{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T20:18:18Z","timestamp":1783196298955,"version":"3.54.6"},"reference-count":33,"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\/501100010818","name":"Beijing Information Science and Technology University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010818","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003213","name":"Beijing Municipal Education Commission","doi-asserted-by":"publisher","award":["KM202411232023"],"award-info":[{"award-number":["KM202411232023"]}],"id":[{"id":"10.13039\/501100003213","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":[[2026,9]]},"DOI":"10.1016\/j.eswa.2026.132772","type":"journal-article","created":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T16:06:35Z","timestamp":1778169995000},"page":"132772","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["UniMAT: A multi-attention joint detection and tracking framework for robust multi-object tracking"],"prefix":"10.1016","volume":"326","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-9371-9566","authenticated-orcid":false,"given":"Junyao","family":"He","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7633-8532","authenticated-orcid":false,"given":"Wensheng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.132772_bib0001","doi-asserted-by":"crossref","DOI":"10.1016\/j.compag.2024.109564","article-title":"StraTracker: A dynamic counting method for growing strawberries based on multi-target tracking","volume":"227","author":"An","year":"2024","journal-title":"Computers and Electronics in Agriculture"},{"issue":"15","key":"10.1016\/j.eswa.2026.132772_bib0002","doi-asserted-by":"crossref","first-page":"9281","DOI":"10.3390\/su14159281","article-title":"Research on pedestrian detection and deepsort tracking in front of intelligent vehicle based on deep learning","volume":"14","author":"Chen","year":"2022","journal-title":"Sustainability"},{"issue":"11","key":"10.1016\/j.eswa.2026.132772_bib0003","doi-asserted-by":"crossref","first-page":"17218","DOI":"10.1109\/TITS.2024.3421339","article-title":"Deep learning-based robust multi-object tracking via fusion of mmwave radar and camera sensors","volume":"25","author":"Cheng","year":"2024","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"issue":"7","key":"10.1016\/j.eswa.2026.132772_bib0004","doi-asserted-by":"crossref","first-page":"7238","DOI":"10.1109\/LRA.2025.3575311","article-title":"HybridTrack: A hybrid approach for robust multi-object tracking","volume":"10","author":"Di Bella","year":"2025","journal-title":"IEEE Robotics and Automation Letters"},{"key":"10.1016\/j.eswa.2026.132772_bib0005","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2025.3639448","article-title":"Multi-target tracking for satellite videos guided by spatial-temporal proximity and topological relationships","volume":"63","author":"Hong","year":"2025","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"issue":"12","key":"10.1016\/j.eswa.2026.132772_bib0006","doi-asserted-by":"crossref","first-page":"21290","DOI":"10.1109\/JIOT.2025.3546639","article-title":"AHMOT: Adaptive Kalman filtering and hierarchical data association for 3D multi-object tracking in IoT-enabled autonomous vehicles","volume":"12","author":"Jiang","year":"2025","journal-title":"IEEE Internet of Things Journal"},{"key":"10.1016\/j.eswa.2026.132772_bib0007","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1016\/j.neucom.2022.04.087","article-title":"Multi-object tracking in traffic environments: A systematic literature review","volume":"494","author":"Jim\u00e9nez-Bravo","year":"2022","journal-title":"Neurocomputing"},{"key":"10.1016\/j.eswa.2026.132772_bib0008","doi-asserted-by":"crossref","DOI":"10.1016\/j.displa.2025.103229","article-title":"Graph-based joint detection and tracking with euclidean edges for multi-object video analysis","volume":"91","author":"Jlidi","year":"2026","journal-title":"Displays"},{"issue":"1","key":"10.1016\/j.eswa.2026.132772_bib0009","doi-asserted-by":"crossref","first-page":"974","DOI":"10.1109\/TITS.2024.3489234","article-title":"MCCA-MOT: Multimodal collaboration-guided cascade association network for 3D multi-object tracking","volume":"26","author":"Li","year":"2025","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"issue":"11","key":"10.1016\/j.eswa.2026.132772_bib0010","doi-asserted-by":"crossref","first-page":"4974","DOI":"10.1109\/TIV.2024.3508743","article-title":"A dynamic 3D multi-object tracking method based on spatiotemporal features","volume":"10","author":"Li","year":"2025","journal-title":"IEEE Transactions on Intelligent Vehicles"},{"issue":"2","key":"10.1016\/j.eswa.2026.132772_bib0011","doi-asserted-by":"crossref","first-page":"864","DOI":"10.1109\/TNNLS.2025.3613354","article-title":"Three-dimensional multiobject tracking based on voxel masking encoder and deep hashing paradigm","volume":"37","author":"Li","year":"2026","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"1","key":"10.1016\/j.eswa.2026.132772_bib0012","doi-asserted-by":"crossref","first-page":"1442","DOI":"10.1109\/TITS.2025.3625426","article-title":"3D multi-object tracking driven by multi-level association and intelligent filtering","volume":"27","author":"Liu","year":"2026","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"issue":"2","key":"10.1016\/j.eswa.2026.132772_bib0013","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":"International Journal of Computer Vision"},{"key":"10.1016\/j.eswa.2026.132772_bib0014","doi-asserted-by":"crossref","DOI":"10.1016\/j.artint.2020.103448","article-title":"Multiple object tracking: A literature review","volume":"293","author":"Luo","year":"2021","journal-title":"Artificial