{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T12:00:04Z","timestamp":1780574404119,"version":"3.54.1"},"reference-count":117,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T00:00:00Z","timestamp":1773705600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T00:00:00Z","timestamp":1780531200000},"content-version":"vor","delay-in-days":79,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"the Doctoral Research Start-up Fund of Guangdong University of Science and Technology","award":["GKY-2025BSQDK-26"],"award-info":[{"award-number":["GKY-2025BSQDK-26"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-026-44182-4","type":"journal-article","created":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T14:34:55Z","timestamp":1773758095000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SynTrackThinking improves multimodal multi-object tracking for autonomous driving through frequency-aware fusion and temporal contrastive learning"],"prefix":"10.1038","volume":"16","author":[{"given":"Zhihao","family":"Su","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,17]]},"reference":[{"key":"44182_CR1","doi-asserted-by":"publisher","first-page":"43439","DOI":"10.1007\/s11042-023-17297-3","volume":"83","author":"S Hassan","year":"2024","unstructured":"Hassan, S., Mujtaba, G., Rajput, A. & Fatima, N. Multi-object tracking: a systematic literature review. Multimedia Tools and Appl. 83, 43439\u201343492 (2024).","journal-title":"Multimedia Tools and Appl."},{"key":"44182_CR2","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1016\/j.neucom.2022.04.087","volume":"494","author":"DM Jim\u00e9nez-Bravo","year":"2022","unstructured":"Jim\u00e9nez-Bravo, D. M., Murciego, \u00c1. L., Mendes, A. S., San Bl\u00e1s, H. S. & Bajo, J. Multi-object tracking in traffic environments: A systematic literature review. Neurocomputing 494, 43\u201355 (2022).","journal-title":"Neurocomputing"},{"key":"44182_CR3","doi-asserted-by":"crossref","unstructured":"Pang, Z. et al. Standing between past and future: Spatio-temporal modeling for multi-camera 3d multi-object tracking. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 17928\u201317938 (2023).","DOI":"10.1109\/CVPR52729.2023.01719"},{"key":"44182_CR4","first-page":"6702","volume":"38","author":"K Yi","year":"2024","unstructured":"Yi, K. et al. Ucmtrack: Multi-object tracking with uniform camera motion compensation. In Proceed. AAAI Confer. Artific. Intell. 38, 6702\u20136710 (2024).","journal-title":"In Proceed. AAAI Confer. Artific. Intell."},{"key":"44182_CR5","doi-asserted-by":"publisher","first-page":"11981","DOI":"10.1109\/TITS.2023.3285651","volume":"24","author":"L Wang","year":"2023","unstructured":"Wang, L. et al. Camo-mot: Combined appearance-motion optimization for 3d multi-object tracking with camera-lidar fusion. IEEE Trans. Intell. Transport. Syst. 24, 11981\u201311996 (2023).","journal-title":"IEEE Trans. Intell. Transport. Syst."},{"key":"44182_CR6","doi-asserted-by":"crossref","unstructured":"Shuai, B., Berneshawi, A., Li, X., Modolo, D. & Tighe, J. Siammot: Siamese multi-object tracking. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 12372\u201312382 (2021).","DOI":"10.1109\/CVPR46437.2021.01219"},{"key":"44182_CR7","doi-asserted-by":"crossref","unstructured":"Ding, S., Rehder, E., Schneider, L., Cordts, M. & Gall, J. 3dmotformer: Graph transformer for online 3d multi-object tracking. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, 9784\u20139794 (2023).","DOI":"10.1109\/ICCV51070.2023.00897"},{"key":"44182_CR8","doi-asserted-by":"crossref","unstructured":"Qin, Z. et al. Towards generalizable multi-object tracking. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 18995\u201319004 (2024).","DOI":"10.1109\/CVPR52733.2024.01797"},{"key":"44182_CR9","doi-asserted-by":"publisher","first-page":"501","DOI":"10.3390\/pr11020501","volume":"11","author":"N Senel","year":"2023","unstructured":"Senel, N., Kefferp\u00fctz, K., Doycheva, K. & Elger, G. Multi-sensor data fusion for real-time multi-object tracking. Processes 11, 501 (2023).","journal-title":"Processes"},{"key":"44182_CR10","doi-asserted-by":"crossref","unstructured":"Luo, C., Yang, X. & Yuille, A. Exploring simple 3d multi-object tracking for autonomous driving. