{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T20:18:47Z","timestamp":1783714727443,"version":"3.55.0"},"reference-count":49,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62576165"],"award-info":[{"award-number":["62576165"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.knosys.2026.116543","type":"journal-article","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T06:37:13Z","timestamp":1782715033000},"page":"116543","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["STA: Spatio-temporal alignment for multimodal test-time adaptation"],"prefix":"10.1016","volume":"350","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-1692-7834","authenticated-orcid":false,"given":"Xiao-Long","family":"Yin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinlin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"De-Chuan","family":"Zhan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.116543_b1","doi-asserted-by":"crossref","unstructured":"Z. Guo, T. Jin, W. Xu, W. Lin, Y. Wu, From Question to Exploration: Can Classic Test-Time Adaptation Strategies Be Effectively Applied in Semantic Segmentation?, in: Proceedings of the 32nd ACM International Conference on Multimedia, 2024, pp. 10085\u201310094.","DOI":"10.1145\/3664647.3680910"},{"key":"10.1016\/j.knosys.2026.116543_b2","doi-asserted-by":"crossref","unstructured":"H. Cao, Y. Xu, J. Yang, P. Yin, X. Ji, S. Yuan, L. Xie, Mm-tta: multi-modal test-time adaptation for 3d semantic segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 16928\u201316937.","DOI":"10.1109\/ICCV51070.2023.01724"},{"key":"10.1016\/j.knosys.2026.116543_b3","doi-asserted-by":"crossref","unstructured":"W. Lin, M.J. Mirza, M. Kozinski, H. Possegger, H. Kuehne, H. Bischof, Video Test-Time Adaptation for Action Recognition, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 22952\u201322961.","DOI":"10.1109\/CVPR52729.2023.02198"},{"key":"10.1016\/j.knosys.2026.116543_b4","doi-asserted-by":"crossref","unstructured":"F. Azimi, S. Palacio, F. Raue, J. Hees, L. Bertinetto, A. Dengel, Self-Supervised Test-Time Adaptation on Video Data, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2022, pp. 3439\u20133448.","DOI":"10.1109\/WACV51458.2022.00266"},{"key":"10.1016\/j.knosys.2026.116543_b5","doi-asserted-by":"crossref","unstructured":"Z. Guo, T. Jin, W. Xu, W. Lin, Y. Wu, Bridging the Gap for Test-Time Multimodal Sentiment Analysis, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 39, 2025, pp. 16987\u201316995.","DOI":"10.1609\/aaai.v39i16.33867"},{"key":"10.1016\/j.knosys.2026.116543_b6","unstructured":"M. Yang, Y. Li, C. Zhang, P. Hu, X. Peng, Test-time Adaptation Against Multi-modal Reliability Bias, in: The Twelfth International Conference on Learning Representations, 2024."},{"key":"10.1016\/j.knosys.2026.116543_b7","doi-asserted-by":"crossref","unstructured":"Y. Zhao, J. Luo, X. Luo, J. Huang, J. Yuan, Z. Xiao, M. Zhang, Attention Bootstrapping for Multi-Modal Test-Time Adaptation, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 39, 2025, pp. 22849\u201322857.","DOI":"10.1609\/aaai.v39i21.34446"},{"key":"10.1016\/j.knosys.2026.116543_b8","series-title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","first-page":"6298","article-title":"Learning robust multi-view representation using dual-masked VAEs","author":"Wang","year":"2025"},{"key":"10.1016\/j.knosys.2026.116543_b9","series-title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","first-page":"5262","article-title":"Disentangling multi-view representations via curriculum learning with learnable prior","author":"Guo","year":"2025"},{"key":"10.1016\/j.knosys.2026.116543_b10","article-title":"Two-stream convolutional networks for action recognition in videos","volume":"27","author":"Simonyan","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116543_b11","doi-asserted-by":"crossref","unstructured":"J. Carreira, A. Zisserman, Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset, in: IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2017.","DOI":"10.1109\/CVPR.2017.502"},{"key":"10.1016\/j.knosys.2026.116543_b12","doi-asserted-by":"crossref","unstructured":"C. Feichtenhofer, H. Fan, J. Malik, K. He, SlowFast Networks for Video Recognition, in: IEEE International Conference on Computer Vision, ICCV, 2019.","DOI":"10.1109\/ICCV.2019.00630"},{"key":"10.1016\/j.knosys.2026.116543_b13","doi-asserted-by":"crossref","unstructured":"B. Jiang, M. Wang, W. Gan, W. Wu, J. Yan, Stm: Spatiotemporal and motion encoding for action recognition, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 2000\u20132009.","DOI":"10.1109\/ICCV.2019.00209"},{"key":"10.1016\/j.knosys.2026.116543_b14","series-title":"35th Conference on Neural Information Processing Systems","article-title":"Benchmarking the robustness of spatial-temporal models against