{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T09:04:23Z","timestamp":1765357463569,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"The Fundamental Research Funds for the Central Universities","award":["No. DUT22ZD210"],"award-info":[{"award-number":["No. DUT22ZD210"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No. 62293540 62293542 U1903215"],"award-info":[{"award-number":["No. 62293540 62293542 U1903215"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611695","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:12Z","timestamp":1698391632000},"page":"2765-2774","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["A Simple Baseline for Open-World Tracking via Self-training"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-1924-6862","authenticated-orcid":false,"given":"Bingyang","family":"Wang","sequence":"first","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7758-6886","authenticated-orcid":false,"given":"Tanlin","family":"Li","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6367-6994","authenticated-orcid":false,"given":"Jiannan","family":"Wu","sequence":"additional","affiliation":[{"name":"The University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2133-8719","authenticated-orcid":false,"given":"Yi","family":"Jiang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6668-9758","authenticated-orcid":false,"given":"Huchuan","family":"Lu","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6111-340X","authenticated-orcid":false,"given":"You","family":"He","sequence":"additional","affiliation":[{"name":"Dalian University of Technology & Tsinghua University, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_24"},{"key":"e_1_3_2_1_2_1","volume-title":"SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenes. arXiv preprint arXiv:2304.05170","author":"Cui Yutao","year":"2023","unstructured":"Yutao Cui, Chenkai Zeng, Xiaoyu Zhao, Yichun Yang, Gangshan Wu, and Limin Wang. 2023. SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenes. arXiv preprint arXiv:2304.05170 (2023)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_26"},{"key":"e_1_3_2_1_4_1","volume-title":"Mot20: A benchmark for multi object tracking in crowded scenes. arXiv preprint arXiv:2003.09003","author":"Dendorfer Patrick","year":"2020","unstructured":"Patrick Dendorfer, Hamid Rezatofighi, Anton Milan, Javen Shi, Daniel Cremers, Ian Reid, Stefan Roth, Konrad Schindler, and Laura Leal-Taix\u00e9. 2020. Mot20: A benchmark for multi object tracking in crowded scenes. arXiv preprint arXiv:2003.09003 (2020)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00037"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_48"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00577"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3144036"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3146922"},{"key":"e_1_3_2_1_14_1","unstructured":"Chuyi Li Lulu Li Hongliang Jiang Kaiheng Weng Yifei Geng Liang Li Zaidan Ke Qingyuan Li Meng Cheng Weiqiang Nie et al. 2022. YOLOv6: A singlestage object detection framework for industrial applications. arXiv preprint arXiv:2209.02976 (2022)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_27"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01146"},{"key":"e_1_3_2_1_17_1","first-page":"21002","article-title":"Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection","volume":"33","author":"Li Xiang","year":"2020","unstructured":"Xiang Li, Wenhai Wang, Lijun Wu, Shuo Chen, Xiaolin Hu, Jun Li, Jinhui Tang, and Jian Yang. 2020. Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection. Advances in Neural Information Processing Systems 33 (2020), 21002--21012.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3165376"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01846"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00959"},{"key":"e_1_3_2_1_23_1","volume-title":"Hota: A higher order metric for evaluating multi-object tracking. International journal of computer vision 129, 2","author":"Luiten Jonathon","year":"2021","unstructured":"Jonathon Luiten, Aljosa Osep, Patrick Dendorfer, Philip Torr, Andreas Geiger, Laura Leal-Taix\u00e9, and Bastian Leibe. 2021. Hota: A higher order metric for evaluating multi-object tracking. International journal of computer vision 129, 2 (2021), 548--578."},{"key":"e_1_3_2_1_24_1","volume-title":"Towards End-to-end Semi-supervised Learning for One-stage Object Detection. arXiv preprint arXiv:2302.11299","author":"Luo Gen","year":"2023","unstructured":"Gen Luo, Yiyi Zhou, Lei Jin, Xiaoshuai Sun, and Rongrong Ji. 2023. Towards End-to-end Semi-supervised Learning for One-stage Object Detection. arXiv preprint arXiv:2302.11299 (2023)."},{"key":"e_1_3_2_1_25_1","volume-title":"CAT: LoCalization and IdentificAtion Cascade Detection Transformer for Open-World Object Detection. arXiv preprint arXiv:2301.01970","author":"Ma Shuailei","year":"2023","unstructured":"Shuailei Ma, Yuefeng Wang, Jiaqi Fan, Ying Wei, Thomas H Li, Hongli Liu, and Fanbing Lv. 2023. CAT: LoCalization and IdentificAtion Cascade Detection Transformer for Open-World Object Detection. arXiv preprint arXiv:2301.01970 (2023)."