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, 10488\u201310497 (2021).","DOI":"10.1109\/ICCV48922.2021.01032"},{"key":"44182_CR11","doi-asserted-by":"crossref","unstructured":"Ren, H. et al. Focus on details: Online multi-object tracking with diverse fine-grained representation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 11289\u201311298 (2023).","DOI":"10.1109\/CVPR52729.2023.01086"},{"key":"44182_CR12","doi-asserted-by":"crossref","unstructured":"Li, Y. et al. Beyond mot: Semantic multi-object tracking. In European Conference on Computer Vision, 276\u2013293 (Springer, 2024).","DOI":"10.1007\/978-3-031-72761-0_16"},{"key":"44182_CR13","doi-asserted-by":"crossref","unstructured":"Cao, J., Pang, J., Weng, X., Khirodkar, R. & Kitani, K. Observation-centric sort: Rethinking sort for robust multi-object tracking. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 9686\u20139696 (2023).","DOI":"10.1109\/CVPR52729.2023.00934"},{"key":"44182_CR14","doi-asserted-by":"publisher","first-page":"1268","DOI":"10.1007\/s10489-021-02457-5","volume":"52","author":"J Yang","year":"2022","unstructured":"Yang, J., Ge, H., Yang, J., Tong, Y. & Su, S. Online multi-object tracking using multi-function integration and tracking simulation training. Appl. Intell. 52, 1268\u20131288 (2022).","journal-title":"Appl. Intell."},{"key":"44182_CR15","doi-asserted-by":"crossref","unstructured":"Yang, X., Dong, W., Cheng, D., Wang, N. & Gao, X. Tienet: A tri-interaction enhancement network for multimodal person reidentification. IEEE Trans. Neural Networks and Learn. Syst. (2025).","DOI":"10.1109\/TNNLS.2025.3544679"},{"key":"44182_CR16","doi-asserted-by":"crossref","unstructured":"Shao, W. & Liu, H. Tcfusion: A three-branch cross-domain fusion network for infrared and visible images. In Proceedings of the 6th ACM International Conference on Multimedia in Asia, 1\u20131 (2024).","DOI":"10.1145\/3696409.3700249"},{"key":"44182_CR17","doi-asserted-by":"crossref","unstructured":"Wang, L., Ouyang, L., Xiong, D. & Zhang, X. Cross-modal frequency-aware transformer for multimodal medical image fusion. In 2024 International Conference on Image Processing, Computer Vision and Machine Learning (ICICML), 201\u2013205 (IEEE, 2024).","DOI":"10.1109\/ICICML63543.2024.10957990"},{"key":"44182_CR18","doi-asserted-by":"crossref","unstructured":"Wang, X. et al. A multimodal fusion depression recognition assisted decision-making system based on eeg and speech signals. In 2023 International Conference on Communications, Computing, Cybersecurity, and Informatics (CCCI), 1\u20138 (IEEE, 2023).","DOI":"10.1109\/CCCI58712.2023.10290732"},{"key":"44182_CR19","unstructured":"Xie, X. et al. Mactfusion: Lightweight cross transformer for adaptive multimodal medical image fusion. IEEE Journal of Biomedical and Health Informatics (2024)."},{"key":"44182_CR20","doi-asserted-by":"crossref","unstructured":"Doering, A., Chen, D., Zhang, S., Schiele, B. & Gall, J. Posetrack21: A dataset for person search, multi-object tracking and multi-person pose tracking. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 20963\u201320972 (2022).","DOI":"10.1109\/CVPR52688.2022.02029"},{"key":"44182_CR21","doi-asserted-by":"crossref","unstructured":"Meinhardt, T., Kirillov, A., Leal-Taix\u00e9, L. & Feichtenhofer, C. Trackformer: Multi-object tracking with transformers. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 8844\u20138854 (2022).","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"44182_CR22","doi-asserted-by":"crossref","unstructured":"Pang, Z., Li, Z. & Wang, N. Simpletrack: Understanding and rethinking 3d multi-object tracking. In European Conference on Computer Vision, 680\u2013696 (Springer, 2022).","DOI":"10.1007\/978-3-031-25056-9_43"},{"key":"44182_CR23","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1016\/j.neunet.2023.09.047","volume":"168","author":"H Mukhtar","year":"2023","unstructured":"Mukhtar, H. & Khan, M. U. G. Stmmot: Advancing multi-object tracking through spatiotemporal memory networks and multi-scale attention pyramids. Neural Networks 168, 363\u2013379 (2023).","journal-title":"Neural Networks"},{"key":"44182_CR24","doi-asserted-by":"publisher","first-page":"23426","DOI":"10.1007\/s10489-023-04617-1","volume":"53","author":"S Gu","year":"2023","unstructured":"Gu, S., Ma, J., Hui, G., Xiao, Q. & Shi, W. Stmt: Spatio-temporal memory transformer for multi-object tracking. Appl. Intell. 53, 23426\u201323441 (2023).","journal-title":"Appl. Intell."},{"key":"44182_CR25","doi-asserted-by":"publisher","first-page":"3759","DOI":"10.1109\/TAI.2024.3353698","volume":"5","author":"T Xu","year":"2024","unstructured":"Xu, T., Wu, X.-J., Zhu, X. & Kittler, J. Memory prompt for spatiotemporal transformer visual object tracking. IEEE Trans. Artific. Intelli. 5, 3759\u20133764 (2024).","journal-title":"IEEE Trans. Artific. Intelli."},{"key":"44182_CR26","doi-asserted-by":"publisher","first-page":"8181","DOI":"10.1109\/ACCESS.2018.2889442","volume":"7","author":"S Lee","year":"2018","unstructured":"Lee, S. & Kim, E. Multiple object tracking via feature pyramid siamese networks. IEEE Access 7, 8181\u20138194 (2018).","journal-title":"IEEE Access"},{"key":"44182_CR27","unstructured":"Shuai, B., Berneshawi, A.