{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T01:25:38Z","timestamp":1781832338001,"version":"3.54.5"},"reference-count":54,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"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":["52575590"],"award-info":[{"award-number":["52575590"]}],"id":[{"id":"10.13039\/501100001809","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":[[2026,8]]},"DOI":"10.1016\/j.eswa.2026.132498","type":"journal-article","created":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T23:14:55Z","timestamp":1776294895000},"page":"132498","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["Enhancing rotational accuracy in deep learning-based visual-inertial odometry via geometric-aware representations and state-space fusion"],"prefix":"10.1016","volume":"323","author":[{"given":"Jiwei","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingchun","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0270-8285","authenticated-orcid":false,"given":"Peihao","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yantao","family":"Zong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.132498_bib0001","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/j.neunet.2022.03.005","article-title":"SelfVIO: Self-supervised deep monocular visual\u2013inertial odometry and depth estimation","volume":"150","author":"Almalioglu","year":"2022","journal-title":"Neural Networks"},{"key":"10.1016\/j.eswa.2026.132498_bib0002","doi-asserted-by":"crossref","first-page":"461","DOI":"10.1016\/j.neunet.2022.09.001","article-title":"Hvionet: A deep learning based hybrid visual\u2013inertial odometry approach for unmanned aerial system position estimation","volume":"155","author":"Aslan","year":"2022","journal-title":"Neural Networks"},{"issue":"6","key":"10.1016\/j.eswa.2026.132498_bib0003","doi-asserted-by":"crossref","first-page":"1874","DOI":"10.1109\/TRO.2021.3075644","article-title":"Orb-slam3: An accurate open-source library for visual, visual\u2013inertial, and multimap slam","volume":"37","author":"Campos","year":"2021","journal-title":"IEEE Transactions on Robotics"},{"key":"10.1016\/j.eswa.2026.132498_bib0004","unstructured":"Chen, C., Rosa, S., Lu, C. X., Trigoni, N., & Markham, A. (2019a). Selectfusion: A generic framework to selectively learn multisensory fusion. arXiv preprint arXiv: 1912.13077,."},{"key":"10.1016\/j.eswa.2026.132498_bib0005","series-title":"Cvf conference on computer vision and pattern recognition (cvpr)","first-page":"10542","article-title":"Selective sensor fusion for neural visual-inertial odometry. in 2019 IEEE","author":"Chen","year":"2019"},{"key":"10.1016\/j.eswa.2026.132498_bib0006","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"6646","article-title":"Projective manifold gradient layer for deep rotation regression","author":"Chen","year":"2022"},{"issue":"24","key":"10.1016\/j.eswa.2026.132498_bib0007","doi-asserted-by":"crossref","first-page":"3063","DOI":"10.3390\/electronics10243063","article-title":"An improved initialization method for monocular visual-inertial SLAM","volume":"10","author":"Cheng","year":"2021","journal-title":"Electronics"},{"key":"10.1016\/j.eswa.2026.132498_bib0008","series-title":"Proceedings of the AAAI conference on artificial intelligence","article-title":"Vinet: Visual-inertial odometry as a sequence-to-sequence learning problem","volume":"vol. 31","author":"Clark","year":"2017"},{"issue":"8","key":"10.1016\/j.eswa.2026.132498_bib0009","doi-asserted-by":"crossref","DOI":"10.1016\/j.asej.2022.102050","article-title":"Deep learning based on LSTM model for enhanced visual odometry navigation system","volume":"14","author":"Deraz","year":"2023","journal-title":"Ain Shams Engineering Journal"},{"key":"10.1016\/j.eswa.2026.132498_bib0010","doi-asserted-by":"crossref","first-page":"13959","DOI":"10.1109\/ACCESS.2025.3531667","article-title":"Transformer-based model for monocular visual odometry: a video understanding approach","volume":"13","author":"Fran\u00e7ani","year":"2025","journal-title":"IEEE Access"},{"key":"10.1016\/j.eswa.2026.132498_bib0011","series-title":"First conference on language modeling","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2024"},{"key":"10.1016\/j.eswa.2026.132498_bib0012","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"12175","article-title":"Cmt: Convolutional neural networks meet vision transformers","author":"Guo","year":"2022"},{"key":"10.1016\/j.eswa.2026.132498_bib0013","doi-asserted-by":"crossref","unstructured":"Han, L., Lin, Y., Du, G., & Lian, S.. Deepvio: