{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T07:49:26Z","timestamp":1785829766650,"version":"3.56.0"},"reference-count":50,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Fusion"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.inffus.2026.104513","type":"journal-article","created":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T15:28:14Z","timestamp":1780327694000},"page":"104513","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["Motion estimation for multi-object tracking using KalmanNet with semantic-independent encoding"],"prefix":"10.1016","volume":"136","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-8891-5320","authenticated-orcid":false,"given":"Jian","family":"Song","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5736-189X","authenticated-orcid":false,"given":"Wei","family":"Mei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2674-3721","authenticated-orcid":false,"given":"Yunfeng","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3831-9856","authenticated-orcid":false,"given":"Qiang","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5893-3127","authenticated-orcid":false,"given":"Renke","family":"Kou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1056-9823","authenticated-orcid":false,"given":"Lina","family":"Bu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6328-5494","authenticated-orcid":false,"given":"Yucheng","family":"Long","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.inffus.2026.104513_bib0001","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102247","article-title":"Deep learning and multi-modal fusion for real-time multi-object tracking: algorithms, challenges, datasets, and comparative study","volume":"105","author":"Wang","year":"2024","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104513_bib0002","unstructured":"Z. Ge, S. Liu, F. Wang, Z. Li, J. Sun, YOLOX: exceeding YOLO series in 2021, 2021, 10.48550\/arXiv.2107.08430."},{"key":"10.1016\/j.inffus.2026.104513_bib0003","unstructured":"G. Jocher, J. Qiu, A. Chaurasia, Ultralytics YOLO, 2025, (Zenodo). 10.5281\/zenodo.15164670."},{"key":"10.1016\/j.inffus.2026.104513_bib0004","series-title":"2016 IEEE International Conference on Image Processing (ICIP)","first-page":"3464","article-title":"Simple online and realtime tracking","author":"Bewley","year":"2016"},{"key":"10.1016\/j.inffus.2026.104513_bib0005","series-title":"2017 IEEE International Conference on Image Processing (ICIP)","first-page":"3645","article-title":"Simple online and realtime tracking with a deep association metric","author":"Wojke","year":"2017"},{"key":"10.1016\/j.inffus.2026.104513_bib0006","series-title":"European Conference on Computer Vision (ECCV)","first-page":"1","article-title":"ByteTrack: multi-object tracking by associating every detection box","volume":"13682","author":"Zhang","year":"2022"},{"key":"10.1016\/j.inffus.2026.104513_bib0007","unstructured":"N. Aharon, R. Orfaig, B.-Z. Bobrovsky, BoT-SORT: robust associations multi-pedestrian tracking, 2022. arXiv: 2206.14651 [cs]."},{"key":"10.1016\/j.inffus.2026.104513_bib0008","doi-asserted-by":"crossref","first-page":"8725","DOI":"10.1109\/TMM.2023.3240881","article-title":"StrongSORT: make DeepSORT great again","volume":"25","author":"Du","year":"2023","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.inffus.2026.104513_bib0009","series-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"9686","article-title":"Observation-centric SORT: rethinking SORT for robust multi-object tracking","author":"Cao","year":"2023"},{"key":"10.1016\/j.inffus.2026.104513_bib0010","unstructured":"A. Milan, L. Leal-Taixe, I. Reid, S. Roth, K. Schindler, MOT16: a benchmark for multi-object tracking, 2016. 10.48550\/arXiv.1603.00831."},{"key":"10.1016\/j.inffus.2026.104513_bib0011","unstructured":"P. Dendorfer, H. Rezatofighi, A. Milan, J. Shi, D. Cremers, I. Reid, S. Roth, K. Schindler, L. Leal-Taix\u00e9, MOT20: a benchmark for multi object tracking in crowded scenes, 2020. 10.48550\/arXiv.2003.09003."},{"key":"10.1016\/j.inffus.2026.104513_bib0012","series-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","first-page":"3490","article-title":"SoccerNet-tracking: multiple object tracking dataset and benchmark in soccer videos","author":"Cioppa","year":"2022"},{"key":"10.1016\/j.inffus.2026.104513_bib0013","series-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"20961","article-title":"DanceTrack: multi-object tracking in uniform appearance and diverse motion","author":"Sun","year":"2022"},{"issue":"5","key":"10.1016\/j.inffus.2026.104513_bib0014","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1109\/JPROC.2023.3247480","article-title":"Model-based deep learning","volume":"111","author":"Shlezinger","year":"2023","journal-title":"Proc. IEEE"},{"key":"10.1016\/j.inffus.2026.104513_bib0015","series-title":"Proceedings of the 36th International Conference on Machine Learning","first-page":"544","article-title":"Recurrent Kalman networks: factorized inference in high-dimensional deep feature spaces","author":"Becker","year":"2019"},{"key":"10.1016\/j.inffus.2026.104513_bib0016","series-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"4918","article-title":"KFNet: learning temporal camera relocalization using Kalman filtering","author":"Zhou","year":"2020"},{"issue":"12","key":"10.1016\/j.inffus.2026.104513_bib0017","doi-asserted-by":"crossref","first-page":"5479","DOI":"10.1109\/TNNLS.2021.3112460","article-title":"DynaNet: neural Kalman dynamical model for motion estimation and prediction","volume":"32","author":"Chen","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.inffus.2026.104513_bib0018","doi-asserted-by":"crossref","first-page":"1532","DOI":"10.1109\/TSP.2022.3158588","article-title":"KalmanNet: neural network aided Kalman filtering for partially known dynamics","volume":"70","author":"Revach","year":"2022","journal-title":"IEEE Trans. Signal Process."