\u00a0G., Modolo, D. & Tighe, J. Multi-object tracking with siamese track-rcnn. arXiv preprint arXiv:2004.07786 (2020)."},{"key":"44182_CR28","doi-asserted-by":"crossref","unstructured":"Liu, S., Li, X., Lu, H. & He, Y. Multi-object tracking meets moving uav. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 8876\u20138885 (2022).","DOI":"10.1109\/CVPR52688.2022.00867"},{"key":"44182_CR29","doi-asserted-by":"publisher","first-page":"121","DOI":"10.3233\/ICA-230702","volume":"30","author":"J Urdiales","year":"2023","unstructured":"Urdiales, J., Mart\u00edn, D. & Armingol, J. M. An improved deep learning architecture for multi-object tracking systems. Integ. Comput.-Aid. Eng. 30, 121\u2013134 (2023).","journal-title":"Integ. Comput.-Aid. Eng."},{"key":"44182_CR30","unstructured":"Sun, S. et al. Spatio-temporal bi-directional cross-frame memory for distractor filtering point cloud single object tracking. arXiv preprint arXiv:2403.15831 (2024)."},{"key":"44182_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, G. et al. Multi-object tracking based on spatio-temporal cue fusion and optimized cascade matching. In 2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP), 666\u2013672 (IEEE, 2022).","DOI":"10.1109\/ICSP54964.2022.9778545"},{"key":"44182_CR32","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.109897","volume":"256","author":"R Wu","year":"2022","unstructured":"Wu, R., Wen, X., Yuan, L. & Xu, H. Dasftot: Dual attention spatiotemporal fused transformer for object tracking. Knowledge-Based Syst. 256, 109897 (2022).","journal-title":"Knowledge-Based Syst."},{"key":"44182_CR33","doi-asserted-by":"crossref","unstructured":"Kugarajeevan, J., Kokul, T., Ramanan, A. & Fernando, S. Transformer tracking using spatiotemporal features. In 2024 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET), 524\u2013529 (IEEE, 2024).","DOI":"10.1109\/IICAIET62352.2024.10730668"},{"key":"44182_CR34","first-page":"1","volume":"60","author":"Q He","year":"2022","unstructured":"He, Q., Sun, X., Yan, Z., Li, B. & Fu, K. Multi-object tracking in satellite videos with graph-based multitask modeling. IEEE Trans. Geosci. Remote Sens. 60, 1\u201313 (2022).","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"44182_CR35","doi-asserted-by":"crossref","unstructured":"Wu, D. et al. Referring multi-object tracking. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 14633\u201314642 (2023).","DOI":"10.1109\/CVPR52729.2023.01406"},{"key":"44182_CR36","doi-asserted-by":"crossref","unstructured":"Chen, J., Lin, J., Zhong, G., Yao, Y. & Li, Z. Multi-granularity localization transformer with collaborative understanding for referring multi-object tracking. IEEE Trans. Instr. Measurement (2025).","DOI":"10.1109\/TIM.2024.3522698"},{"key":"44182_CR37","doi-asserted-by":"crossref","unstructured":"Liang, S. et al. Cognitive disentanglement for referring multi-object tracking. Inform Fusion 103349 (2025).","DOI":"10.1016\/j.inffus.2025.103349"},{"key":"44182_CR38","first-page":"1","volume":"20","author":"J Ye","year":"2024","unstructured":"Ye, J. et al. Uniqrnet: Unifying referring expression grounding and segmentation with qrnet. ACM Trans. Multimedia Comput., Commun. Appl. 20, 1\u201328 (2024).","journal-title":"ACM Trans. Multimedia Comput., Commun. Appl."},{"key":"44182_CR39","first-page":"10528","volume":"39","author":"Z Zhao","year":"2025","unstructured":"Zhao, Z. et al. Hff-tracker: A hierarchical fine-grained fusion tracker for referring multi-object tracking. In Proceed. AAAI Confer. Artific. Intell. 39, 10528\u201310536 (2025).","journal-title":"In Proceed. AAAI Confer. Artific. Intell."},{"key":"44182_CR40","first-page":"3991","volume":"38","author":"R Luo","year":"2024","unstructured":"Luo, R. et al. Diffusiontrack: Diffusion model for multi-object tracking. In Proceed. AAAI Confer. Artific. Intell. 38, 3991\u20133999 (2024).","journal-title":"In Proceed. AAAI Confer. Artific. Intell."},{"key":"44182_CR41","doi-asserted-by":"crossref","unstructured":"Gao, R. & Wang, L. Memotr: Long-term memory-augmented transformer for multi-object tracking. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, 9901\u20139910 (2023).","DOI":"10.1109\/ICCV51070.2023.00908"},{"key":"44182_CR42","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Wang, T. & Zhang, X. Motrv2: Bootstrapping end-to-end multi-object tracking by pretrained object detectors. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 22056\u201322065 (2023).","DOI":"10.1109\/CVPR52729.2023.02112"},{"key":"44182_CR43","doi-asserted-by":"publisher","first-page":"1073","DOI":"10.1109\/TASLP.2022.3156795","volume":"30","author":"M Nigro","year":"2022","unstructured":"Nigro, M. & Krishnan, S. Multimodal system for audio scene source counting and analysis. IEEE\/ACM Trans Audio, Speech, and Language Process. 30, 1073\u20131082 (2022).","journal-title":"IEEE\/ACM Trans Audio, Speech, and Language Process."},{"key":"44182_CR44","doi-asserted-by":"publisher","first-page":"15528","DOI":"10.1109\/TNNLS.2023.3288022","volume":"35","author":"Z Song","year":"2023","unstructured":"Song, Z. & Zhang, Z. Visually guided sound source separation with audio-visual predictive coding. IEEE Trans Neural Networks Learn. Syst 35, 15528\u201315542 (2023).","journal-title":"IEEE Trans Neural Networks Learn. Syst"},{"key":"44182_CR45","doi-asserted-by":"crossref","unstructured":"Park, S., Senocak, A. & Chung, J.\u00a0S. Hearing and seeing through clip: A framework for self-supervised sound source localization. arXiv preprint arXiv:2505.05343 (2025).","DOI":"10.1007\/s11263-025-02687-x"},{"key":"44182_CR46","doi-asserted-by":"crossref","unstructured":"Chatterjee, M., Le Roux, J., Ahuja, N. & Cherian, A. Visual scene graphs for audio source separation. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, 1204\u20131213 (2021).","DOI":"10.1109\/ICCV48922.2021.00124"},{"key":"44182_CR47","doi-asserted-by":"crossref","unstructured":"Qin, Z. et al. Motiontrack: Learning robust short-term and long-term motions for multi-object tracking. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 17939\u201317948 (2023).","DOI":"10.1109\/CVPR52729.2023.01720"},{"key":"44182_CR48","doi-asserted-by":"publisher","first-page":"10479","DOI":"10.1007\/s13369-023-07661-8","volume":"48","author":"S Chowdhury","year":"2023","unstructured":"Chowdhury, S. & Soni, B. Qsfvqa: A time efficient, scalable and optimized vqa framework. Arab. J. Sci. Eng. 48, 10479\u201310491 (2023).","journal-title":"Arab. J. Sci. Eng."},{"key":"44182_CR49","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.129906","volume":"635","author":"S Chowdhury","year":"2025","unstructured":"Chowdhury, S. & Soni, B. Handling language prior and compositional reasoning issues in visual question answering system. Neurocomputing 635, 129906 (2025).","journal-title":"Neurocomputing"},{"key":"44182_CR50","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.109948","volume":"142","author":"S Chowdhury","year":"2025","unstructured":"Chowdhury, S. & Soni, B. Envqa: Improving visual question answering model by enriching the visual feature. Eng. Appl. Artific. Intell. 142, 109948 (2025).","journal-title":"Eng. Appl. Artific. Intell."},{"key":"44182_CR51","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112827","volume":"309","author":"S Chowdhury","year":"2025","unstructured":"Chowdhury, S. & Soni, B. R-vqa: A robust visual question answering model. Knowledge-Based Syst. 309, 112827 (2025).","journal-title":"Knowledge-Based Syst."},{"key":"44182_CR52","doi-asserted-by":"crossref","unstructured":"Yang, Y., Su, Y. & An, S. Vdssa: Ventral & dorsal sequential self-attention autoencoder for cognitive-consistency disentanglement. In Chinese Conference on Pattern Recognition and Computer Vision (PRCV), 693\u2013705 (Springer, 2022).","DOI":"10.1007\/978-3-031-18910-4_55"},{"key":"44182_CR53","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1186\/s40537-025-01299-z","volume":"12","author":"Q Peng","year":"2025","unstructured":"Peng, Q., An, S., Nie, S. & Su, Y. Collar: combating low-rank temporal latent representation for high-dimensional multivariate time series prediction using dynamic koopman regularization. J. Big Data 12, 258 (2025).","journal-title":"J. Big Data"},{"key":"44182_CR54","doi-asserted-by":"crossref","unstructured":"Su, Y. et al. Coming out of the dark: human pose estimation in low-light conditions. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, 1882\u20131890 (2025).","DOI":"10.24963\/ijcai.2025\/210"},{"key":"44182_CR55","doi-asserted-by":"crossref","unstructured":"Sun, P. et al. Dancetrack: Multi-object tracking in uniform appearance and diverse motion. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 20993\u201321002 (2022).","DOI":"10.1109\/CVPR52688.2022.02032"},{"key":"44182_CR56","doi-asserted-by":"crossref","unstructured":"Cui, Y. et al. Sportsmot: A large multi-object tracking dataset in multiple sports scenes. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, 9921\u20139931 (2023).","DOI":"10.1109\/ICCV51070.2023.00910"},{"key":"44182_CR57","doi-asserted-by":"crossref","unstructured":"Zhang, Y. et al. Bytetrack: Multi-object tracking by associating every detection box. In European Conference on Computer Vision, 1\u201321 (Springer, 2022).","DOI":"10.1007\/978-3-031-20047-2_1"},{"key":"44182_CR58","doi-asserted-by":"crossref","unstructured":"Ding, S., Schneider, L., Cordts, M. & Gall, J. Ada-track: End-to-end multi-camera 3d multi-object tracking with alternating detection and association. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 15184\u201315194 (2024).","DOI":"10.1109\/CVPR52733.2024.01438"},{"key":"44182_CR59","doi-asserted-by":"crossref","unstructured":"Vaquero, L., Xu, Y., Alameda-Pineda, X., Brea, V.\u00a0M. & Mucientes, M. Lost and found: Overcoming detector failures in online multi-object tracking. In European Conference on Computer Vision, 448\u2013466 (Springer, 2024).","DOI":"10.1007\/978-3-031-73464-9_27"},{"key":"44182_CR60","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126558","volume":"552","author":"TI Amosa","year":"2023","unstructured":"Amosa, T. I. et al. Multi-camera multi-object tracking: A review of current trends and future advances. Neurocomputing 552, 126558 (2023).","journal-title":"Neurocomputing"},{"key":"44182_CR61","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wang, X., Wang, C., Liu, W. & Bai, X. Sparsetrack: Multi-object tracking by performing scene decomposition based on pseudo-depth. IEEE Trans. Circuits Syst. Video Technol. (2025).","DOI":"10.1109\/TCSVT.2024.3524670"},{"key":"44182_CR62","doi-asserted-by":"crossref","unstructured":"Mancusi, G. et al. Trackflow: Multi-object tracking with normalizing flows. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, 9531\u20139543 (2023).","DOI":"10.1109\/ICCV51070.2023.00874"},{"key":"44182_CR63","first-page":"6504","volume":"38","author":"M Yang","year":"2024","unstructured":"Yang, M. et al. Hybrid-sort: Weak cues matter for online multi-object tracking. In Proceed. AAAI Confer. Artific. Intell. 38, 6504\u20136512 (2024).","journal-title":"In Proceed. AAAI Confer. Artific. Intell."},{"key":"44182_CR64","doi-asserted-by":"crossref","unstructured":"Wang, Y. & Mariano, V.\u00a0Y. A multi object tracking framework based on yolov8s and bytetrack algorithm. IEEE Access (2024).","DOI":"10.1109\/ACCESS.2024.3450370"},{"key":"44182_CR65","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2024.118560","volume":"311","author":"Z Shao","year":"2024","unstructured":"Shao, Z., Yin, Y., Lyu, H. & Soares, C. G. A robust method for multi object tracking in autonomous ship navigation systems. Ocean Eng. 311, 118560 (2024).","journal-title":"Ocean Eng."},{"key":"44182_CR66","doi-asserted-by":"publisher","first-page":"308","DOI":"10.3390\/electronics12020308","volume":"12","author":"A Pearce","year":"2023","unstructured":"Pearce, A., Zhang, J. A., Xu, R. & Wu, K. Multi-object tracking with mmwave radar: A review. Electronics 12, 308 (2023).","journal-title":"Electronics"},{"key":"44182_CR67","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2023.107857","volume":"209","author":"Z Zheng","year":"2023","unstructured":"Zheng, Z., Li, J. & Qin, L. Yolo-byte: An efficient multi-object tracking algorithm for automatic monitoring of dairy cows. Comput. Electron. Agri. 209, 107857 (2023).","journal-title":"Comput. Electron. Agri."},{"key":"44182_CR68","doi-asserted-by":"publisher","first-page":"32650","DOI":"10.1109\/ACCESS.2021.3060821","volume":"9","author":"L Kalake","year":"2021","unstructured":"Kalake, L., Wan, W. & Hou, L. Analysis based on recent deep learning approaches applied in real-time multi-object tracking: a review. IEEE Access 9, 32650\u201332671 (2021).","journal-title":"IEEE Access"},{"key":"44182_CR69","doi-asserted-by":"crossref","unstructured":"Yu, E., Li, Z. & Han, S. Towards discriminative representation: Multi-view trajectory contrastive learning for online multi-object tracking. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 8834\u20138843 (2022).","DOI":"10.1109\/CVPR52688.2022.00863"},{"key":"44182_CR70","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wu, J. & Fu, Y. Collaborative tracking learning for frame-rate-insensitive multi-object tracking. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, 9964\u20139973 (2023).","DOI":"10.1109\/ICCV51070.2023.00914"},{"key":"44182_CR71","doi-asserted-by":"publisher","first-page":"8650","DOI":"10.3390\/s22228650","volume":"22","author":"Z Zhu","year":"2022","unstructured":"Zhu, Z., Nie, J., Wu, H., He, Z. & Gao, M. Msa-mot: Multi-stage association for 3d multimodality multi-object tracking. Sensors 22, 8650 (2022).","journal-title":"Sensors"},{"key":"44182_CR72","unstructured":"Yu, E. et al. Motrv3: Release-fetch supervision for end-to-end multi-object tracking. arXiv preprint arXiv:2305.14298 (2023)."