Intelligence"},{"key":"10.1016\/j.eswa.2026.132772_bib0015","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"8844","article-title":"TrackFormer: Multi-object tracking with transformers","author":"Meinhardt","year":"2022"},{"issue":"9","key":"10.1016\/j.eswa.2026.132772_bib0016","doi-asserted-by":"crossref","first-page":"6400","DOI":"10.1007\/s10489-021-02293-7","article-title":"Deep learning in multi-object detection and tracking: state of the art","volume":"51","author":"Pal","year":"2021","journal-title":"Applied Intelligence"},{"key":"10.1016\/j.eswa.2026.132772_bib0017","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"164","article-title":"Quasi-dense similarity learning for multiple object tracking","author":"Pang","year":"2021"},{"key":"10.1016\/j.eswa.2026.132772_bib0018","first-page":"1","article-title":"Self-attention-based transformer for nonlinear maneuvering target tracking","volume":"61","author":"Shen","year":"2023","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.eswa.2026.132772_bib0019","unstructured":"Sun, P., Cao, J., Jiang, Y., Zhang, R., Xie, E., Yuan, Z., Wang, C., & Luo, P. (2020). TransTrack: Multiple object tracking with transformer. arXiv preprint arXiv: 2012.15460."},{"key":"10.1016\/j.eswa.2026.132772_bib0020","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.107084","article-title":"CSCMOT: Multi-object tracking based on channel spatial cooperative attention mechanism","volume":"126","author":"Wang","year":"2023","journal-title":"Engineering Applications of Artificial Intelligence"},{"issue":"1","key":"10.1016\/j.eswa.2026.132772_bib0021","doi-asserted-by":"crossref","first-page":"284","DOI":"10.1109\/TASE.2022.3216450","article-title":"ST-TrackNet: A multiple-object tracking network using spatio-temporal information","volume":"21","author":"Wang","year":"2022","journal-title":"IEEE Transactions on Automation Science and Engineering"},{"issue":"6","key":"10.1016\/j.eswa.2026.132772_bib0022","doi-asserted-by":"crossref","first-page":"4735","DOI":"10.1109\/JIOT.2022.3219627","article-title":"Hybrid motion model for multiple object tracking in mobile devices","volume":"10","author":"Wu","year":"2022","journal-title":"IEEE Internet of Things Journal"},{"key":"10.1016\/j.eswa.2026.132772_bib0023","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106539","article-title":"MotionTrack: Learning motion predictor for multiple object tracking","volume":"179","author":"Xiao","year":"2024","journal-title":"Neural Networks"},{"issue":"6","key":"10.1016\/j.eswa.2026.132772_bib0024","doi-asserted-by":"crossref","first-page":"8079","DOI":"10.1109\/TII.2024.3366983","article-title":"Rethinking joint detection and embedding for multiobject tracking in multiscenario","volume":"20","author":"Xu","year":"2024","journal-title":"IEEE Transactions on Industrial Informatics"},{"key":"10.1016\/j.eswa.2026.132772_bib0025","series-title":"European conference on computer vision","first-page":"659","article-title":"MOTR: End-to-end multiple-object tracking with transformer","author":"Zeng","year":"2022"},{"key":"10.1016\/j.eswa.2026.132772_bib0026","doi-asserted-by":"crossref","DOI":"10.1016\/j.oceaneng.2023.116005","article-title":"Multi-target tracking algorithm in aquaculture monitoring based on deep learning","volume":"289","author":"Zhai","year":"2023","journal-title":"Ocean Engineering"},{"key":"10.1016\/j.eswa.2026.132772_bib0027","doi-asserted-by":"crossref","DOI":"10.1016\/j.oceaneng.2023.116005","article-title":"Multi-target tracking algorithm in aquaculture monitoring based on deep learning","volume":"289","author":"Zhai","year":"2023","journal-title":"Ocean Engineering"},{"key":"10.1016\/j.eswa.2026.132772_bib0028","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"5682","article-title":"Extracting motion and appearance via inter-frame attention for efficient video frame interpolation","author":"Zhang","year":"2023"},{"key":"10.1016\/j.eswa.2026.132772_bib0029","series-title":"European conference on computer vision","first-page":"1","article-title":"ByteTrack: Multi-object tracking by associating every detection box","author":"Zhang","year":"2022"},{"issue":"11","key":"10.1016\/j.eswa.2026.132772_bib0030","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":"International Journal of Computer Vision"},{"key":"10.1016\/j.eswa.2026.132772_bib0031","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"1647","article-title":"SaLM2: An extremely lightweight saliency mamba model for real-time cognitive awareness of driver attention","volume":"vol. 39","author":"Zhao","year":"2025"},{"key":"10.1016\/j.eswa.2026.132772_bib0032","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.110344","article-title":"Algorithm for surface flow velocity measurement in trunk canal based on improved YOLOv8 and deepSORT","volume":"148","author":"Zhou","year":"2025","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"10.1016\/j.eswa.2026.132772_bib0033","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., & Dai, J. (2020). Deformable DETR: Deformable transformers for end-to-end object detection. arXiv preprint arXiv: 2010.04159."}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426016854?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426016854?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T19:53:35Z","timestamp":1783194815000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426016854"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":33,"alternative-id":["S0957417426016854"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132772","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"UniMAT: A multi-attention joint detection and tracking framework for robust multi-object tracking","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132772","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":"132772"}}