Self-supervised deep learning of monocular visual inertial odometry using 3D geometric constraints. in 2019 IEEE. In Rsj international conference on intelligent robots and systems (IROS) (pp. 6906\u20136913).","DOI":"10.1109\/IROS40897.2019.8968467"},{"issue":"8","key":"10.1016\/j.eswa.2026.132498_bib0014","doi-asserted-by":"crossref","first-page":"618","DOI":"10.1007\/s11760-025-04145-0","article-title":"Crossformer3D: Cross spatio-temporal transformer for 3d human pose estimation","volume":"19","author":"Hassanin","year":"2025","journal-title":"Signal, Image and Video Processing"},{"issue":"1","key":"10.1016\/j.eswa.2026.132498_bib0015","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1007\/s00138-023-01488-x","article-title":"A stereo vision SLAM with moving vehicles tracking in outdoor environment","volume":"35","author":"Hong","year":"2024","journal-title":"Machine Vision and Applications"},{"issue":"7","key":"10.1016\/j.eswa.2026.132498_bib0016","doi-asserted-by":"crossref","first-page":"667","DOI":"10.1177\/0278364919853361","article-title":"Robocentric visual\u2013inertial odometry","volume":"41","author":"Huai","year":"2022","journal-title":"The International Journal of Robotics Research"},{"key":"10.1016\/j.eswa.2026.132498_bib0017","doi-asserted-by":"crossref","first-page":"17879","DOI":"10.1109\/TITS.2025.3550122","article-title":"Dynamic feature rejection based on geometric constraint for visual SLAM in autonomous driving","volume":"26","author":"Huang","year":"2025","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"issue":"4","key":"10.1016\/j.eswa.2026.132498_bib0018","doi-asserted-by":"crossref","first-page":"1166","DOI":"10.1109\/TIM.2003.815996","article-title":"Visual odometer for pedestrian navigation","volume":"52","author":"Jirawimut","year":"2003","journal-title":"IEEE Transactions on Instrumentation and measurement"},{"key":"10.1016\/j.eswa.2026.132498_bib0019","doi-asserted-by":"crossref","first-page":"2745","DOI":"10.1109\/JSTARS.2022.3158281","article-title":"A spectral-spatial feature extraction method with polydirectional CNN for multispectral image compression","volume":"15","author":"Kong","year":"2022","journal-title":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing"},{"key":"10.1016\/j.eswa.2026.132498_bib0020","doi-asserted-by":"crossref","first-page":"24087","DOI":"10.1109\/ACCESS.2023.3252884","article-title":"Scale-aware visual-inertial depth estimation and odometry using monocular self-supervised learning","volume":"11","author":"Lee","year":"2023","journal-title":"IEEE Access"},{"issue":"22","key":"10.1016\/j.eswa.2026.132498_bib0021","doi-asserted-by":"crossref","first-page":"37392","DOI":"10.1109\/JSEN.2024.3466851","article-title":"Monocular visual\u2013inertial odometer based on adaptive variational bayes algorithm","volume":"24","author":"Li","year":"2024","journal-title":"IEEE Sensors Journal"},{"key":"10.1016\/j.eswa.2026.132498_bib0022","doi-asserted-by":"crossref","first-page":"12341","DOI":"10.1109\/LRA.2025.3619774","article-title":"Tcb-vio: Tightly-coupled focal-plane binary-enhanced visual inertial odometry","volume":"10","author":"Lisondra","year":"2025","journal-title":"IEEE Robotics and Automation Letters"},{"key":"10.1016\/j.eswa.2026.132498_bib0023","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.111326","article-title":"Mamba model guided deep visual-inertial odometry","volume":"158","author":"Liu","year":"2025","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"10.1016\/j.eswa.2026.132498_bib0024","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.111326","article-title":"Mamba model guided deep visual-inertial odometry","volume":"158","author":"Liu","year":"2025","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"10.1016\/j.eswa.2026.132498_bib0025","series-title":"Icassp 2021-2021 ieee international conference on acoustics, speech and signal processing (icassp)","first-page":"4125","article-title":"Atvio: Attention guided visual-inertial odometry","author":"Liu","year":"2021"},{"issue":"1","key":"10.1016\/j.eswa.2026.132498_bib0026","doi-asserted-by":"crossref","first-page":"33","DOI":"10.3390\/machines13010033","article-title":"Resistance spot welding defect detection based on visual inspection: Improved faster r-CNN model","volume":"13","author":"Liu","year":"2025","journal-title":"Machines"},{"key":"10.1016\/j.eswa.2026.132498_bib0027","doi-asserted-by":"crossref","first-page":"505","DOI":"10.1109\/TNNLS.2025.3610435","article-title":"Vision mamba: A comprehensive