},{"key":"10.1016\/j.inffus.2026.104513_bib0019","series-title":"International Conference on Learning Representations","article-title":"A time series is worth 64 words: long-term forecasting with transformers","author":"Nie","year":"2023"},{"key":"10.1016\/j.inffus.2026.104513_bib0020","series-title":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","first-page":"1185","article-title":"DUET: dual clustering enhanced multivariate time series forecasting","author":"Qiu","year":"2025"},{"key":"10.1016\/j.inffus.2026.104513_bib0021","doi-asserted-by":"crossref","first-page":"1890","DOI":"10.1109\/LSP.2024.3431443","article-title":"Practical implementation of KalmanNet for accurate data fusion in integrated navigation","volume":"31","author":"Song","year":"2024","journal-title":"IEEE Signal Process. Lett."},{"issue":"6","key":"10.1016\/j.inffus.2026.104513_bib0022","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1109\/MCS.2009.934469","article-title":"The probabilistic data association filter","volume":"29","author":"Bar-Shalom","year":"2009","journal-title":"IEEE Control Syst. Mag."},{"key":"10.1016\/j.inffus.2026.104513_bib0023","series-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"164","article-title":"Quasi-dense similarity learning for multiple object tracking","author":"Pang","year":"2021"},{"key":"10.1016\/j.inffus.2026.104513_bib0024","doi-asserted-by":"crossref","first-page":"3069","DOI":"10.1007\/s11263-021-01513-4","article-title":"FairMOT: on the fairness of detection and re-identification in multiple object tracking","volume":"129","author":"Zhang","year":"2021","journal-title":"Int. J. Comput. Vis."},{"issue":"16","key":"10.1016\/j.inffus.2026.104513_bib0025","doi-asserted-by":"crossref","first-page":"4165","DOI":"10.1109\/TSP.2015.2424194","article-title":"Extended target tracking using gaussian processes","volume":"63","author":"Wahlstrom","year":"2015","journal-title":"IEEE Trans. Signal Process."},{"key":"10.1016\/j.inffus.2026.104513_bib0026","series-title":"An approach to target tracking","author":"Gruber","year":"1967"},{"key":"10.1016\/j.inffus.2026.104513_bib0027","series-title":"Defense, Security, and Sensing","article-title":"New extension of the Kalman filter to nonlinear systems","author":"Julier","year":"1997"},{"issue":"2","key":"10.1016\/j.inffus.2026.104513_bib0028","first-page":"107","article-title":"Novel approach to nonlinear\/non-Gaussian Bayesian state estimation","volume":"140","author":"Gordon","year":"1993","journal-title":"IEE Proc. F"},{"key":"10.1016\/j.inffus.2026.104513_bib0029","series-title":"2021 IEEE 24th International Conference on Information Fusion, FUSION","first-page":"1","article-title":"An IMM-enabled adaptive 3D multi-object tracker for autonomous driving","author":"Liu","year":"2021"},{"key":"10.1016\/j.inffus.2026.104513_bib0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.jvcir.2024.104064","article-title":"Multiple object tracking with segmentation and interactive multiple model","volume":"99","author":"Qi","year":"2024","journal-title":"J. Visual Commun. Image Represent."},{"key":"10.1016\/j.inffus.2026.104513_bib0031","series-title":"Proceedings Advances in Neural Information Processing Systems","first-page":"3604","article-title":"A disentangled recognition and nonlinear dynamics model for unsupervised learning","volume":"30","author":"Fraccaro","year":"2017"},{"key":"10.1016\/j.inffus.2026.104513_bib0032","series-title":"Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence","first-page":"2101","article-title":"Structured inference networks for nonlinear state space models","author":"Krishnan","year":"2017"},{"issue":"3","key":"10.1016\/j.inffus.2026.104513_bib0033","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1109\/MSP.2025.3569395","article-title":"Artificial intelligence-aided Kalman filters: AI-augmented designs for Kalman-type algorithms","volume":"42","author":"Shlezinger","year":"2025","journal-title":"IEEE Signal Process. Mag."