{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T16:40:32Z","timestamp":1781282432556,"version":"3.54.1"},"reference-count":67,"publisher":"Springer Science and Business Media LLC","issue":"16","license":[{"start":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T00:00:00Z","timestamp":1761868800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T00:00:00Z","timestamp":1761868800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Transportation Technology Project of Shanxi Province","award":["23-09X"],"award-info":[{"award-number":["23-09X"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"DOI":"10.1007\/s11227-025-07991-4","type":"journal-article","created":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T16:47:55Z","timestamp":1761929275000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Multi-vehicle tracking in highway roadside surveillance videos via spatial\u2013temporal fusion network with adaptive decay memory"],"prefix":"10.1007","volume":"81","author":[{"given":"Xuan","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chihang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingpeng","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyi","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhao","family":"Deng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,10,31]]},"reference":[{"issue":"11","key":"7991_CR1","doi-asserted-by":"publisher","first-page":"3069","DOI":"10.1007\/s11263-021-01513-4","volume":"129","author":"YF Zhang","year":"2021","unstructured":"Zhang YF, Wang CY, Wang XG et al (2021) FairMOT: on the fairness of detection and re-identification in multiple object tracking. Int J Comput Vis 129(11):3069\u20133087. https:\/\/doi.org\/10.1007\/s11263-021-01513-4","journal-title":"Int J Comput Vis"},{"key":"7991_CR2","doi-asserted-by":"publisher","unstructured":"Zhang YF, Sun PZ, Jiang Y et al (2002) ByteTrack: multi-object tracking by associating every detection box. In: Proceedings of the European Conference on Computer Vision (ECCV), pp 1\u201321. https:\/\/doi.org\/10.1007\/978-3-031-20047-2_1","DOI":"10.1007\/978-3-031-20047-2_1"},{"key":"7991_CR3","doi-asserted-by":"publisher","unstructured":"Cao J, Pang J, Weng X, Khirodkar R, Kitani K (2023) Observationcentric SORT: rethinking SORT for robust multi-object tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 9686\u20139696. https:\/\/doi.org\/10.1109\/CVPR52729.2023.00934","DOI":"10.1109\/CVPR52729.2023.00934"},{"key":"7991_CR4","unstructured":"Sun P, Jiang Y, Zhang R et al (2020) Transtrack: multiple-object tracking with transformer. arXiv:2012.15460"},{"key":"7991_CR5","doi-asserted-by":"publisher","unstructured":"Meinhardt T, Kirillov A, Leal-Taix\u00e9 L, Feichtenhofer C (2022) TrackFormer: multi-object tracking with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 8844\u20138854. https:\/\/doi.org\/10.1109\/CVPR52688.2022.00864","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"7991_CR6","doi-asserted-by":"publisher","unstructured":"Zeng FG, Dong B, Zhang Y et al (2022) MOTR: end-to-end multiple-object tracking with transformer. In: Proceedings of the European Conference on Computer Vision (ECCV), pp 659\u2013675. https:\/\/doi.org\/10.1007\/978-3-031-19812-0_38","DOI":"10.1007\/978-3-031-19812-0_38"},{"key":"7991_CR7","doi-asserted-by":"publisher","unstructured":"Gao RP, Wang LM (2023) MeMOTR: long-term memory-augmented transformer for multi-object tracking. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp 9867\u20139876. https:\/\/doi.org\/10.1109\/ICCV51070.2023.00908","DOI":"10.1109\/ICCV51070.2023.00908"},{"key":"7991_CR8","doi-asserted-by":"publisher","first-page":"103750","DOI":"10.1016\/j.jvcir.2022.103750","volume":"90","author":"MH Nasseri","year":"2023","unstructured":"Nasseri MH, Babaee M, Moradi H, Hosseini R (2023) Online relational tracking with camera motion suppression. J Vis Commun Image Represent 90:103750. https:\/\/doi.org\/10.1016\/j.jvcir.2022.103750","journal-title":"J Vis Commun Image Represent"},{"key":"7991_CR9","doi-asserted-by":"publisher","first-page":"110369","DOI":"10.1016\/j.patcog.2024.110369","volume":"151","author":"YJ Zheng","year":"2024","unstructured":"Zheng YJ, Qi H, Li L et al (2024) Motion-guided and occlusion-aware multi-object tracking with hierarchical matching. Pattern Recogn 151:110369. https:\/\/doi.org\/10.1016\/j.patcog.2024.110369","journal-title":"Pattern Recogn"},{"key":"7991_CR10","doi-asserted-by":"publisher","first-page":"109078","DOI":"10.1016\/j.compeleceng.2024.109078","volume":"114","author":"YH Li","year":"2024","unstructured":"Li YH, Zhao HH, Liu QY et al (2024) TPTrack: strengthening tracking-by-detection methods from tracklet processing perspectives. Comput Electr Eng 114:109078. https:\/\/doi.org\/10.1016\/j.compeleceng.2024.109078","journal-title":"Comput Electr Eng"},{"key":"7991_CR11","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1109\/TIP.2022.3228168","volume":"32","author":"YJ Zheng","year":"2023","unstructured":"Zheng YJ, Yu ZF, Wang S, Huang TJ (2023) Spike-based motion estimation for object tracking through bio-inspired unsupervised learning. IEEE Trans Image Process 32:335\u2013349. https:\/\/doi.org\/10.1109\/TIP.2022.3228168","journal-title":"IEEE Trans Image Process"},{"key":"7991_CR12","doi-asserted-by":"publisher","unstructured":"Sun PZ, Cao JK, Jiang Y et al (2022) DanceTrack: multi-object tracking in uniform appearance and diverse motion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. (CVPR), pp 20961\u201320970. https:\/\/doi.org\/10.1109\/CVPR52688.2022.02032","DOI":"10.1109\/CVPR52688.2022.02032"},{"key":"7991_CR13","doi-asserted-by":"publisher","unstructured":"Cui YT, Zeng CK, Zhao XY et al (2023) SportsMOT: a large multi-object tracking dataset in multiple sports scenes. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp 9887\u20139897. https:\/\/doi.org\/10.1109\/ICCV51070.2023.00910","DOI":"10.1109\/ICCV51070.2023.00910"},{"key":"7991_CR14","doi-asserted-by":"publisher","unstructured":"Zhang Y, Wang TC, Zhang XY (2023) MOTRv2: bootstrapping end-to-end multi-object tracking by pretrained object detectors. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 22056\u201322065. https:\/\/doi.org\/10.1109\/CVPR52729.2023.02112","DOI":"10.1109\/CVPR52729.2023.02112"},{"key":"7991_CR15","doi-asserted-by":"publisher","unstructured":"Cai JR, Xu MZ, Li W et al (2022) MeMOT: multi-object tracking with memory. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. (CVPR), pp 8080\u20138090. https:\/\/doi.org\/10.1109\/CVPR52688.2022.00792","DOI":"10.1109\/CVPR52688.2022.00792"},{"issue":"6","key":"7991_CR16","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"SQ Ren","year":"2017","unstructured":"Ren SQ, He KM, Girshick R, Sun J (2017) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137\u20131149. https:\/\/doi.org\/10.1109\/TPAMI.2016.2577031","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"7991_CR17","unstructured":"Ge Z, Liu S, Wang F, Li Z, Sun J (2021) Yolox: exceeding yolo series in 2021. arXiv:2107.08430"},{"issue":"2","key":"7991_CR18","doi-asserted-by":"publisher","first-page":"872","DOI":"10.1109\/TCSVT.2022.3208062","volume":"33","author":"PN