survey and taxonomy","volume":"37","author":"Liu","year":"2025","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"6","key":"10.1016\/j.eswa.2026.132498_bib0028","doi-asserted-by":"crossref","first-page":"7478","DOI":"10.1109\/TNNLS.2022.3227717","article-title":"A survey of visual transformers","volume":"35","author":"Liu","year":"2023","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.eswa.2026.132498_bib0029","series-title":"2013 IEEE\/RSJ international conference on intelligent robots and systems","first-page":"3923","article-title":"A robust and modular multi-sensor fusion approach applied to MAV navigation","author":"Lynen","year":"2013"},{"key":"10.1016\/j.eswa.2026.132498_bib0030","series-title":"Proceedings of the european conference on computer vision (ECCV) workshops","article-title":"Analysis of the effect of sensors for end-to-end machine learning odometry","author":"Marquez Rodriguez-Peral","year":"2018"},{"issue":"2","key":"10.1016\/j.eswa.2026.132498_bib0031","doi-asserted-by":"crossref","first-page":"552","DOI":"10.3390\/s20020552","article-title":"Improving positioning accuracy via map matching algorithm for visual\u2013inertial odometer","volume":"20","author":"Meng","year":"2020","journal-title":"Sensors"},{"key":"10.1016\/j.eswa.2026.132498_bib0032","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"9903","article-title":"Gigapose: Fast and robust novel object pose estimation via one correspondence","author":"Nguyen","year":"2024"},{"key":"10.1016\/j.eswa.2026.132498_bib0033","series-title":"2024 IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"18019","article-title":"Adaptive vio: Deep visual-inertial odometry with online continual learning","author":"Pan","year":"2024"},{"issue":"12","key":"10.1016\/j.eswa.2026.132498_bib0034","doi-asserted-by":"crossref","first-page":"7682","DOI":"10.1109\/TPAMI.2024.3392941","article-title":"A survey on efficient vision transformers: algorithms, techniques, and performance benchmarking","volume":"46","author":"Papa","year":"2024","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.eswa.2026.132498_bib0035","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.111279","article-title":"Mamba-360: Survey of state space models as transformer alternative for long sequence modelling: Methods, applications, and challenges","volume":"159","author":"Patro","year":"2025","journal-title":"Engineering Applications of Artificial Intelligence"},{"issue":"3","key":"10.1016\/j.eswa.2026.132498_bib0036","doi-asserted-by":"crossref","first-page":"679","DOI":"10.1002\/rob.22487","article-title":"Visual inertial SLAM based on spatiotemporal consistency optimization in diverse environments","volume":"42","author":"Pu","year":"2025","journal-title":"Journal of Field Robotics"},{"issue":"9","key":"10.1016\/j.eswa.2026.132498_bib0037","doi-asserted-by":"crossref","first-page":"304","DOI":"10.3390\/jimaging11090304","article-title":"A comparative survey of vision transformers for feature extraction in texture analysis","volume":"11","author":"Scabini","year":"2025","journal-title":"Journal of Imaging"},{"key":"10.1016\/j.eswa.2026.132498_bib0038","series-title":"Proceedings of the 2018 IEEE\/RSJ international conference on intelligent robots and systems (IROS)","first-page":"2524","article-title":"Vision-Aided Absolute Trajectory Estimation Using an Unsupervised Deep Network with Online Error Correction","author":"Shamwell","year":"2018"},{"key":"10.1016\/j.eswa.2026.132498_bib0039","unstructured":"Shinde, K., Lee, J., Humt, M., Sezgin, A., & Triebel, R. (2020). Learning multiplicative interactions with bayesian neural networks for visual-inertial odometry. arXiv preprint arXiv: 2007.07630,."},{"issue":"21","key":"10.1016\/j.eswa.2026.132498_bib0040","doi-asserted-by":"crossref","first-page":"20877","DOI":"10.1109\/JSEN.2022.3208200","article-title":"Ema-vio: Deep visual\u2013inertial odometry with external memory attention","volume":"22","author":"Tu","year":"2022","journal-title":"IEEE Sensors Journal"},{"key":"10.1016\/j.eswa.2026.132498_bib0041","series-title":"Proceedings of the ieee\/cvf conference on computer vision and pattern recognition","first-page":"2464","article-title":"Covio: Online continual learning for visual-inertial odometry","author":"V\u00f6disch","year":"2023"},{"key":"10.1016\/j.eswa.2026.132498_bib0042","series-title":"2018 international conference on indoor positioning and indoor navigation (IPIN)","first-page":"1","article-title":"Lstm-based zero-velocity detection for robust inertial