corruptions","author":"Yi","year":"2021"},{"key":"10.1016\/j.knosys.2026.116543_b15","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"251","article-title":"Fully test-time adaptation for image segmentation","author":"Hu","year":"2021"},{"key":"10.1016\/j.knosys.2026.116543_b16","doi-asserted-by":"crossref","first-page":"122917","DOI":"10.52202\/079017-3906","article-title":"Cross-device collaborative test-time adaptation","volume":"37","author":"Chen","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116543_b17","doi-asserted-by":"crossref","first-page":"6204","DOI":"10.52202\/068431-0449","article-title":"Test time adaptation via conjugate pseudo-labels","volume":"35","author":"Goyal","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116543_b18","doi-asserted-by":"crossref","unstructured":"L. Zancato, A. Achille, T.Y. Liu, M. Trager, P. Perera, S. Soatto, Train\/Test-Time Adaptation with Retrieval, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 15911\u201315921.","DOI":"10.1109\/CVPR52729.2023.01527"},{"key":"10.1016\/j.knosys.2026.116543_b19","doi-asserted-by":"crossref","first-page":"74671","DOI":"10.52202\/075280-3264","article-title":"Efficient test-time adaptation for super-resolution with second-order degradation and reconstruction","volume":"36","author":"Deng","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116543_b20","series-title":"DELTA: Degradation-free fully test-time adaptation","author":"Zhao","year":"2023"},{"key":"10.1016\/j.knosys.2026.116543_b21","doi-asserted-by":"crossref","first-page":"38629","DOI":"10.52202\/068431-2799","article-title":"MEMO: Test time robustness via adaptation and augmentation","volume":"35","author":"Zhang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116543_b22","series-title":"SGEM: Test-time adaptation for automatic speech recognition via sequential-level generalized entropy minimization","author":"Kim","year":"2023"},{"key":"10.1016\/j.knosys.2026.116543_b23","doi-asserted-by":"crossref","unstructured":"Z. Gao, X.-Y. Zhang, C.-L. Liu, Unified Entropy Optimization for Open-Set Test-Time Adaptation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 23975\u201323984.","DOI":"10.1109\/CVPR52733.2024.02263"},{"key":"10.1016\/j.knosys.2026.116543_b24","doi-asserted-by":"crossref","unstructured":"J. Zhang, L. Qi, Y. Shi, Y. Gao, DomainAdaptor: A Novel Approach to Test-Time Adaptation, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 18971\u201318981.","DOI":"10.1109\/ICCV51070.2023.01739"},{"key":"10.1016\/j.knosys.2026.116543_b25","doi-asserted-by":"crossref","first-page":"2033","DOI":"10.1109\/TIP.2023.3258753","article-title":"Uncertainty-induced transferability representation for source-free unsupervised domain adaptation","volume":"32","author":"Pei","year":"2023","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.knosys.2026.116543_b26","doi-asserted-by":"crossref","unstructured":"M. Litrico, A.D. Bue, P. Morerio, Guiding Pseudo-Labels with Uncertainty Estimation for Source-Free Unsupervised Domain Adaptation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 7640\u20137650.","DOI":"10.1109\/CVPR52729.2023.00738"},{"key":"10.1016\/j.knosys.2026.116543_b27","doi-asserted-by":"crossref","unstructured":"Y. Su, X. Xu, K. Jia, Towards Real-World Test-Time Adaptation: Tri-Net Self-Training with Balanced Normalization, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 38, 2024, pp. 15126\u201315135.","DOI":"10.1609\/aaai.v38i13.29435"},{"key":"10.1016\/j.knosys.2026.116543_b28","doi-asserted-by":"crossref","unstructured":"Y. Wu, Z. Chi, Y. Wang, K.N. Plataniotis, S. Feng, Test-Time Domain Adaptation by Learning Domain-Aware Batch Normalization, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 38, 2024, pp. 15961\u201315969.","DOI":"10.1609\/aaai.v38i14.29527"},{"key":"10.1016\/j.knosys.2026.116543_b29","series-title":"MixNorm: Test-time adaptation through online normalization estimation","author":"Hu","year":"2021"},{"key":"10.1016\/j.knosys.2026.116543_b30","series-title":"Invariant test-time adaptation for vision-language model generalization","author":"Ma","year":"2024"},{"key":"10.1016\/j.knosys.2026.116543_b31","doi-asserted-by":"crossref","unstructured":"A.T. Nguyen, T. Nguyen-Tang, S.-N. Lim, P.H.S. Torr, TIPI: Test Time Adaptation With Transformation Invariance, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 24162\u201324171.","DOI":"10.1109\/CVPR52729.2023.02314"},{"key":"10.1016\/j.knosys.2026.116543_b32","series-title":"International Conference on Artificial Intelligence and Statistics","first-page":"3080","article-title":"MT3: Meta test-time training for self-supervised test-time adaptation","author":"Bartler","year":"2022"},{"key":"10.1016\/j.knosys.2026.116543_b33","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2021.102136","article-title":"Autoencoder based self-supervised test-time adaptation for medical image analysis","volume":"72","author":"He","year":"2021","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.knosys.2026.116543_b34","unstructured":"M. Prabhudesai, T.