{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T01:02:54Z","timestamp":1782522174852,"version":"3.54.5"},"reference-count":38,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T00:00:00Z","timestamp":1768780800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100023758","name":"Fachhochschule S\u00fcdwestfalen","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100023758","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1016\/j.eswa.2026.131270","type":"journal-article","created":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T00:19:58Z","timestamp":1768868398000},"page":"131270","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":3,"special_numbering":"C","title":["Lipschitz-controlled attention fusion for stable multimodal autoencoders in industrial robotics and manufacturing"],"prefix":"10.1016","volume":"310","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-7928-5874","authenticated-orcid":false,"given":"Diyar","family":"Altinses","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8405-0977","authenticated-orcid":false,"given":"Andreas","family":"Schwung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.131270_bib0001","series-title":"Iecon 2023-49th annual conference of the ieee industrial electronics society","first-page":"1","article-title":"Deep multimodal fusion with corrupted spatio-temporal data using fuzzy regularization","author":"Altinses","year":"2023"},{"key":"10.1016\/j.eswa.2026.131270_bib0002","series-title":"Iecon 2023-49th annual conference of the ieee industrial electronics society","first-page":"1","article-title":"Multimodal synthetic dataset balancing: A framework for realistic and balanced training data generation in industrial settings","author":"Altinses","year":"2023"},{"key":"10.1016\/j.eswa.2026.131270_bib0003","doi-asserted-by":"crossref","DOI":"10.1016\/j.mlwa.2025.100691","article-title":"Performance benchmarking of multimodal data-driven approaches in industrial settings","volume":"21","author":"Altinses","year":"2025","journal-title":"Machine Learning with Applications"},{"key":"10.1016\/j.eswa.2026.131270_bib0004","unstructured":"Arevalo, J., Solorio, T., Montes-y G\u00f3mez, M., & Gonz\u00e1lez, F. A. (2017). Gated multimodal units for information fusion. arXiv: 1702.01992."},{"key":"10.1016\/j.eswa.2026.131270_bib0005","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1007\/s00530-010-0182-0","article-title":"Multimodal fusion for multimedia analysis: A survey","volume":"16","author":"Atrey","year":"2010","journal-title":"Multimedia Systems"},{"issue":"2","key":"10.1016\/j.eswa.2026.131270_bib0006","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","article-title":"Multimodal machine learning: A survey and taxonomy","volume":"41","author":"Baltru\u0161aitis","year":"2018","journal-title":"IEEE Transactions on Pattern Analysis And Machine Intelligence"},{"key":"10.1016\/j.eswa.2026.131270_bib0007","doi-asserted-by":"crossref","first-page":"14804","DOI":"10.1109\/ACCESS.2023.3243854","article-title":"A systematic literature review on multimodal machine learning: Applications, challenges, gaps and future directions","volume":"11","author":"Barua","year":"2023","journal-title":"IEEE Access"},{"issue":"1","key":"10.1016\/j.eswa.2026.131270_bib0008","doi-asserted-by":"crossref","first-page":"326","DOI":"10.1038\/s41597-025-04636-2","article-title":"Robomnist: A multimodal dataset for multi-robot activity recognition using wifi sensing, video, and audio","volume":"12","author":"Behzad","year":"2025","journal-title":"Scientific Data"},{"key":"10.1016\/j.eswa.2026.131270_bib0009","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2021.114820","article-title":"Machine learning for industrial applications: A comprehensive literature review","volume":"175","author":"Bertolini","year":"2021","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.131270_bib0010","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","article-title":"Multi-level variational autoencoder: Learning disentangled representations from grouped observations","volume":"32","author":"Bouchacourt","year":"2018"},{"issue":"8","key":"10.1016\/j.eswa.2026.131270_bib0011","doi-asserted-by":"crossref","first-page":"2350","DOI":"10.3390\/s20082350","article-title":"Choosing the best sensor fusion method: A machine-learning approach","volume":"20","author":"Brena","year":"2020","journal-title":"Sensors"},{"key":"10.1016\/j.eswa.2026.131270_bib0012","series-title":"2017 IEEE symposium on security and privacy (sp)","first-page":"39","article-title":"Towards evaluating the robustness of neural networks","author":"Carlini","year":"2017"},{"key":"10.1016\/j.eswa.2026.131270_bib0013","series-title":"2020\u202fIEEE 23rd international conference on information fusion (FUSION)","first-page":"1","article-title":"Early vs late fusion in multimodal convolutional neural networks","author":"Gadzicki","year":"2020"},{"key":"10.1016\/j.eswa.2026.131270_bib0014","doi-asserted-by":"crossref","first-page":"393","DOI":"10.1007\/s10994-020-05929-w","article-title":"Regularisation of neural networks by enforcing lipschitz continuity","volume":"110","author":"Gouk","year":"2021","journal-title":"Machine Learning"},{"key":"10.1016\/j.eswa.2026.131270_bib0015","first-page":"57","article-title":"Application of machine learning in industry 4.0","author":"Gourisaria","year":"2021","journal-title":"Machine Learning: Theoretical Foundations and Practical Applications"},{"key":"10.1016\/j.eswa.2026.131270_bib0016","series-title":"Computer vision\u2013ACCV 2016: 13th asian conference on computer vision, taipei, taiwan, november 20\u201324, 2016, revised selected papers, part i 13","first-page":"213","article-title":"Fusenet: Incorporating depth into semantic segmentation via fusion-based cnn architecture","author":"Hazirbas","year":"2017"},{"key":"10.1016\/j.eswa.2026.131270_bib0017","series-title":"Proceedings of the IEEE international conference on computer vision","first-page":"4193","article-title":"Attention-based multimodal fusion for video description","author":"Hori","year":"2017"},{"key":"10.1016\/j.eswa.2026.131270_bib0018","series-title":"Proceedings of the advances in neural