},{"key":"44182_CR73","doi-asserted-by":"crossref","unstructured":"Solano-Carrillo, E. et al. Utrack: Multi-object tracking with uncertain detections. In European Conference on Computer Vision, 219\u2013236 (Springer, 2024).","DOI":"10.1007\/978-3-031-91585-7_14"},{"key":"44182_CR74","doi-asserted-by":"publisher","first-page":"1075","DOI":"10.1007\/s11263-023-01922-7","volume":"132","author":"S Hao","year":"2024","unstructured":"Hao, S. et al. Divotrack: A novel dataset and baseline method for cross-view multi-object tracking in diverse open scenes. Int. J. Comput. Vision 132, 1075\u20131090 (2024).","journal-title":"Int. J. Comput. Vision"},{"key":"44182_CR75","doi-asserted-by":"crossref","unstructured":"Liu, H., Zhang, C., Fan, B. & Xu, J. Pro2diff: Proposal propagation for multi-object tracking via the diffusion model. IEEE Trans. Image Process. (2024).","DOI":"10.1109\/TIP.2024.3494600"},{"key":"44182_CR76","doi-asserted-by":"crossref","unstructured":"Gavrilyuk, K., Ghodrati, A., Li, Z. & Snoek, C.\u00a0G. Actor and action video segmentation from a sentence. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 5958\u20135966 (2018).","DOI":"10.1109\/CVPR.2018.00624"},{"key":"44182_CR77","doi-asserted-by":"crossref","unstructured":"Seo, S., Lee, J.-Y. & Han, B. Urvos: Unified referring video object segmentation network with a large-scale benchmark. In European Conference on Computer Vision, 208\u2013223 (Springer, 2020).","DOI":"10.1007\/978-3-030-58555-6_13"},{"key":"44182_CR78","doi-asserted-by":"crossref","unstructured":"Ding, H., Liu, C., He, S., Jiang, X. & Loy, C.\u00a0C. Mevis: A large-scale benchmark for video segmentation with motion expressions. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2694\u20132703 (2023).","DOI":"10.1109\/ICCV51070.2023.00254"},{"key":"44182_CR79","doi-asserted-by":"crossref","unstructured":"Senocak, A., Oh, T.-H., Kim, J., Yang, M.-H. & Kweon, I.\u00a0S. Learning to localize sound source in visual scenes. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 4358\u20134366 (2018).","DOI":"10.1109\/CVPR.2018.00458"},{"key":"44182_CR80","doi-asserted-by":"crossref","unstructured":"Chen, H. et al. Localizing visual sounds the hard way. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 16867\u201316876 (2021).","DOI":"10.1109\/CVPR46437.2021.01659"},{"key":"44182_CR81","doi-asserted-by":"crossref","unstructured":"Pan, W. et al. Wnet: Audio-guided video object segmentation via wavelet-based cross-modal denoising networks. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 1320\u20131331 (2022).","DOI":"10.1109\/CVPR52688.2022.00138"},{"key":"44182_CR82","doi-asserted-by":"crossref","unstructured":"Zhou, J. et al. Audio\u2013visual segmentation. In European Conference on Computer Vision, 386\u2013403 (Springer, 2022).","DOI":"10.1007\/978-3-031-19836-6_22"},{"key":"44182_CR83","doi-asserted-by":"crossref","unstructured":"Wu, H., Sun, H., Ji, K. & Kuang, G. Temporal-spatial feature interaction network for multi-drone multi-object tracking. IEEE Transactions on Circuits and Systems for Video Technology (2024).","DOI":"10.1109\/TCSVT.2024.3478758"},{"key":"44182_CR84","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1016\/j.neucom.2021.12.104","volume":"476","author":"S Han","year":"2022","unstructured":"Han, S. et al. Mat: Motion-aware multi-object tracking. Neurocomputing 476, 75\u201386 (2022).","journal-title":"Neurocomputing"},{"key":"44182_CR85","first-page":"31130","volume":"14","author":"K Vinoth","year":"2024","unstructured":"Vinoth, K. & Sasikumar, P. Multi-sensor fusion and segmentation for autonomous vehicle multi-object tracking using deep q networks. Sci. Reports 14, 31130 (2024).","journal-title":"Sci. Reports"},{"key":"44182_CR86","first-page":"81992","volume":"37","author":"H Naik","year":"2024","unstructured":"Naik, H. et al. Bucktales: A multi-uav dataset for multi-object tracking and re-identification of wild antelopes. Adv. Neural Inform. Process. Syst. 37, 81992\u201382009 (2024).","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"44182_CR87","unstructured":"Zhang, Y., Wu, D., Han, W. & Dong, X. Bootstrapping referring multi-object tracking. arXiv preprint arXiv:2406.05039 (2024)."},{"key":"44182_CR88","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.127328","volume":"575","author":"S Chan","year":"2024","unstructured":"Chan, S. et al. Fusion detection and reid embedding with hybrid attention for multi-object tracking. Neurocomputing 575, 127328 (2024).","journal-title":"Neurocomputing"},{"key":"44182_CR89","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111623","volume":"165","author":"Y Li","year":"2025","unstructured":"Li, Y. et al. Indoor scene multi-object tracking based on region search and memory buffer pool. Pattern Recogn. 