute of AI, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Wang","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4728-7347","authenticated-orcid":false,"given":"Zhengyang","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2817-7337","authenticated-orcid":false,"given":"Yuxuan","family":"Liang","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1492-3477","authenticated-orcid":false,"given":"Xu","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6079-7053","authenticated-orcid":false,"given":"Yang","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5224-4344","authenticated-orcid":false,"given":"Yu","family":"Zheng","sequence":"additional","affiliation":[{"name":"JD iCity, JD Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2924-946X","authenticated-orcid":false,"given":"Xuelong","family":"Li","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi&#x2019;an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2020.0097"},{"key":"ref2","article-title":"FourCastNet: A global data-driven high-resolution weather model using adaptive fourier neural operators","author":"Pathak","year":"2022"},{"key":"ref3","article-title":"Pangu-Weather: A 3D high-resolution model for fast and accurate global weather forecast","author":"Bi","year":"2022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10694-021-01109-x"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.105258"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijpe.2020.107868"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3333824"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29521"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0712"},{"key":"ref10","first-page":"75354","article-title":"LargeST: A benchmark dataset for large-scale traffic forecasting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Liu","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3690624.3709391"},{"key":"ref12","first-page":"37417","article-title":"Solving high-dimensional PDEs with latent spectral models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wu","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/s43586-021-00018-1"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11023-020-09548-1"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3149"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1515\/9781937585730"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.126.177701"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/1352-2310(95)00442-4"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1175\/1520-0450(1972)011<0312:NMOAAD>2.0.CO;2"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10915-022-01939-z"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2020.113250"},{"key":"ref24","article-title":"EuLagNet: Eulerian fluid prediction with lagrangian dynamics","author":"Ma","year":"2024","journal-title":"CoRR"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3293145"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00667-9"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01518"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681489"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/262"},{"key":"ref30","first-page":"30367","article-title":"ForkMerge: Mitigating negative transfer in auxiliary-task learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Jiang","year":"2023"},{"key":"ref31","article-title":"Transferability in deep learning: A survey","author":"Jiang","year":"2022"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3472291"},{"key":"ref33","first-page":"3208","article-title":"PDE-Net: Learning PDEs from data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Long","year":"2018"},{"key":"ref34","article-title":"Hamiltonian neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Greydanus","year":"2019"},{"key":"ref35","article-title":"PDE-driven spatiotemporal disentanglement","author":"Don\u00e0","year":"2020"},{"key":"ref36","article-title":"Invariant risk minimization","author":"Arjovsky","year":"2019"},{"key":"ref37","article-title":"Distributionally robust neural networks for group shifts: On the importance of regularization for worst-case generalization","author":"Sagawa","year":"2019"},{"key":"ref38","article-title":"The risks of invariant risk minimization","author":"Rosenfeld","year":"2020"},{"key":"ref39","first-page":"1448","article-title":"Invariant rationalization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chang","year":"2020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01657"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3505244"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"ref43","article-title":"DeepViT: Towards deeper vision transformer","author":"Zhou","year":"2021"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00020"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3089943"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511803161"},{"key":"ref48","volume-title":"The Book of Why: The New Science of Cause and Effect","author":"Pearl","year":"2018"},{"key":"ref49","first-page":"39","article-title":"Causal inference","volume-title":"Proc. Workshop Causality: Objectives Assessment NIPS 2008","volume":"6","author":"Pearl","year":"2010"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7687-1_79"},{"key":"ref51","article-title":"NuwaDynamics: Discovering and updating in causal spatio-temporal modeling","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Wang","year":"2024"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261988"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3361474"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3626235"},{"key":"ref55","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho","year":"2020"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref57","first-page":"881","article-title":"MADE: Masked autoencoder for distribution estimation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Germain","year":"2015"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765202"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3130191"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2023.05.010"},{"key":"ref62","article-title":"Convolutional LSTM network: A machine learning approach for precipitation nowcasting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Shi","year":"2015"},{"key":"ref63","article-title":"PredRNN: Recurrent neural networks for predictive learning using spatiotemporal lstms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.s","volume":"30","author":"Wang","year":"2017"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3165153"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00937"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.478"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/408"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00910"},{"key":"ref69","article-title":"Eidetic 3D LSTM: A model for video prediction and beyond","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2018"},{"key":"ref70","article-title":"CrevNet: Conditionally reversible video