Zhen","year":"2023","unstructured":"Zhen PN, Yan XT, Wang W et al (2023) Toward compact transformers for end-to-end object detection with decomposed chain tensor structure. IEEE Trans Circuits Syst Video Technol 33(2):872\u2013885. https:\/\/doi.org\/10.1109\/TCSVT.2022.3208062","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"7991_CR19","unstructured":"Zhu X, Su W, Lu L et al (2020) Deformable detr: deformable transformers for end-to-end object detection. arXiv:2010.04159"},{"key":"7991_CR20","doi-asserted-by":"crossref","unstructured":"Bewley A, Ge Z, Ott L et al (2016) Simple online and realtime tracking. In: Proceedings of the IEEE International Conference on Image Processing (ICIP), pp 3464\u20133468","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"7991_CR21","doi-asserted-by":"crossref","unstructured":"Wojke N, Bewley A, Paulus D (2017) Simple online and realtime tracking with a deep association metric. In: Proceedings of the IEEE International Conference on Image Processing (ICIP), pp 3645\u20133649","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"7991_CR22","doi-asserted-by":"publisher","unstructured":"He L, Liao X, Liu W, Liu X, Cheng P, Mei T (2023) Fastreid: a pytorch toolbox for general instance re-identification. In: Proceedings of the 31st ACM International Conference on Multimedia, pp 9664\u20139667. https:\/\/doi.org\/10.1145\/3581783.3613460","DOI":"10.1145\/3581783.3613460"},{"key":"7991_CR23","doi-asserted-by":"crossref","unstructured":"Wang Z, Zheng L, Liu Y et al (2020) Towards real-time multi-object tracking. In: Proceedings of the European Conference on Computer Vision (ECCV), pp 107\u2013122","DOI":"10.1007\/978-3-030-58621-8_7"},{"key":"7991_CR24","doi-asserted-by":"publisher","unstructured":"Voigtlaender P, Krause M, Osep A et al (2019) MOTS: multi-object tracking and segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. (CVPR), pp 7934\u20137943. https:\/\/doi.org\/10.1109\/CVPR.2019.00813","DOI":"10.1109\/CVPR.2019.00813"},{"key":"7991_CR25","doi-asserted-by":"publisher","unstructured":"Yan B, Jiang Y, Sun PZ et al (2022) Towards grand unification of object tracking. In: Proceedings of the European Conference on Computer Vision (ECCV), pp 733\u2013751. https:\/\/doi.org\/10.1007\/978-3-031-19803-8_43","DOI":"10.1007\/978-3-031-19803-8_43"},{"key":"7991_CR26","unstructured":"Nir Aharon, Roy Orfaig, \u201cBen-Zion Bobrovsky. BoT-SORT: Robust Associations Multi-Pedestrian Tracking,\u201d 2022, arXiv:2206.14651v2"},{"key":"7991_CR27","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.imavis.2024.104951","volume":"143","author":"YB Yuan","year":"2024","unstructured":"Yuan YB, Wu YQ, Zhao LY et al (2024) Multiple object detection and tracking from drone videos based on GM-YOLO and multi-tracker. Image Vis Comput 143:14. https:\/\/doi.org\/10.1016\/j.imavis.2024.104951","journal-title":"Image Vis Comput"},{"key":"7991_CR28","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1016\/j.imavis.2024.104964","volume":"144","author":"X Huang","year":"2024","unstructured":"Huang X, Zhan YW (2024) Multi-object tracking with adaptive measurement noise and information fusion. Image Vis Comput 144:10. https:\/\/doi.org\/10.1016\/j.imavis.2024.104964","journal-title":"Image Vis Comput"},{"issue":"4","key":"7991_CR29","doi-asserted-by":"publisher","first-page":"5911","DOI":"10.1109\/TASE.2023.3319676","volume":"21","author":"FW Gu","year":"2023","unstructured":"Gu FW, Lu J, Cai CT et al (2023) EANTrack: an efficient attention network for visual tracking. IEEE Trans Autom Sci Eng 21(4):5911\u20135928. https:\/\/doi.org\/10.1109\/TASE.2023.3319676","journal-title":"IEEE Trans Autom Sci Eng"},{"issue":"2","key":"7991_CR30","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1109\/THMS.2024.3370582","volume":"54","author":"FW Gu","year":"2024","unstructured":"Gu FW, Lu J, Cai CT et al (2024) RTSformer: a robust toroidal transformer with spatiotemporal features for visual tracking. IEEE Trans Hum-Mach Syst 54(2):214\u2013225. https:\/\/doi.org\/10.1109\/THMS.2024.3370582","journal-title":"IEEE Trans Hum-Mach Syst"},{"key":"7991_CR31","doi-asserted-by":"publisher","first-page":"5011214","DOI":"10.1109\/TIM.2022.3170972","volume":"71","author":"FW Gu","year":"2022","unstructured":"Gu FW, Lu J, Cai CT (2022) Rpformer: a robust parallel transformer for visual tracking in complex scenes. IEEE Trans Instrum Meas 71:5011214. https:\/\/doi.org\/10.1109\/TIM.2022.3170972","journal-title":"IEEE Trans Instrum Meas"},{"issue":"3","key":"7991_CR32","doi-asserted-by":"publisher","first-page":"1224","DOI":"10.1109\/TCSII.2022.3223871","volume":"70","author":"D Yuan","year":"2023","unstructured":"Yuan D, Shu X, Liu Q, He ZY (2023) Aligned spatial-temporal memory network for thermal infrared target tracking. IEEE Trans Circuits Syst Video Technol 70(3):1224\u20131228. https:\/\/doi.org\/10.1109\/TCSII.2022.3223871","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"7991_CR33","doi-asserted-by":"crossref","unstructured":"Carion N, Massa F, Synnaeve G, et al (2020) End-to-end object detection with transformers. In: Proceedings of the European Conference on Computer Vision (ECCV), pp 213\u2013229","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"7991_CR34","unstructured":"Yu E, Wang T, Li et al (2023) Motrv3: release-fetch supervision for end-to-end multi-object tracking, 2023, arXiv:2305.14298"},{"key":"7991_CR35","unstructured":"Liu et al SS (2022) DAB-DETR: Dynamic anchor boxes are better queries for DETR, arXiv:2201.12329"},{"key":"7991_CR36","doi-asserted-by":"crossref","unstructured":"Gao R, Zhang Y, Wang L (2024) Multiple object tracking as ID prediction, arXiv:2403.16848","DOI":"10.1109\/CVPR52734.2025.02596"},{"issue":"4","key":"7991_CR37","doi-asserted-by":"publisher","first-page":"845","DOI":"10.1007\/s11263-020-01393-0","volume":"129","author":"P Dendorfer","year":"2021","unstructured":"Dendorfer P, Osep A, Milan A et al (2021) MOTChallenge: a benchmark for single-camera multiple target tracking. Int J Comput Vis 129(4):845\u2013881. https:\/\/doi.org\/10.1007\/s11263-020-01393-0","journal-title":"Int J Comput Vis"},{"key":"7991_CR38","doi-asserted-by":"publisher","unstructured":"Yu F, Chen HF, Wang X, et al (2020) BDD100K: a diverse driving dataset for heterogeneous multitask learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. (CVPR), pp 2633\u20132642. https:\/\/doi.org\/10.1109\/CVPR42600.2020.00271","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"7991_CR39","doi-asserted-by":"publisher","unstructured":"Wang XL, Xiao TT, Jiang YN et al (2018) Repulsion loss: detecting pedestrians in a crowd. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 7774\u20137783, https:\/\/doi.org\/10.1109\/CVPR.2018.00811","DOI":"10.1109\/CVPR.2018.00811"},{"key":"7991_CR40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.cviu.2020.102907","volume":"193","author":"LY Wen","year":"2020","unstructured":"Wen LY, Du DW, Cai ZW et al (2020) UA-UA-DETRAC: a new benchmark and protocol for multi-object detection and tracking. Comput Vis Image Underst 193:1\u201320. https:\/\/doi.org\/10.1016\/j.cviu.2020.102907","journal-title":"Comput Vis Image Underst"},{"key":"7991_CR41","doi-asserted-by":"publisher","unstructured":"Bernardin K, Stiefelhagen R (2008) Evaluating multiple object tracking performance: the CLEAR MOT metrics. EURASIP J Image Video Process, 246309. https:\/\/doi.org\/10.1155\/2008\/246309","DOI":"10.1155\/2008\/246309"},{"issue":"2","key":"7991_CR42","doi-asserted-by":"publisher","first-page":"548","DOI":"10.1007\/s11263-020-01375-2","volume":"129","author":"J Luiten","year":"2021","unstructured":"Luiten J, Osep A, Dendorfer P et al (2021) HOTA: a higher order metric for evaluating multi-object tracking. Int J Comput Vis 129(2):548\u2013578. https:\/\/doi.org\/10.1007\/s11263-020-01375-2","journal-title":"Int J Comput Vis"},{"key":"7991_CR43","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1007\/978-3-319-48881-3_2","volume":"2016","author":"E Ristani","year":"2016","unstructured":"Ristani E, Solera F, Zou R et al (2016) Performance measures and a data set for multi-target, multi-camera tracking. Proc Eur Conf Comput Vis (ECCV) 2016:17\u201335. https:\/\/doi.org\/10.1007\/978-3-319-48881-3_2","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"issue":"11","key":"7991_CR44","doi-asserted-by":"publisher","first-page":"6571","DOI":"10.1109\/TCSVT.2023.3263884","volume":"33","author":"M Hu","year":"2023","unstructured":"Hu M, Zhu X, Wang H, Cao S, Liu C, Song Q (2023) Stdformer: spatial-temporal motion transformer for multiple object tracking,. IEEE Trans IEEE Trans Circuits Syst Video Technol 33(11):6571\u20136594. https:\/\/doi.org\/10.1109\/TCSVT.2023.3263884","journal-title":"IEEE Trans IEEE Trans Circuits Syst Video Technol"},{"key":"7991_CR45","doi-asserted-by":"publisher","unstructured":"Zhou XY, Yin TW, Koltun V, Kr\u00e4henbuhl P, (2022) Global tracking transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. (CVPR), pp 8761\u20138770. https:\/\/doi.org\/10.1109\/CVPR52688.2022.00857","DOI":"10.1109\/CVPR52688.2022.00857"},{"issue":"12","key":"7991_CR46","doi-asserted-by":"publisher","first-page":"15380","DOI":"10.1109\/TPAMI.2023.3301975","volume":"45","author":"T Fischer","year":"2023","unstructured":"Fischer T, Huang TE, Pang JM et al (2023) Qdtrack: quasi-dense similarity learning for appearance-only multiple object tracking. IEEE Trans Pattern Anal Mach Intell 45(12):15380\u201315393. https:\/\/doi.org\/10.1109\/TPAMI.2023.3301975","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"7991_CR47","doi-asserted-by":"publisher","first-page":"8725","DOI":"10.1109\/TMM.2023.3240881","volume":"25","author":"YH Du","year":"2023","unstructured":"Du YH, Zhao ZC, Song Y et al (2023) Strongsort: make deepsort great again. IEEE Trans Multimedia 25:8725\u20138737. https:\/\/doi.org\/10.1109\/TMM.2023.3240881","journal-title":"IEEE Trans Multimedia"},{"key":"7991_CR48","unstructured":"Meng T, Fu C, Huang M et al (2023) Localization-guided track: a deep association multi-object tracking framework based on localization confidence of detections, arXiv:2309.09765"},{"key":"7991_CR49","doi-asserted-by":"publisher","unstructured":"Yang F, Odashima S, Masui S, Jiang S (2023) Hard to track objects with irregular motions and similar appearances? Make it easier by buffering the matching space. In: Proceedings of IEEE\/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW), 2023, pp 