165, 111623 (2025).","journal-title":"Pattern Recogn."},{"key":"44182_CR90","doi-asserted-by":"publisher","first-page":"3323","DOI":"10.1109\/LRA.2024.3364450","volume":"9","author":"S Su","year":"2024","unstructured":"Su, S. et al. Collaborative multi-object tracking with conformal uncertainty propagation. IEEE Robot. Auto. Lett. 9, 3323\u20133330 (2024).","journal-title":"IEEE Robot. Auto. Lett."},{"key":"44182_CR91","doi-asserted-by":"crossref","unstructured":"Wu, J. et al. Track to detect and segment: An online multi-object tracker. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 12352\u201312361 (2021).","DOI":"10.1109\/CVPR46437.2021.01217"},{"key":"44182_CR92","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2023.107871","volume":"209","author":"H Zhang","year":"2023","unstructured":"Zhang, H., Li, W., Qi, Y., Liu, H. & Li, Z. Dynamic fry counting based on multi-object tracking and one-stage detection. Comput. Electron. Agri. 209, 107871 (2023).","journal-title":"Comput. Electron. Agri."},{"key":"44182_CR93","doi-asserted-by":"publisher","first-page":"2319","DOI":"10.3390\/electronics10182319","volume":"10","author":"H Wu","year":"2021","unstructured":"Wu, H., Du, C., Ji, Z., Gao, M. & He, Z. Sort-ym: An algorithm of multi-object tracking with yolov4-tiny and motion prediction. Electronics 10, 2319 (2021).","journal-title":"Electronics"},{"key":"44182_CR94","doi-asserted-by":"publisher","first-page":"2426","DOI":"10.1109\/TIV.2022.3216102","volume":"8","author":"Y Ma","year":"2022","unstructured":"Ma, Y. et al. 3d multi-object tracking based on dual-tracker and ds evidence theory. IEEE Trans. Intell. Vehicles 8, 2426\u20132436 (2022).","journal-title":"IEEE Trans. Intell. Vehicles"},{"key":"44182_CR95","doi-asserted-by":"publisher","first-page":"3035","DOI":"10.1007\/s11263-022-01678-6","volume":"130","author":"G Braso","year":"2022","unstructured":"Braso, G., Cetintas, O. & Leal-Taix\u00e9, L. Multi-object tracking and segmentation via neural message passing. Int. J. Comput. Vision 130, 3035\u20133053 (2022).","journal-title":"Int. J. Comput. Vision"},{"key":"44182_CR96","unstructured":"Wang, X. et al. You only need two detectors to achieve multi-modal 3d multi-object tracking. arXiv preprint arXiv:2304.08709 (2023)."},{"key":"44182_CR97","doi-asserted-by":"publisher","first-page":"5103","DOI":"10.1109\/LRA.2022.3145952","volume":"7","author":"J-N Zaech","year":"2022","unstructured":"Zaech, J.-N., Liniger, A., Dai, D., Danelljan, M. & Van Gool, L. Learnable online graph representations for 3d multi-object tracking. IEEE Robot. Auto. Lett. 7, 5103\u20135110 (2022).","journal-title":"IEEE Robot. Auto. Lett."},{"key":"44182_CR98","doi-asserted-by":"crossref","unstructured":"Zhang, C., Zhang, C., Guo, Y., Chen, L. & Happold, M. Motiontrack: End-to-end transformer-based multi-object tracking with lidar-camera fusion. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 151\u2013160 (2023).","DOI":"10.1109\/CVPRW59228.2023.00020"},{"key":"44182_CR99","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.105770","volume":"119","author":"C-Y Tsai","year":"2023","unstructured":"Tsai, C.-Y., Shen, G.-Y. & Nisar, H. Swin-jde: Joint detection and embedding multi-object tracking in crowded scenes based on swin-transformer. Eng. Appl. Artific. Intell. 119, 105770 (2023).","journal-title":"Eng. Appl. Artific. Intell."},{"key":"44182_CR100","doi-asserted-by":"publisher","first-page":"4464","DOI":"10.1109\/TITS.2022.3229978","volume":"24","author":"Z Cao","year":"2022","unstructured":"Cao, Z., Li, J., Zhang, D., Zhou, M. & Abusorrah, A. A multi-object tracking algorithm with center-based feature extraction and occlusion handling. IEEE Trans. Intell. Transport. Syst. 24, 4464\u20134473 (2022).","journal-title":"IEEE Trans. Intell. Transport. Syst."},{"key":"44182_CR101","doi-asserted-by":"publisher","first-page":"548","DOI":"10.1007\/s11263-020-01375-2","volume":"129","author":"J Luiten","year":"2021","unstructured":"Luiten, J. et al. Hota: A higher order metric for evaluating multi-object tracking. Int. J. Comput. Vision 129, 548\u2013578 (2021).","journal-title":"Int. J. Comput. Vision"},{"key":"44182_CR102","unstructured":"Yan, F., Luo, W., Zhong, Y., Gan, Y. & Ma, L. Bridging the gap between end-to-end and non-end-to-end multi-object tracking. arXiv preprint arXiv:2305.12724 (2023)."