-W. Ke, A.C. Li, D. Pathak, K. Fragkiadaki, Test-Time Adaptation with Diffusion Models, in: ICML 2023 Workshop on Structured Probabilistic Inference & Generative Modeling, 2023."},{"key":"10.1016\/j.knosys.2026.116543_b35","doi-asserted-by":"crossref","first-page":"17567","DOI":"10.52202\/075280-0770","article-title":"Diffusion-TTA: Test-time adaptation of discriminative models via generative feedback","volume":"36","author":"Prabhudesai","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116543_b36","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2026.115867","article-title":"Learning from surprise: Fusing LLM-guided test-time adaptation for temporal knowledge graphs","author":"Bai","year":"2026","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116543_b37","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2026.115570","article-title":"DPC-TTA: Dual perturbation and correction network guided test-time adaptation","author":"Luo","year":"2026","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116543_b38","article-title":"A test-time adaptation method using evidential deep learning for online machinery fault diagnosis","author":"Tian","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116543_b39","unstructured":"J. Lei, F. Pernkopf, Two-Level Test-Time Adaptation in Multimodal Learning, in: ICML 2024 Workshop on Foundation Models in the Wild, 2024."},{"key":"10.1016\/j.knosys.2026.116543_b40","series-title":"Advances in multimodal adaptation and generalization: From traditional approaches to foundation models","author":"Dong","year":"2025"},{"issue":"1","key":"10.1016\/j.knosys.2026.116543_b41","first-page":"106","article-title":"Image steganography in color conversion","volume":"71","author":"Li","year":"2023","journal-title":"IEEE Trans. Circuits Syst. II: Express Briefs"},{"issue":"2","key":"10.1016\/j.knosys.2026.116543_b42","doi-asserted-by":"crossref","first-page":"1399","DOI":"10.1109\/TCSVT.2024.3466961","article-title":"Robust image steganography via color conversion","volume":"35","author":"Li","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"8","key":"10.1016\/j.knosys.2026.116543_b43","doi-asserted-by":"crossref","first-page":"5695","DOI":"10.1109\/TCSVT.2021.3138795","article-title":"Concealed attack for robust watermarking based on generative model and perceptual loss","volume":"32","author":"Li","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.knosys.2026.116543_b44","doi-asserted-by":"crossref","DOI":"10.1109\/TDSC.2025.3603570","article-title":"Encrypt a story: A video segment encryption method based on the discrete sinusoidal memristive rulkov neuron","author":"Gao","year":"2025","journal-title":"IEEE Trans. Dependable Secur. Comput."},{"issue":"1","key":"10.1016\/j.knosys.2026.116543_b45","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11263-010-0390-2","article-title":"A database and evaluation methodology for optical flow","volume":"92","author":"Baker","year":"2011","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.knosys.2026.116543_b46","series-title":"Lightmetry and Light and Optics in Biomedicine 2004","first-page":"42","article-title":"Colorfulness of the image: Definition, computation, and properties","volume":"Vol. 6158","author":"Palus","year":"2006"},{"key":"10.1016\/j.knosys.2026.116543_b47","unstructured":"D. Wang, E. Shelhamer, S. Liu, B. Olshausen, T. Darrell, Tent: Fully Test-time Adaptation by Entropy Minimization, in: International Conference on Learning Representations, ICLR, 2021."},{"key":"10.1016\/j.knosys.2026.116543_b48","series-title":"Proceedings of the 39th International Conference on Machine Learning","first-page":"16888","article-title":"Efficient test-time model adaptation without forgetting","author":"Niu","year":"2022"},{"key":"10.1016\/j.knosys.2026.116543_b49","series-title":"Towards stable test-time adaptation in dynamic wild world","author":"Niu","year":"2023"}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126012694?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126012694?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T19:53:16Z","timestamp":1783713196000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126012694"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":49,"alternative-id":["S0950705126012694"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116543","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"STA: Spatio-temporal alignment for multimodal test-time adaptation","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116543","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"116543"}}