prediction","author":"Yu","year":"2019"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01149"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.14711\/thesis-991013340437803412"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-0912-1"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06221-2"},{"key":"ref76","article-title":"Neural ordinary differential equations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Chen","year":"2018"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1029\/2022JB024775"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.5194\/hess-26-5085-2022"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9682807"},{"key":"ref80","article-title":"Fourier neural operator for parametric partial differential equations","author":"Li","year":"2020"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1038\/s42254-021-00314-5"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-021-00302-5"},{"key":"ref83","first-page":"655","article-title":"Causal intervention for weakly-supervised semantic segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Zhang","year":"2020"},{"key":"ref84","article-title":"CoST: Contrastive learning of disentangled seasonal-trend representations for time series forecasting","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Woo","year":"2022"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449788"},{"key":"ref86","volume-title":"Models, Reasoning and Inference","volume":"19","author":"Pearl","year":"2000"},{"key":"ref87","article-title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","author":"Geirhos","year":"2018"},{"key":"ref88","first-page":"5637","article-title":"WILDS: A benchmark of in-the-wild distribution shifts","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Koh","year":"2021"},{"key":"ref89","article-title":"In search of lost domain generalization","author":"Gulrajani","year":"2020"},{"key":"ref90","first-page":"37765","article-title":"Discover and cure: Concept-aware mitigation of spurious correlation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wu","year":"2023"},{"key":"ref91","article-title":"Grad-CAM: Why did you say that?","author":"Selvaraju","year":"2016"},{"key":"ref92","first-page":"19620","article-title":"Parameterized explainer for graph neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Luo","year":"2020"},{"key":"ref93","article-title":"GNNExplainer: Generating explanations for graph neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Ying","year":"2019"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3342184"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.5244\/C.34.146"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539366"},{"key":"ref97","article-title":"Coping with label shift via distributionally robust optimisation","author":"Zhang","year":"2020"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.116"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3168"},{"key":"ref100","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref101","first-page":"13937","article-title":"DynamicViT: Efficient vision transformers with dynamic token sparsification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Rao","year":"2021"},{"key":"ref102","first-page":"24898","article-title":"IA-RED${^{2}}$2: Interpretability-aware redundancy reduction for vision transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Pan","year":"2021"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20202"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.4324\/9781315081656"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462971"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1016\/j.jjimei.2020.100004"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref110","article-title":"Text-to-image diffusion model in generative AI: A survey","author":"Zhang","year":"2023"},{"key":"ref111","article-title":"IP-Adapter: Text compatible image prompt adapter for text-to-image diffusion models","author":"Ye","year":"2023"},{"key":"ref112","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020"},{"key":"ref113","article-title":"Pseudo numerical methods for diffusion models on manifolds","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu","year":"2022"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0418"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-025-1562-4"},{"key":"ref116","article-title":"Classifier-free diffusion guidance","volume-title":"NeurIPS Workshop Deep Generative Models Downstream Appl.","author":"Ho","year":"2021"},{"key":"ref117","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Den","year":"2017"},{"key":"ref118","article-title":"Generating diverse high-fidelity images with VQ-VAE-2","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Razavi","year":"2019"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1214\/09-SS057"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.2202\/1557-4679.1203"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10735"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"ref123","first-page":"1596","article-title":"PDEBench: An extensive benchmark for scientific machine learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Takamoto","year":"2022"},{"key":"ref124","first-page":"22009","article-title":"SEVIR : A storm event imagery dataset for deep learning applications in radar and satellite meteorology","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Veillette","year":"2020"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1029\/2020MS002203"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1038\/s43588-022-00281-6"},{"key":"ref127","article-title":"Spatio-temporal twins with a cache for modeling long-term system dynamics","author":"Wu","year":"2024"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3162882"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681489"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671779"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00317"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.5194\/gmd-13-2631-2020"},{"key":"ref133","first-page":"10778","article-title":"Unsupervised transfer learning for spatiotemporal predictive networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yao","year":"2020"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.5194\/gmd-12-2797-2019"},{"key":"ref135","article-title":"Forecasting global weather with graph neural networks","author":"Keisler","year":"2022"},{"key":"ref136","first-page":"107604","article-title":"Causal deciphering and inpainting in spatio-temporal dynamics via diffusion model","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Duan","year":"2024"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11474534\/11342292.pdf?arnumber=11342292","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T19:56:12Z","timestamp":1775505372000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11342292\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":136,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3652303","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}