},{"key":"e_1_3_2_1_26_1","volume-title":"MOT16: A benchmark for multi-object tracking. arXiv preprint arXiv:1603.00831","author":"Milan Anton","year":"2016","unstructured":"Anton Milan, Laura Leal-Taix\u00e9, Ian Reid, Stefan Roth, and Konrad Schindler. 2016. MOT16: A benchmark for multi-object tracking. arXiv preprint arXiv:1603.00831 (2016)."},{"key":"e_1_3_2_1_27_1","volume-title":"V-net: Fully convolutional neural networks for volumetric medical image segmentation. In 2016 fourth international conference on 3D vision (3DV)","author":"Milletari Fausto","year":"2016","unstructured":"Fausto Milletari, Nassir Navab, and Seyed-Ahmad Ahmadi. 2016. V-net: Fully convolutional neural networks for volumetric medical image segmentation. In 2016 fourth international conference on 3D vision (3DV). IEEE, 565--571."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00023"},{"key":"e_1_3_2_1_29_1","volume-title":"Selftraining with dual uncertainty for semi-supervised medical image segmentation. arXiv preprint arXiv:2304.04441","author":"Qiu Zhanhong","year":"2023","unstructured":"Zhanhong Qiu, Haitao Gan, Ming Shi, Zhongwei Huang, and Zhi Yang. 2023. Selftraining with dual uncertainty for semi-supervised medical image segmentation. arXiv preprint arXiv:2304.04441 (2023)."},{"key":"e_1_3_2_1_30_1","volume-title":"Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems 28","author":"Ren Shaoqing","year":"2015","unstructured":"Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems 28 (2015)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"e_1_3_2_1_32_1","volume-title":"A simple semi-supervised learning framework for object detection. arXiv preprint arXiv:2005.04757","author":"Sohn Kihyuk","year":"2020","unstructured":"Kihyuk Sohn, Zizhao Zhang, Chun-Liang Li, Han Zhang, Chen-Yu Lee, and Tomas Pfister. 2020. A simple semi-supervised learning framework for object detection. arXiv preprint arXiv:2005.04757 (2020)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02032"},{"key":"e_1_3_2_1_34_1","volume-title":"Transtrack: Multiple object tracking with transformer. arXiv preprint arXiv:2012.15460","author":"Sun Peize","year":"2020","unstructured":"Peize Sun, Jinkun Cao, Yi Jiang, Rufeng Zhang, Enze Xie, Zehuan Yuan, Changhu Wang, and Ping Luo. 2020. Transtrack: Multiple object tracking with transformer. arXiv preprint arXiv:2012.15460 (2020)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01068"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561110"},{"key":"e_1_3_2_1_37_1","volume-title":"Detecting Everything in the Open World: Towards Universal Object Detection. arXiv preprint arXiv:2303.11749","author":"Wang Zhenyu","year":"2023","unstructured":"Zhenyu Wang, Yali Li, Xi Chen, Ser-Nam Lim, Antonio Torralba, Hengshuang Zhao, and Shengjin Wang. 2023. Detecting Everything in the Open World: Towards Universal Object Detection. arXiv preprint arXiv:2303.11749 (2023)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_7"},{"key":"e_1_3_2_1_39_1","volume-title":"Conference on Robot Learning. PMLR, 384--393","author":"Wong Kelvin","year":"2020","unstructured":"Kelvin Wong, Shenlong Wang, Mengye Ren, Ming Liang, and Raquel Urtasun. 2020. Identifying unknown instances for autonomous driving. In Conference on Robot Learning. PMLR, 384--393."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_34"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2020.103911"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00305"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_43"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01471"},{"key":"e_1_3_2_1_45_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 4268--4277","author":"Yang Lihe","year":"2022","unstructured":"Lihe Yang, Wei Zhuo, Lei Qi, Yinghuan Shi, and Yang Gao. 2022. St: Make selftraining work better for semi-supervised semantic segmentation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 4268--4277."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20234"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_1"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00031"},{"key":"e_1_3_2_1_50_1","volume-title":"Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159","author":"Zhu Xizhou","year":"2020","unstructured":"Xizhou Zhu, Weijie Su, Lewei Lu, Bin Li, Xiaogang Wang, and Jifeng Dai. 2020. Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)."}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Ottawa ON Canada","acronym":"MM '23"},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611695","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611695","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T23:58:25Z","timestamp":1755820705000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611695"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":50,"alternative-id":["10.1145\/3581783.3611695","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611695","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}