{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,25]],"date-time":"2026-01-25T11:31:54Z","timestamp":1769340714006,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":28,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819788576","type":"print"},{"value":"9789819788583","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"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":[[2025]]},"DOI":"10.1007\/978-981-97-8858-3_26","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T22:03:12Z","timestamp":1730584992000},"page":"376-389","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["More Efficient Encoder: Boosting Transformer-Based Multi-object Tracking Performance Through YOLOX"],"prefix":"10.1007","author":[{"given":"Le","family":"Zheng","sequence":"first","affiliation":[]},{"given":"Yaobin","family":"Mao","sequence":"additional","affiliation":[]},{"given":"Mengjin","family":"Zheng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"26_CR1","doi-asserted-by":"crossref","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. IEEE (2016)","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"26_CR2","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":"26_CR3","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: European Conference on Computer Vision, pp. 213\u2013229. Springer (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"26_CR4","unstructured":"Dendorfer, P., Rezatofighi, H., Milan, A., Shi, J., Cremers, D., Reid, I., Roth, S., Schindler, K., Leal-Taix\u00e9, L.: Mot20: a benchmark for multi object tracking in crowded scenes (2020). arXiv:2003.09003"},{"key":"26_CR5","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":"26_CR6","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: Yolox: Exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430 (2021)"},{"key":"26_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"26_CR8","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., Torr, P., Geiger, A., Leal-Taix\u00e9, L., Leibe, B.: 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":"26_CR9","doi-asserted-by":"crossref","unstructured":"Meinhardt, T., Kirillov, A., Leal-Taixe, L., Feichtenhofer, C.: Trackformer: Multi-object tracking with transformers. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 8844\u20138854 (2022)","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"26_CR10","unstructured":"Milan, A., Leal-Taix\u00e9, L., Reid, I., Roth, S., Schindler, K.: Mot16: A benchmark for multi-object tracking. arXiv preprint arXiv:1603.00831 (2016)"},{"key":"26_CR11","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et\u00a0al.: Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32 (2019)"},{"key":"26_CR12","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: Unified, real-time object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"26_CR13","doi-asserted-by":"crossref","unstructured":"Ristani, E., Solera, F., Zou, R., Cucchiara, R., Tomasi, C.: Performance measures and a data set for multi-target, multi-camera tracking. In: European conference on computer vision. pp. 17\u201335. Springer (2016)","DOI":"10.1007\/978-3-319-48881-3_2"},{"key":"26_CR14","unstructured":"Shao, S., Zhao, Z., Li, B., Xiao, T., Yu, G., Zhang, X., Sun, J.: Crowdhuman: A benchmark for detecting human in a crowd. arXiv preprint arXiv:1805.00123 (2018)"},{"key":"26_CR15","doi-asserted-by":"crossref","unstructured":"Sun, P., Cao, J., Jiang, Y., Yuan, Z., Bai, S., Kitani, K., Luo, P.: Dancetrack: Multi-object tracking in uniform appearance and diverse motion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 20993\u201321002 (2022)","DOI":"10.1109\/CVPR52688.2022.02032"},{"key":"26_CR16","unstructured":"Sun, P., Cao, J., Jiang, Y., Zhang, R., Xie, E., Yuan, Z., Wang, C., Luo, P.: Transtrack: Multiple object tracking with transformer. arXiv preprint arXiv:2012.15460 (2020)"},{"key":"26_CR17","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. Advances in neural information processing systems 30 (2017)"},{"key":"26_CR18","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zheng, L., Liu, Y., Li, Y., Wang, S.: Towards real-time multi-object tracking. In: European conference on computer vision. pp. 107\u2013122. Springer (2020)","DOI":"10.1007\/978-3-030-58621-8_7"},{"key":"26_CR19","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). pp. 3645\u20133649. IEEE (2017)","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"26_CR20","unstructured":"Yan, F., Li, Z., Luo, W., Liang, F., Wei, X., Ma, L., et\u00a0al.: Multiple object tracking challenge technical report for team mt_iot. arXiv preprint arXiv:2212.03586 (2022)"},{"key":"26_CR21","unstructured":"Yu, E., Wang, T., Li, Z., Zhang, Y., Zhang, X., Tao, W.: Motrv3: Release-fetch supervision for end-to-end multi-object tracking. arXiv preprint arXiv:2305.14298 (2023)"},{"key":"26_CR22","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. pp. 659\u2013675. Springer (2022)","DOI":"10.1007\/978-3-031-19812-0_38"},{"key":"26_CR23","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Sun, P., Jiang, Y., Yu, D., Weng, F., Yuan, Z., Luo, P., Liu, W., Wang, X.: Bytetrack: Multi-object tracking by associating every detection box. In: European conference on computer vision. pp. 1\u201321. Springer (2022)","DOI":"10.1007\/978-3-031-20047-2_1"},{"key":"26_CR24","doi-asserted-by":"publisher","first-page":"3069","DOI":"10.1007\/s11263-021-01513-4","volume":"129","author":"Y Zhang","year":"2021","unstructured":"Zhang, Y., Wang, C., Wang, X., Zeng, W., Liu, W.: Fairmot: On the fairness of detection and re-identification in multiple object tracking. Int. J. Comput. Vision 129, 3069\u20133087 (2021)","journal-title":"Int. J. Comput. Vision"},{"key":"26_CR25","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"},{"key":"26_CR26","doi-asserted-by":"crossref","unstructured":"Zhou, X., Koltun, V., Kr\u00e4henb\u00fchl, P.: Tracking objects as points. In: European conference on computer vision. pp. 474\u2013490. Springer (2020)","DOI":"10.1007\/978-3-030-58548-8_28"},{"key":"26_CR27","doi-asserted-by":"crossref","unstructured":"Zhou, X., Yin, T., Koltun, V., Kr\u00e4henb\u00fchl, P.: Global tracking transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 8771\u20138780 (2022)","DOI":"10.1109\/CVPR52688.2022.00857"},{"key":"26_CR28","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8858-3_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,13]],"date-time":"2025-02-13T17:28:06Z","timestamp":1739467686000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8858-3_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9789819788576","9789819788583"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8858-3_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}