information processing systems","first-page":"1564","article-title":"Bilinear attention networks","volume":"vol. 31","author":"Kim","year":"2018"},{"key":"10.1016\/j.eswa.2026.131270_bib0019","series-title":"International conference on artificial intelligence and statistics","first-page":"2507","article-title":"Lipschitz continuous autoencoders in application to anomaly detection","author":"Kim","year":"2020"},{"issue":"11","key":"10.1016\/j.eswa.2026.131270_bib0020","doi-asserted-by":"crossref","first-page":"1105","DOI":"10.3390\/machines10111105","article-title":"A deep-learning-based multi-modal sensor fusion approach for detection of equipment faults","volume":"10","author":"Kullu","year":"2022","journal-title":"Machines"},{"key":"10.1016\/j.eswa.2026.131270_bib0021","doi-asserted-by":"crossref","first-page":"74762","DOI":"10.1109\/ACCESS.2018.2884793","article-title":"Towards robust human-robot collaborative manufacturing: Multimodal fusion","volume":"6","author":"Liu","year":"2018","journal-title":"IEEE Access"},{"issue":"2","key":"10.1016\/j.eswa.2026.131270_bib0022","doi-asserted-by":"crossref","first-page":"715","DOI":"10.1109\/TCDS.2021.3071170","article-title":"Comparing recognition performance and robustness of multimodal deep learning models for multimodal emotion recognition","volume":"14","author":"Liu","year":"2021","journal-title":"IEEE Transactions on Cognitive and Developmental Systems"},{"issue":"3","key":"10.1016\/j.eswa.2026.131270_bib0023","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TII.2018.2793246","article-title":"Deep coupling autoencoder for fault diagnosis with multimodal sensory data","volume":"14","author":"Ma","year":"2018","journal-title":"IEEE Transactions on Industrial Informatics"},{"key":"10.1016\/j.eswa.2026.131270_bib0024","series-title":"International conference on machine learning","first-page":"7325","article-title":"Stability and convergence of stochastic gradient clipping: Beyond lipschitz continuity and smoothness","author":"Mai","year":"2021"},{"key":"10.1016\/j.eswa.2026.131270_bib0025","series-title":"Proceedings of the 28th international conference on machine learning (ICML-11)","first-page":"689","article-title":"Multimodal deep learning","author":"Ngiam","year":"2011"},{"issue":"3","key":"10.1016\/j.eswa.2026.131270_bib0026","doi-asserted-by":"crossref","first-page":"602","DOI":"10.1137\/22M1527210","article-title":"Gradient descent in the absence of global lipschitz continuity of the gradients","volume":"6","author":"Patel","year":"2024","journal-title":"SIAM Journal on Mathematics of Data Science"},{"key":"10.1016\/j.eswa.2026.131270_bib0027","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"1944","article-title":"Making deep neural networks robust to label noise: A loss correction approach","author":"Patrini","year":"2017"},{"key":"10.1016\/j.eswa.2026.131270_bib0028","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1109\/LCSYS.2021.3050444","article-title":"Training robust neural networks using lipschitz bounds","volume":"6","author":"Pauli","year":"2021","journal-title":"IEEE Control Systems Letters"},{"issue":"6","key":"10.1016\/j.eswa.2026.131270_bib0029","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1109\/MSP.2017.2738401","article-title":"Deep multimodal learning: A survey on recent advances and trends","volume":"34","author":"Ramachandram","year":"2017","journal-title":"IEEE Signal Processing Magazine"},{"key":"10.1016\/j.eswa.2026.131270_bib0030","series-title":"Advances in neural information processing systems","article-title":"Multimodal learning with deep boltzmann machines","volume":"25","author":"Srivastava","year":"2012"},{"key":"10.1016\/j.eswa.2026.131270_bib0031","unstructured":"Suzuki, M., Nakayama, K., & Matsuo, Y. (2016). Joint multimodal learning with deep generative models. arXiv: 1611.01891."},{"key":"10.1016\/j.eswa.2026.131270_bib0032","series-title":"Proceedings of the conference. association for computational linguistics. meeting","first-page":"6558","article-title":"Multimodal transformer for unaligned multimodal language sequences","volume":"vol. 2019","author":"Tsai","year":"2019"},{"key":"10.1016\/j.eswa.2026.131270_bib0033","series-title":"Advances in neural information processing systems","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.eswa.2026.131270_bib0034","article-title":"Lipschitz regularity of deep neural networks: analysis and efficient estimation","volume":"31","author":"Virmaux","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.131270_bib0035","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"8032","article-title":"Multimodal industrial anomaly detection via hybrid fusion","author":"Wang","year":"2023"},{"key":"10.1016\/j.eswa.2026.131270_bib0036","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"2335","article-title":"Aligning latent spaces for 3d hand pose estimation","author":"Yang","year":"2019"},{"key":"10.1016\/j.eswa.2026.131270_bib0037","series-title":"Proceedings of the 2017 conference on empirical methods in natural language processing","first-page":"1103","article-title":"Tensor fusion network for multimodal sentiment analysis","author":"Zadeh","year":"2017"},{"key":"10.1016\/j.eswa.2026.131270_bib0038","series-title":"International conference on machine learning","first-page":"7584","article-title":"Lipschitz generative adversarial nets","author":"Zhou","year":"2019"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426001831?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426001831?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T12:23:19Z","timestamp":1775305399000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426001831"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":38,"alternative-id":["S0957417426001831"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.131270","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,5]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Lipschitz-controlled attention fusion for stable multimodal autoencoders in industrial robotics and manufacturing","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.131270","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"131270"}}