{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T10:40:20Z","timestamp":1770460820303,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":44,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819557578","type":"print"},{"value":"9789819557585","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/978-981-95-5758-5_22","type":"book-chapter","created":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T04:59:31Z","timestamp":1770353971000},"page":"296-310","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SDFTrack: Exploring Semantic Information Fusion for\u00a0Image-Level Object Tracking"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-0847-2559","authenticated-orcid":false,"given":"Zhao","family":"Huang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1962-8856","authenticated-orcid":false,"given":"Lei","family":"Liu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2206-1047","authenticated-orcid":false,"given":"Shuai","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5901-9019","authenticated-orcid":false,"given":"Jun","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,2,7]]},"reference":[{"key":"22_CR1","doi-asserted-by":"crossref","unstructured":"Bai, Y., Zhao, Z., Gong, Y., Wei, X.: Artrackv2: prompting autoregressive tracker where to look and how to describe. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19048\u201319057 (2024)","DOI":"10.1109\/CVPR52733.2024.01802"},{"key":"22_CR2","doi-asserted-by":"crossref","unstructured":"Bai, Z., Wu, G., Qi, X., Liu, Y., Oguchi, K., Barth, M.J.: Infrastructure-based object detection and tracking for cooperative driving automation: a survey. In: 2022 IEEE Intelligent Vehicles Symposium (IV), pp. 1366\u20131373. IEEE (2022)","DOI":"10.1109\/IV51971.2022.9827461"},{"key":"22_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"850","DOI":"10.1007\/978-3-319-48881-3_56","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"L Bertinetto","year":"2016","unstructured":"Bertinetto, L., Valmadre, J., Henriques, J.F., Vedaldi, A., Torr, P.H.S.: 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"},{"key":"22_CR4","doi-asserted-by":"crossref","unstructured":"Cai, Y., Liu, J., Tang, J., Wu, G.: Robust object modeling for visual tracking. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9589\u20139600 (2023)","DOI":"10.1109\/ICCV51070.2023.00879"},{"key":"22_CR5","doi-asserted-by":"crossref","unstructured":"Cao, X.: Eye tracking in human-computer interaction recognition. In: 2023 IEEE International Conference on Sensors, Electronics and Computer Engineering (ICSECE), pp. 203\u2013207. IEEE (2023)","DOI":"10.1109\/ICSECE58870.2023.10263468"},{"key":"22_CR6","unstructured":"Cao, Y., et al.: Mmfuser: multimodal multi-layer feature fuser for fine-grained vision-language understanding. arXiv preprint arXiv:2410.11829 (2024)"},{"key":"22_CR7","doi-asserted-by":"crossref","unstructured":"Chen, X., et al.: Sutrack: towards simple and unified single object tracking. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a039, pp. 2239\u20132247 (2025)","DOI":"10.1609\/aaai.v39i2.32223"},{"key":"22_CR8","doi-asserted-by":"crossref","unstructured":"Chen, X., Peng, H., Wang, D., Lu, H., Hu, H.: Seqtrack: sequence to sequence learning for visual object tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14572\u201314581 (2023)","DOI":"10.1109\/CVPR52729.2023.01400"},{"key":"22_CR9","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"},{"key":"22_CR10","doi-asserted-by":"crossref","unstructured":"Choubisa, M., Kumar, V., Kumar, M., Khanna, S.: Object tracking in intelligent video surveillance system based on artificial system. In: 2023 International Conference on Computational Intelligence, Communication Technology and Networking (CICTN), pp. 160\u2013166. IEEE (2023)","DOI":"10.1109\/CICTN57981.2023.10140727"},{"key":"22_CR11","doi-asserted-by":"crossref","unstructured":"Cui, Y., Jiang, C., Wang, L., Wu, G.: Mixformer: end-to-end tracking with iterative mixed attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13608\u201313618 (2022)","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"22_CR12","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"22_CR13","doi-asserted-by":"crossref","unstructured":"Fan, H., et al.: Lasot: a high-quality large-scale single object