4788\u20134797, https:\/\/doi.org\/10.1109\/WACV56688.2023.00478","DOI":"10.1109\/WACV56688.2023.00478"},{"issue":"4","key":"7991_CR50","doi-asserted-by":"publisher","first-page":"4464","DOI":"10.1109\/TITS.2022.3229978","volume":"24","author":"Z Cao","year":"2023","unstructured":"Cao Z, Li J, Zhang D, Zhou M, Abusorrah A (2023) A multi-object tracking algorithm with center-based feature extraction and occlusion handling. IEEE Trans Intell Transp Syst 24(4):4464\u20134473. https:\/\/doi.org\/10.1109\/TITS.2022.3229978","journal-title":"IEEE Trans Intell Transp Syst"},{"issue":"2","key":"7991_CR51","doi-asserted-by":"publisher","first-page":"1992","DOI":"10.1109\/TITS.2023.3316691","volume":"25","author":"Z Shen","year":"2024","unstructured":"Shen Z, Cai K, Zhao P, Luo X (2024) An interactively motion-assisted network for multiple object tracking in complex traffic scenes. IEEE Trans Intell Transp Syst 25(2):1992\u20132004. https:\/\/doi.org\/10.1109\/TITS.2023.3316691","journal-title":"IEEE Trans Intell Transp Syst"},{"issue":"10","key":"7991_CR52","doi-asserted-by":"publisher","first-page":"9866","DOI":"10.1109\/TCSVT.2024.3404275","volume":"34","author":"J Lin","year":"2024","unstructured":"Lin J, Liang G, Zhang R (2024) Lttrack: rethinking the tracking framework for long-term multi-object tracking,. IEEE Trans Circuits Syst Video Technol 34(10):9866\u20139881. https:\/\/doi.org\/10.1109\/TCSVT.2024.3404275","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"issue":"8","key":"7991_CR53","doi-asserted-by":"publisher","first-page":"4054","DOI":"10.1109\/TCSVT.2023.3238716","volume":"33","author":"K Deng","year":"2023","unstructured":"Deng K, Zhang C, Chen Z, Hu W, Li B, Lu F (2023) Jointing recurrent across-channel and spatial attention for multi-object tracking with block-erasing data augmentation. IEEE Trans Circuits Syst Video Technol 33(8):4054\u20134069. https:\/\/doi.org\/10.1109\/TCSVT.2023.3238716","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"issue":"9","key":"7991_CR54","doi-asserted-by":"publisher","first-page":"5102","DOI":"10.1109\/TCSVT.2023.3249468","volume":"33","author":"C Tang","year":"2023","unstructured":"Tang C, Wang X, Bai Y, Wu Z, Zhang J, Huang Y (2023) Learning spatial-frequency transformer for visual object tracking. IEEE Trans Circuits Syst Video Technol 33(9):5102\u20135116. https:\/\/doi.org\/10.1109\/TCSVT.2023.3249468","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"7991_CR55","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. In: NIPS, pap 5998\u20136008"},{"key":"7991_CR56","doi-asserted-by":"crossref","unstructured":"Geiger A, Lenz P, Urtasun R (2012) Are we ready for autonomous driving? The KITTI vision benchmark suite. In: Proc. IEEE IEEE Conference on Computer Vision and Pattern Recognition, pp 3354\u20133361","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"7991_CR57","doi-asserted-by":"crossref","unstructured":"Kim A, Osep A, Leal-Taix\u00e9 L (2021) EagerMOT: 3D multi-object tracking via sensor fusion. In: Proceedings of IEEE International Conference on Robotics and Automation (ICRA), pp 11315\u201311321","DOI":"10.1109\/ICRA48506.2021.9562072"},{"key":"7991_CR58","doi-asserted-by":"crossref","unstructured":"Weng X, Wang J, Held D, Kitani K (2020) 3D multi-object tracking: a baseline and new evaluation metrics. In: International Conference on Intelligent Robots and Systems (IROS), pp 10359\u201310366","DOI":"10.1109\/IROS45743.2020.9341164"},{"key":"7991_CR59","doi-asserted-by":"crossref","unstructured":"Ai H, Wang L (2024) Elite360D: towards efficient 360 depth estimation via semantic- and distance-aware bi-projection fusion. In: 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (Cvpr), pp. 9926\u20139935","DOI":"10.1109\/CVPR52733.2024.00947"},{"key":"7991_CR60","doi-asserted-by":"crossref","unstructured":"Marinello N, Proesmans M, Van Gool L (2022) Triplettrack: 3D object tracking using triplet embeddings and LSTM. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 4500\u20134510","DOI":"10.1109\/CVPRW56347.2022.00496"},{"issue":"1","key":"7991_CR61","doi-asserted-by":"publisher","first-page":"626","DOI":"10.1109\/TIV.2023.3286979","volume":"9","author":"C Jiang","year":"2023","unstructured":"Jiang C, Wang Z, Liang H, Wang Y (2023) A novel adaptive noise covariance matrix estimation and filtering method: application to multiobject tracking. IEEE Trans Intell Veh 9(1):626\u2013641","journal-title":"IEEE Trans Intell Veh"},{"key":"7991_CR62","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3379865","author":"C Peng","year":"2024","unstructured":"Peng C et al (2024) Pnas-mot: multi-modal object tracking with Pareto neural architecture search. IEEE Robot Autom Lett. https:\/\/doi.org\/10.1109\/LRA.2024.3379865","journal-title":"IEEE Robot Autom Lett"},{"key":"7991_CR63","unstructured":"Im E, Jee C, Lee JK (2024) SPB3DTracker: a robust LiDAR-based person tracker for noisy environments. arXiv preprint arXiv:2408.05940"},{"issue":"3","key":"7991_CR64","doi-asserted-by":"publisher","first-page":"8260","DOI":"10.1109\/LRA.2022.3187264","volume":"7","author":"XY Wang","year":"2022","unstructured":"Wang XY, Fu CY, Li ZK et al (2022) Deepfusionmot: a 3D multi-object tracking framework based on camera-LiDAR fusion with deep association. IEEE Robot Autom Lett 7(3):8260\u20138267","journal-title":"IEEE Robot Autom Lett"},{"key":"7991_CR65","unstructured":"Chaabane M, Zhang P, Beveridge JR, O\u2019Hara S (2021) DEFT: detection embeddings for tracking, arXiv:2102.02267"},{"key":"7991_CR66","doi-asserted-by":"crossref","unstructured":"Hu HN, Cai QZ, Wang DQ et al (2019) Joint monocular 3D vehicle detection and tracking. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV 2019), pp 5389\u20135398","DOI":"10.1109\/ICCV.2019.00549"},{"key":"7991_CR67","doi-asserted-by":"crossref","unstructured":"Wang GA, Gu RS, Liu ZZ, et al (2021) Track without appearance: learn box and tracklet embedding with local and global motion patterns for vehicle tracking. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV 2021), pp 9856\u20139866","DOI":"10.1109\/ICCV48922.2021.00973"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-025-07991-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-025-07991-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-025-07991-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T16:47:59Z","timestamp":1761929279000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-025-07991-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,31]]},"references-count":67,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["7991"],"URL":"https:\/\/doi.org\/10.1007\/s11227-025-07991-4","relation":{},"ISSN":["1573-0484"],"issn-type":[{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,31]]},"assertion":[{"value":"28 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 October 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"There are no potential competing interests in this paper. And all authors have seen the manuscript and approved to submit to the journal. We confirm that the content of the manuscript has not been published or submitted for publication elsewhere.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}}],"article-number":"1513"}}