},{"key":"44182_CR103","doi-asserted-by":"crossref","unstructured":"Kumar, A., Sarren, P. & Raja. Deep learning-based multi-object tracking. In Object Tracking Technology: Trends, Challenges and Applications, 183\u2013199 (Springer, 2023).","DOI":"10.1007\/978-981-99-3288-7_8"},{"key":"44182_CR104","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P. & Urtasun, R. Are we ready for autonomous driving? the kitti vision benchmark suite. In Conference on Computer Vision and Pattern Recognition (CVPR) (2012).","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"44182_CR105","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Stiller, C. & Urtasun, R. Vision meets robotics: The kitti dataset. Int. J. Robot. Res. (IJRR) (2013).","DOI":"10.1177\/0278364913491297"},{"key":"44182_CR106","doi-asserted-by":"crossref","unstructured":"Fritsch, J., Kuehnl, T. & Geiger, A. A new performance measure and evaluation benchmark for road detection algorithms. In International Conference on Intelligent Transportation Systems (ITSC) (2013).","DOI":"10.1109\/ITSC.2013.6728473"},{"key":"44182_CR107","doi-asserted-by":"crossref","unstructured":"Menze, M. & Geiger, A. Object scene flow for autonomous vehicles. In Conference on Computer Vision and Pattern Recognition (CVPR) (2015).","DOI":"10.1109\/CVPR.2015.7298925"},{"key":"44182_CR108","doi-asserted-by":"publisher","first-page":"9106","DOI":"10.3390\/s22239106","volume":"22","author":"G Zhang","year":"2022","unstructured":"Zhang, G. et al. Achieving adaptive visual multi-object tracking with unscented kalman filter. Sensors 22, 9106 (2022).","journal-title":"Sensors"},{"key":"44182_CR109","doi-asserted-by":"crossref","unstructured":"Li, S., Kong, Y. & Rezatofighi, H. Learning of global objective for network flow in multi-object tracking. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 8855\u20138865 (2022).","DOI":"10.1109\/CVPR52688.2022.00865"},{"key":"44182_CR110","doi-asserted-by":"crossref","unstructured":"Kim, A., O\u0161ep, A. & Leal-Taix\u00e9, L. Eagermot: 3d multi-object tracking via sensor fusion. In 2021 IEEE International Conference on Robotics and Automation (ICRA), 11315\u201311321 (IEEE, 2021).","DOI":"10.1109\/ICRA48506.2021.9562072"},{"key":"44182_CR111","doi-asserted-by":"crossref","unstructured":"Wang, S., Yang, D., Wu, Y., Liu, Y. & Sheng, H. Tracking game: Self-adaptative agent based multi-object tracking. In Proceedings of the 30th ACM International Conference on Multimedia, 1964\u20131972 (2022).","DOI":"10.1145\/3503161.3548231"},{"key":"44182_CR112","unstructured":"Sun, P. et al. Transtrack: Multiple object tracking with transformer. arXiv preprint arXiv:2012.15460 (2020)."},{"key":"44182_CR113","doi-asserted-by":"crossref","unstructured":"Yan, B. et al. Universal instance perception as object discovery and retrieval. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 15325\u201315336 (2023).","DOI":"10.1109\/CVPR52729.2023.01471"},{"key":"44182_CR114","doi-asserted-by":"crossref","unstructured":"Miao, B., Bennamoun, M., Gao, Y. & Mian, A. Spectrum-guided multi-granularity referring video object segmentation. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, 920\u2013930 (2023).","DOI":"10.1109\/ICCV51070.2023.00091"},{"key":"44182_CR115","doi-asserted-by":"crossref","unstructured":"Wojke, N., Bewley, A. & Paulus, D. Simple online and realtime tracking with a deep association metric. In 2017 IEEE International Conference on Image Processing (ICIP), 3645\u20133649 (IEEE, 2017).","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"44182_CR116","doi-asserted-by":"publisher","first-page":"3182","DOI":"10.1109\/TIP.2022.3165376","volume":"31","author":"C Liang","year":"2022","unstructured":"Liang, C. et al. Rethinking the competition between detection and reid in multiobject tracking. IEEE Trans. Image Process. 31, 3182\u20133196 (2022).","journal-title":"IEEE Trans. Image Process."},{"key":"44182_CR117","doi-asserted-by":"crossref","unstructured":"Du, Y., Lei, C., Zhao, Z. & Su, F. ikun: Speak to trackers without retraining. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 19135\u201319144 (2024).","DOI":"10.1109\/CVPR52733.2024.01810"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-44182-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-44182-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-44182-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T11:03:00Z","timestamp":1780570980000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-44182-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,17]]},"references-count":117,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["44182"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-44182-4","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,17]]},"assertion":[{"value":"10 November 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"17353"}}