{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T05:00:03Z","timestamp":1762491603469,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032093202","type":"print"},{"value":"9783032093219","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T00:00:00Z","timestamp":1762560000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T00:00:00Z","timestamp":1762560000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-09321-9_24","type":"book-chapter","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T04:58:20Z","timestamp":1762491500000},"page":"351-365","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Tracking-by-Transformer by\u00a0Using State Transition Prediction"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2523-8851","authenticated-orcid":false,"given":"Thuc","family":"Nguyen-Quang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3046-3041","authenticated-orcid":false,"given":"Minh-Triet","family":"Tran","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,8]]},"reference":[{"key":"24_CR1","doi-asserted-by":"publisher","unstructured":"Bergmann, P., Meinhardt, T., Leal-Taixe, L.: Tracking without bells and whistles. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV). IEEE (2019). https:\/\/doi.org\/10.1109\/iccv.2019.00103","DOI":"10.1109\/iccv.2019.00103"},{"issue":"1","key":"24_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2008\/246309","volume":"2008","author":"K Bernardin","year":"2008","unstructured":"Bernardin, K., Stiefelhagen, R.: Evaluating multiple object tracking performance: the CLEAR MOT metrics. EURASIP J. Image Video Process. 2008(1), 1\u201310 (2008). https:\/\/doi.org\/10.1155\/2008\/246309","journal-title":"EURASIP J. Image Video Process."},{"key":"24_CR3","doi-asserted-by":"publisher","unstructured":"Bewley, A., Ge, Z., Ott, L., Ramos, F., Upcroft, B.: Simple online and realtime tracking. In: 2016 IEEE International Conference on Image Processing (ICIP), pp. 3464\u20133468 (2016). https:\/\/doi.org\/10.1109\/ICIP.2016.7533003","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"24_CR4","doi-asserted-by":"crossref","unstructured":"Cai, J., et al.: Memot: multi-object tracking with memory. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8080\u20138090 (2022)","DOI":"10.1109\/CVPR52688.2022.00792"},{"key":"24_CR5","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, pp. 9686\u20139696 (2023)","DOI":"10.1109\/CVPR52729.2023.00934"},{"key":"24_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"24_CR7","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, pp. 9901\u20139910 (2023)","DOI":"10.1109\/ICCV51070.2023.00908"},{"key":"24_CR8","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: Yolox: exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430 (2021)"},{"key":"24_CR9","doi-asserted-by":"crossref","unstructured":"Kong, L., Shen, C., Yang, J.: Fastflownet: a lightweight network for fast optical flow estimation. In: 2021 IEEE International Conference on Robotics and Automation (ICRA) (2021)","DOI":"10.1109\/ICRA48506.2021.9560800"},{"key":"24_CR10","unstructured":"Liu, S., et al.: DAB-DETR: dynamic anchor boxes are better queries for DETR. In: International Conference on Learning Representations (2022)"},{"key":"24_CR11","doi-asserted-by":"publisher","unstructured":"Luiten, J., et al.: HOTA: a higher order metric for evaluating multi-object tracking. Int. J. Comput. Vis. (1), 1\u201331 (2020). https:\/\/doi.org\/10.1007\/s11263-020-01375-2","DOI":"10.1007\/s11263-020-01375-2"},{"key":"24_CR12","doi-asserted-by":"crossref","unstructured":"Maggiolino, G., Ahmad, A., Cao, J., Kitani, K.: Deep OC-sort: multi-pedestrian tracking by adaptive re-identification (2023)","DOI":"10.1109\/ICIP49359.2023.10222576"},{"issue":"5","key":"24_CR13","doi-asserted-by":"publisher","first-page":"3943","DOI":"10.1109\/TITS.2020.3046478","volume":"23","author":"SM Marvasti-Zadeh","year":"2021","unstructured":"Marvasti-Zadeh, S.M., Cheng, L., Ghanei-Yakhdan, H., Kasaei, S.: Deep learning for visual tracking: a comprehensive survey. IEEE Trans. Intell. Transp. Syst. 23(5), 3943\u20133968 (2021)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"24_CR14","doi-asserted-by":"crossref","unstructured":"Meinhardt, T., Kirillov, A., Leal-Taixe, L., Feichtenhofer, C.: Trackformer: multi-object tracking with transformers. In: The IEEE Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"24_CR15","unstructured":"Milan, A., Leal-Taixe, L., Reid, I., Roth, S., Schindler, K.: Mot16: a benchmark for multi-object tracking (2016)"},{"key":"24_CR16","doi-asserted-by":"publisher","unstructured":"Nguyen-Quang, T., Tran, M.T.: TF-sasm: training-free spatial-aware sparse memory for multi-object tracking. In: 2024 International Conference on Multimedia Analysis and Pattern Recognition (MAPR), pp.\u00a01\u20136 (2024). https:\/\/doi.org\/10.1109\/MAPR63514.2024.10660850","DOI":"10.1109\/MAPR63514.2024.10660850"},{"key":"24_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1007\/978-3-319-48881-3_2","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"E Ristani","year":"2016","unstructured":"Ristani, E., Solera, F., Zou, R., Cucchiara, R., Tomasi, C.: Performance measures and a data set for\u00a0multi-target, multi-camera tracking. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 17\u201335. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-48881-3_2"},{"key":"24_CR18","unstructured":"Shao, S., et al.: Crowdhuman: a benchmark for detecting human in a crowd. arXiv preprint arXiv:1805.00123 (2018)"},{"key":"24_CR19","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 (2022)","DOI":"10.1109\/CVPR52688.2022.02032"},{"key":"24_CR20","unstructured":"Sun, P., et al.: Transtrack: multiple-object tracking with transformer. arXiv preprint arXiv: 2012.15460 (2020)"},{"key":"24_CR21","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS 2017, pp. 6000\u20136010. Curran Associates Inc., Red Hook (2017)"},{"key":"24_CR22","doi-asserted-by":"publisher","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), pp. 3645\u20133649. IEEE (2017). https:\/\/doi.org\/10.1109\/ICIP.2017.8296962","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"24_CR23","unstructured":"Yu, E., Wang, T., Li, Z., Zhang, Y., Zhang, X., Tao, W.: Motrv3: release-fetch supervision for end-to-end multi-object tracking (2023)"},{"key":"24_CR24","doi-asserted-by":"crossref","unstructured":"Zeng, F., Dong, B., Zhang, Y., Wang, T., Zhang, X., Wei, Y.: Motr: end-to-end multiple-object tracking with transformer. In: European Conference on Computer Vision (ECCV) (2022)","DOI":"10.1007\/978-3-031-19812-0_38"},{"key":"24_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, Y., et al.: Bytetrack: multi-object tracking by associating every detection box. In: Proceedings of the European Conference on Computer Vision (ECCV) (2022)","DOI":"10.1007\/978-3-031-20047-2_1"},{"key":"24_CR26","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, pp. 22056\u201322065 (2023)","DOI":"10.1109\/CVPR52729.2023.02112"}],"container-title":["Lecture Notes in Computer Science","Computational Collective Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-09321-9_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T04:58:23Z","timestamp":1762491503000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-09321-9_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,8]]},"ISBN":["9783032093202","9783032093219"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-09321-9_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,8]]},"assertion":[{"value":"8 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICCCI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Collective Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ho Chi Minh City","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iccci2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iccci.pwr.edu.pl\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}