navigation","author":"Wagstaff","year":"2018"},{"key":"10.1016\/j.eswa.2026.132498_bib0043","first-page":"1","article-title":"Building extraction with vision transformer","volume":"60","author":"Wang","year":"2022","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.eswa.2026.132498_bib0044","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2025.112809","article-title":"A tightly-coupled dense monocular visual-inertial odometry system with lightweight depth estimation network","volume":"171","author":"Wang","year":"2025","journal-title":"Applied Soft Computing"},{"key":"10.1016\/j.eswa.2026.132498_bib0045","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.129178","article-title":"Is mamba effective for time series forecasting?","volume":"619","author":"Wang","year":"2025","journal-title":"Neurocomputing"},{"issue":"2","key":"10.1016\/j.eswa.2026.132498_bib0046","first-page":"449","article-title":"Cross-modal retrieval with CNN visual features: A new baseline","volume":"47","author":"Wei","year":"2016","journal-title":"IEEE Transactions on Cybernetics"},{"issue":"9","key":"10.1016\/j.eswa.2026.132498_bib0047","doi-asserted-by":"crossref","first-page":"2004","DOI":"10.3390\/s19092004","article-title":"An optimized tightly-coupled VIO design on the basis of the fused point and line features for patrol robot navigation","volume":"19","author":"Xia","year":"2019","journal-title":"Sensors"},{"key":"10.1016\/j.eswa.2026.132498_bib0048","first-page":"1","article-title":"Intermittently dynamic fuzzy learning-based tracking control of amplitude signals for vibratory gyroscopes with composite identification","volume":"74","author":"Xu","year":"2025","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"10.1016\/j.eswa.2026.132498_bib0049","doi-asserted-by":"crossref","first-page":"1859","DOI":"10.1109\/TNSE.2025.3540643","article-title":"Federated learning-based offset-free distributed control of nonlinear networked systems with application to IIot","volume":"12","author":"Xu","year":"2025","journal-title":"IEEE Transactions on Network Science and Engineering"},{"key":"10.1016\/j.eswa.2026.132498_bib0050","doi-asserted-by":"crossref","first-page":"20837","DOI":"10.1109\/TASE.2025.3608014","article-title":"Personalized federated learning-based distributed model predictive control with predictive error compensation for nonlinear networked systems","volume":"22","author":"Xu","year":"2025","journal-title":"IEEE Transactions on Automation Science and Engineering"},{"issue":"6","key":"10.1016\/j.eswa.2026.132498_bib0051","doi-asserted-by":"crossref","first-page":"6080","DOI":"10.1109\/TNSE.2024.3448609","article-title":"Category-guided graph convolution network for semantic segmentation","volume":"11","author":"Xu","year":"2024","journal-title":"IEEE Transactions on Network Science and Engineering"},{"issue":"18","key":"10.1016\/j.eswa.2026.132498_bib0052","doi-asserted-by":"crossref","first-page":"5737","DOI":"10.3390\/s25185737","article-title":"Rwkv-vio: An efficient and low-drift visual\u2013inertial odometry using an end-to-end deep network","volume":"25","author":"Yang","year":"2025","journal-title":"Sensors"},{"issue":"10","key":"10.1016\/j.eswa.2026.132498_bib0053","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3729420","article-title":"A survey of autonomous driving from a deep learning perspective","volume":"57","author":"Zhao","year":"2025","journal-title":"ACM Computing Surveys"},{"key":"10.1016\/j.eswa.2026.132498_bib0054","doi-asserted-by":"crossref","first-page":"863","DOI":"10.1109\/TIV.2024.3419101","article-title":"Tightly-coupled visual\/inertial\/map integration with observability analysis for reliable localization of intelligent vehicles","volume":"10","author":"Zheng","year":"2024","journal-title":"IEEE Transactions on Intelligent Vehicles"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426014119?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426014119?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T23:25:52Z","timestamp":1781738752000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426014119"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":54,"alternative-id":["S0957417426014119"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132498","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Enhancing rotational accuracy in deep learning-based visual-inertial odometry via geometric-aware representations and state-space fusion","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132498","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"132498"}}