tracking benchmark. Int. J. Comput. Vision 129, 439\u2013461 (2021)","DOI":"10.1007\/s11263-020-01387-y"},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"Fan, H., et al.: Lasot: a high-quality benchmark for large-scale single object tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5374\u20135383 (2019)","DOI":"10.1109\/CVPR.2019.00552"},{"key":"22_CR15","doi-asserted-by":"crossref","unstructured":"Fu, Z., Liu, Q., Fu, Z., Wang, Y.: Stmtrack: template-free visual tracking with space-time memory networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13774\u201313783 (2021)","DOI":"10.1109\/CVPR46437.2021.01356"},{"key":"22_CR16","doi-asserted-by":"crossref","unstructured":"Gao, S., Zhou, C., Zhang, J.: Generalized relation modeling for transformer tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18686\u201318695 (2023)","DOI":"10.1109\/CVPR52729.2023.01792"},{"key":"22_CR17","unstructured":"Gu, A., Dao, T.: Mamba: linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752 (2023)"},{"key":"22_CR18","doi-asserted-by":"crossref","unstructured":"Guo, X., Zhong, P., Lin, L., Zhang, H., Huang, L., Li, S.: Tracking reflected objects: a benchmark. In: Proceedings of the Asian Conference on Computer Vision, pp. 1756\u20131776 (2024)","DOI":"10.1007\/978-981-96-0901-7_21"},{"key":"22_CR19","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, C., Xie, S., Li, Z., Wang, Z.: Target-aware tracking with long-term context attention. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 773\u2013780 (2023)","DOI":"10.1609\/aaai.v37i1.25155"},{"issue":"5","key":"22_CR20","doi-asserted-by":"publisher","first-page":"1562","DOI":"10.1109\/TPAMI.2019.2957464","volume":"43","author":"L Huang","year":"2019","unstructured":"Huang, L., Zhao, X., Huang, K.: Got-10k: a large high-diversity benchmark for generic object tracking in the wild. IEEE Trans. Pattern Anal. Mach. Intell. 43(5), 1562\u20131577 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"22_CR21","doi-asserted-by":"crossref","unstructured":"Hui, T., et al.: Bridging search region interaction with template for RGB-T tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13630\u201313639 (2023)","DOI":"10.1109\/CVPR52729.2023.01310"},{"key":"22_CR22","doi-asserted-by":"crossref","unstructured":"Li, B., Wu, W., Wang, Q., Zhang, F., Xing, J., Yan, J.: Siamrpn++: evolution of siamese visual tracking with very deep networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4282\u20134291 (2019)","DOI":"10.1109\/CVPR.2019.00441"},{"key":"22_CR23","doi-asserted-by":"crossref","unstructured":"Li, X., Zhong, B., Liang, Q., Li, G., Mo, Z., Song, S.: Mambalct: boosting tracking via long-term context state space model. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a039, pp. 4986\u20134994 (2025)","DOI":"10.1609\/aaai.v39i5.32528"},{"key":"22_CR24","doi-asserted-by":"crossref","unstructured":"Lin, J., et al.: Multi-layer visual feature fusion in multimodal LLMs: methods, analysis, and best practices. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 4156\u20134166 (2025)","DOI":"10.1109\/CVPR52734.2025.00393"},{"key":"22_CR25","first-page":"16743","volume":"35","author":"L Lin","year":"2022","unstructured":"Lin, L., Fan, H., Zhang, Z., Xu, Y., Ling, H.: Swintrack: a simple and strong baseline for transformer tracking. Adv. Neural. Inf. Process. Syst. 35, 16743\u201316754 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"22_CR27","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2019). https:\/\/openreview.net\/forum?id=Bkg6RiCqY7"},{"key":"22_CR28","doi-asserted-by":"crossref","unstructured":"Muller, M., Bibi, A., Giancola, S., Alsubaihi, S., Ghanem, B.: Trackingnet: a large-scale dataset and benchmark for object tracking in the wild. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 300\u2013317 (2018)","DOI":"10.1007\/978-3-030-01246-5_19"},{"key":"22_CR29","first-page":"130797","volume":"37","author":"L Peng","year":"2024","unstructured":"Peng, L., et al.: Vasttrack: vast category visual object tracking. Adv. Neural. Inf. Process. Syst. 37, 130797\u2013130818 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR30","doi-asserted-by":"crossref","unstructured":"Shi, L., Zhong, B., Liang, Q., Hu, X., Mo, Z., Song, S.: Mamba adapter: efficient multi-modal fusion for vision-language tracking. IEEE Trans. Circuits Syst. Video Technol. (2025)","DOI":"10.1109\/TCSVT.2025.3557570"},{"key":"22_CR31","doi-asserted-by":"crossref","unstructured":"Shi, L., Zhong, B., Liang, Q., Li, N., Zhang, S., Li, X.: Explicit visual prompts for visual object tracking. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 4838\u20134846 (2024)","DOI":"10.1609\/aaai.v38i5.28286"},{"key":"22_CR32","doi-asserted-by":"crossref","unstructured":"Tian, Y., et al.: Fast-iTPN: integrally pre-trained transformer pyramid network with token migration. IEEE Trans. Pattern Anal. Mach. Intell. (2024)","DOI":"10.1109\/TPAMI.2024.3429508"},{"key":"22_CR33","doi-asserted-by":"crossref","unstructured":"Wei, X., Bai, Y., Zheng, Y., Shi, D., Gong, Y.: Autoregressive visual tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9697\u20139706 (2023)","DOI":"10.1109\/CVPR52729.2023.00935"},{"key":"22_CR34","doi-asserted-by":"crossref","unstructured":"Xie, F., Chu, L., Li, J., Lu, Y., Ma, C.: Videotrack: learning to track objects via video transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22826\u201322835 (2023)","DOI":"10.1109\/CVPR52729.2023.02186"},{"key":"22_CR35","doi-asserted-by":"crossref","unstructured":"Xie, J., Zhong, B., Liang, Q., Li, N., Mo, Z., Song, S.: Robust tracking via mamba-based context-aware token learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a039, pp. 8727\u20138735 (2025)","DOI":"10.1609\/aaai.v39i8.32943"},{"key":"22_CR36","doi-asserted-by":"crossref","unstructured":"Xie, J., et al.: Autoregressive queries for adaptive tracking with spatio-temporal transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19300\u201319309 (2024)","DOI":"10.1109\/CVPR52733.2024.01826"},{"key":"22_CR37","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":"22_CR38","doi-asserted-by":"crossref","unstructured":"Yang, D., He, J., Ma, Y., Yu, Q., Zhang, T.: Foreground-background distribution modeling transformer for visual object tracking. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10117\u201310127 (2023)","DOI":"10.1109\/ICCV51070.2023.00928"},{"key":"22_CR39","doi-asserted-by":"crossref","unstructured":"Ye, B., Chang, H., Ma, B., Shan, S., Chen, X.: Joint feature learning and relation modeling for tracking: a one-stream framework. In: European Conference on Computer Vision, pp. 341\u2013357. Springer (2022)","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"22_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, L., Gonzalez-Garcia, A., Weijer, J.V.D., Danelljan, M., Khan, F.S.: Learning the model update for siamese trackers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4010\u20134019 (2019)","DOI":"10.1109\/ICCV.2019.00411"},{"key":"22_CR41","unstructured":"Zhang, X., et al.: Hivit: a simpler and more efficient design of hierarchical vision transformer. In: International Conference on Learning Representations (2023)"},{"key":"22_CR42","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"771","DOI":"10.1007\/978-3-030-58589-1_46","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Zhang","year":"2020","unstructured":"Zhang, Z., Peng, H., Fu, J., Li, B., Hu, W.: Ocean: object-aware anchor-free tracking. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12366, pp. 771\u2013787. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58589-1_46"},{"key":"22_CR43","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Zhong, B., Liang, Q., Mo, Z., Zhang, S., Li, X.: Odtrack: online dense temporal token learning for visual tracking. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 7588\u20137596 (2024)","DOI":"10.1609\/aaai.v38i7.28591"},{"key":"22_CR44","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. In: International Conference on Learning Representations (2021)"}],"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\/978-981-95-5758-5_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T04:59:40Z","timestamp":1770353980000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5758-5_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819557578","9789819557585"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5758-5_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"7 February 2026","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":"Shanghai","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}