},{"key":"10.1016\/j.inffus.2026.104513_bib0034","series-title":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"1","article-title":"KalmanBOT: KalmanNet-aided bollinger bands for pairs trading","author":"Deng","year":"2023"},{"key":"10.1016\/j.inffus.2026.104513_bib0035","first-page":"1","article-title":"Moving magnetic target localization using automatically initialized KalmanNet driven by euler deconvolution","volume":"22","author":"Zhao","year":"2025","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"10.1016\/j.inffus.2026.104513_bib0036","doi-asserted-by":"crossref","first-page":"352","DOI":"10.1109\/TSP.2023.3344360","article-title":"Latent-KalmanNet: learned Kalman filtering for tracking from high-Dimensional signals","volume":"72","author":"Buchnik","year":"2024","journal-title":"IEEE Trans. Signal Process."},{"key":"10.1016\/j.inffus.2026.104513_bib0037","doi-asserted-by":"crossref","first-page":"3700","DOI":"10.1109\/TSP.2024.3435935","article-title":"GSP-KalmanNet: tracking graph signals via neural-Aided Kalman filtering","volume":"72","author":"Buchnik","year":"2024","journal-title":"IEEE Trans. Signal Process."},{"key":"10.1016\/j.inffus.2026.104513_bib0038","doi-asserted-by":"crossref","first-page":"2558","DOI":"10.1109\/TSP.2025.3581703","article-title":"Bayesian KalmanNet: quantifying uncertainty in deep learning augmented Kalman filter","volume":"73","author":"Dahan","year":"2025","journal-title":"IEEE Trans. Signal Process."},{"key":"10.1016\/j.inffus.2026.104513_bib0039","series-title":"2023 31st European Signal Processing Conference (EUSIPCO)","first-page":"870","article-title":"DANSE: data-driven non-linear state estimation of model-free process in unsupervised Bayesian setup","author":"Ghosh","year":"2023"},{"key":"10.1016\/j.inffus.2026.104513_bib0040","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102750","article-title":"IFNet: data-driven multisensor estimate fusion with unknown correlation in sensor measurement noises","volume":"115","author":"Wang","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104513_bib0041","series-title":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","first-page":"1267","article-title":"IMMNN: robust wireless electromagnetic-inertial fusion tracking via learning an adaptive IMM","author":"Lin","year":"2025"},{"issue":"9","key":"10.1016\/j.inffus.2026.104513_bib0042","doi-asserted-by":"crossref","first-page":"12326","DOI":"10.1109\/TVT.2023.3270353","article-title":"Split-KalmanNet: a robust model-based deep learning approach for state estimation","volume":"72","author":"Choi","year":"2023","journal-title":"IEEE Trans. Veh. Technol."},{"key":"10.1016\/j.inffus.2026.104513_bib0043","unstructured":"S. Bai, J.Z. Kolter, V. Koltun, An empirical evaluation of generic convolutional and recurrent networks for sequence modeling, 2018. 10.48550\/arXiv.1803.01271."},{"key":"10.1016\/j.inffus.2026.104513_bib0044","series-title":"2015 IEEE International Conference on Computer Vision, ICCV","first-page":"1440","article-title":"Fast R-CNN","author":"Girshick","year":"2015"},{"key":"10.1016\/j.inffus.2026.104513_bib0045","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2008\/246309","article-title":"Evaluating multiple object tracking performance: the CLEAR MOT metrics","volume":"2008","author":"Bernardin","year":"2008","journal-title":"EURASIP J. Image Video Process."},{"issue":"2","key":"10.1016\/j.inffus.2026.104513_bib0046","doi-asserted-by":"crossref","first-page":"548","DOI":"10.1007\/s11263-020-01375-2","article-title":"HOTA: a higher order metric for evaluating multi-object tracking","volume":"129","author":"Luiten","year":"2021","journal-title":"Int. J. Comput. Vis."},{"issue":"4","key":"10.1016\/j.inffus.2026.104513_bib0047","doi-asserted-by":"crossref","first-page":"814","DOI":"10.1109\/TPAMI.2015.2465908","article-title":"What makes for effective detection proposals?","volume":"38","author":"Hosang","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.inffus.2026.104513_bib0048","doi-asserted-by":"crossref","first-page":"165103","DOI":"10.1109\/ACCESS.2019.2953276","article-title":"Online multi-object tracking with GMPHD filter and occlusion group management","volume":"7","author":"Song","year":"2019","journal-title":"IEEE Access"},{"key":"10.1016\/j.inffus.2026.104513_bib0049","unstructured":"M. Chaabane, P. Zhang, J.R. Beveridge, S. O\u2019Hara, DEFT: detection embeddings for tracking, 2021, 10.48550\/arXiv.2102.02267."},{"key":"10.1016\/j.inffus.2026.104513_bib0050","unstructured":"B. Hu, R. Luo, Z. Liu, C. Wang, W. Liu, TrackSSM: a general motion predictor by state-space model, 2024. 10.48550\/arXiv.2409.00487."}],"container-title":["Information Fusion"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253526003921?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253526003921?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T07:34:30Z","timestamp":1785828870000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1566253526003921"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":50,"alternative-id":["S1566253526003921"],"URL":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104513","relation":{},"ISSN":["1566-2535"],"issn-type":[{"value":"1566-2535","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Motion estimation for multi-object tracking using KalmanNet with semantic-independent encoding","name":"articletitle","label":"Article Title"},{"value":"Information Fusion","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104513","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":"104513"}}