{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T00:55:09Z","timestamp":1760316909791,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031882166"},{"type":"electronic","value":"9783031882173"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-3-031-88217-3_18","type":"book-chapter","created":{"date-parts":[[2025,5,26]],"date-time":"2025-05-26T10:23:25Z","timestamp":1748255005000},"page":"256-266","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Adapting SAM 2 for\u00a0Visual Object Tracking: 1st Place Solution for\u00a0MMVPR Challenge Multi-modal Tracking"],"prefix":"10.1007","author":[{"given":"Cheng-Yen","family":"Yang","sequence":"first","affiliation":[]},{"given":"Hsiang-Wei","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Pyong-Kun","family":"Kim","sequence":"additional","affiliation":[]},{"given":"Chien-Kai","family":"Kuo","sequence":"additional","affiliation":[]},{"given":"Jui-Wei","family":"Chang","sequence":"additional","affiliation":[]},{"given":"Kwang-Ju","family":"Kim","sequence":"additional","affiliation":[]},{"given":"Chung-I","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Jenq-Neng","family":"Hwang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,5,27]]},"reference":[{"key":"18_CR1","doi-asserted-by":"publisher","unstructured":"Bertinetto, L., Valmadre, J., Henriques, J.F., Vedaldi, A., Torr, P.: Fully-Convolutional Siamese Networks for Object Tracking. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 850\u2013865. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-48881-3_56","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Chen, X., Yan, B., Zhu, J., Wang, D., Yang, X., Lu, H.: Transformer tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8126\u20138135 (2021)","DOI":"10.1109\/CVPR46437.2021.00803"},{"issue":"3","key":"18_CR3","first-page":"3072","volume":"45","author":"W Hu","year":"2023","unstructured":"Hu, W., Wang, Q., Zhang, L., Bertinetto, L., Torr, P.H.: Siammask: a framework for fast online object tracking and segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 45(3), 3072\u20133089 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"18_CR4","unstructured":"Huang, H.W., Yang, C.Y., Chai, W., Jiang, Z., Hwang, J.N.: Exploring learning-based motion models in multi-object tracking. arXiv preprint arXiv:2403.10826 (2024)"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Huang, H.W., et\u00a0al.: Enhancing multi-camera people tracking with anchor-guided clustering and spatio-temporal consistency id re-assignment. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5239\u20135249 (2023)","DOI":"10.1109\/CVPRW59228.2023.00552"},{"key":"18_CR6","unstructured":"Jiawen, Z., Simiao, l., Xin, C., Wang, D., Lu, H.: Visual prompt multi-modal tracking. In: CVPR (2023)"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4015\u20134026 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Kuan, S.Y., et al.: Boosting online 3d multi-object tracking through camera-radar cross check. In: 2024 IEEE Intelligent Vehicles Symposium (IV), pp. 2125\u20132132. IEEE (2024)","DOI":"10.1109\/IV55156.2024.10588514"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Li, B., Yan, J., Wu, W., Zhu, Z., Hu, X.: High performance visual tracking with SIAMESE region proposal network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8971\u20138980 (2018)","DOI":"10.1109\/CVPR.2018.00935"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Perazzi, F., Pont-Tuset, J., McWilliams, B., Van\u00a0Gool, L., Gross, M., Sorkine-Hornung, A.: A benchmark dataset and evaluation methodology for video object segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 724\u2013732 (2016)","DOI":"10.1109\/CVPR.2016.85"},{"key":"18_CR11","unstructured":"Ravi, N., et\u00a0al.: Sam 2: segment anything in images and videos. arXiv preprint arXiv:2408.00714 (2024)"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Sun, J., Huang, H.W., Yang, C.Y., Jiang, Z., Hwang, J.N.: GTA: global tracklet association for multi-object tracking in sports. In: Proceedings of the Asian Conference on Computer Vision, pp. 421\u2013434 (2024)","DOI":"10.1007\/978-981-96-2644-1_6"},{"key":"18_CR13","unstructured":"Xu, N., et al.: Youtube-VOS: a large-scale video object segmentation benchmark. arXiv preprint arXiv:1809.03327 (2018)"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Yan, B., Peng, H., Fu, J., Wang, D., Lu, H.: Learning spatio-temporal transformer for visual tracking. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10448\u201310457 (2021)","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"18_CR15","unstructured":"Yang, C.Y., Huang, H.W., Chai, W., Jiang, Z., Hwang, J.N.: Samurai: adapting segment anything model for zero-shot visual tracking with motion-aware memory. arXiv preprint arXiv:2411.11922 (2024)"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Yang, C.Y., et al.: Sea you later: metadata-guided long-term re-identification for UAV-based multi-object tracking. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 805\u2013812 (2024)","DOI":"10.1109\/WACVW60836.2024.00093"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Yang, C.Y., et al.: An online approach and evaluation method for tracking people across cameras in extremely long video sequence. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7037\u20137045 (2024)","DOI":"10.1109\/CVPRW63382.2024.00697"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Zhang, L., Danelljan, M., Gonzalez-Garcia, A., Van De\u00a0Weijer, J., Shahbaz\u00a0Khan, F.: Multi-modal fusion for end-to-end RGB-T tracking. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops (2019)","DOI":"10.1109\/ICCVW.2019.00278"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Zhu, J., Lai, S., Chen, X., Wang, D., Lu, H.: Visual prompt multi-modal tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9516\u20139526 (2023)","DOI":"10.1109\/CVPR52729.2023.00918"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition. ICPR 2024 International Workshops and Challenges"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-88217-3_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T19:13:52Z","timestamp":1760296432000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-88217-3_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031882166","9783031882173"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-88217-3_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"27 May 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}