{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T05:17:35Z","timestamp":1783315055184,"version":"3.54.6"},"reference-count":71,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T00:00:00Z","timestamp":1773100800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T00:00:00Z","timestamp":1773100800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"University Synergy Innovation Program of Anhui Province","award":["GXXT- 2023-108"],"award-info":[{"award-number":["GXXT- 2023-108"]}]},{"name":"Scientific Research Program of Anhui Provincial Ministry of Education","award":["2024AH051686"],"award-info":[{"award-number":["2024AH051686"]}]},{"DOI":"10.13039\/501100003787","name":"Natural Science Foundation of Hebei Province","doi-asserted-by":"crossref","award":["F2022201013"],"award-info":[{"award-number":["F2022201013"]}],"id":[{"id":"10.13039\/501100003787","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s00530-026-02228-7","type":"journal-article","created":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T13:10:35Z","timestamp":1773148235000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Mamba-driven context-aware tracking with dual prompts"],"prefix":"10.1007","volume":"32","author":[{"given":"Zhao","family":"Huang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuai","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,10]]},"reference":[{"key":"2228_CR1","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 (2022). IEEE","DOI":"10.1109\/IV51971.2022.9827461"},{"key":"2228_CR2","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 (2023). IEEE","DOI":"10.1109\/ICSECE58870.2023.10263468"},{"issue":"1","key":"2228_CR3","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1007\/s00371-023-02777-2","volume":"40","author":"L Baker","year":"2024","unstructured":"Baker, L., Ventura, J., Langlotz, T., Gul, S., Mills, S., Zollmann, S.: Localization and tracking of stationary users for augmented reality. Vis. Comput. 40(1), 227\u2013244 (2024)","journal-title":"Vis. Comput."},{"issue":"3","key":"2228_CR4","doi-asserted-by":"publisher","first-page":"723","DOI":"10.1109\/TPDS.2021.3081254","volume":"33","author":"L Cheng","year":"2021","unstructured":"Cheng, L., Wang, J., Li, Y.: Vitrack: efficient tracking on the edge for commodity video surveillance systems. IEEE Trans. Parallel Distrib. Syst. 33(3), 723\u2013735 (2021)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"2228_CR5","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 (2023). IEEE","DOI":"10.1109\/CICTN57981.2023.10140727"},{"key":"2228_CR6","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 (2022). Springer","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"2228_CR7","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":"2228_CR8","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":"2228_CR9","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":"2228_CR10","doi-asserted-by":"crossref","unstructured":"Wang, N., Zhou, W., Wang, J., Li, H.: Transformer meets tracker: exploiting temporal context for robust visual tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1571\u20131580 (2021)","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"2228_CR11","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":"2228_CR12","doi-asserted-by":"publisher","first-page":"16743","DOI":"10.52202\/068431-1218","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":"2228_CR13","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":"2228_CR14","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":"2228_CR15","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. 38, pp. 7588\u20137596 (2024)","DOI":"10.1609\/aaai.v38i7.28591"},{"key":"2228_CR16","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. 38, pp. 4838\u20134846 (2024)","DOI":"10.1609\/aaai.v38i5.28286"},{"key":"2228_CR17","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":"2228_CR18","doi-asserted-by":"crossref","unstructured":"Song, Z., Luo, R., Yu, J., Chen, Y.-P.P., Yang, W.: Compact transformer tracker with correlative masked modeling. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, pp. 2321\u20132329 (2023)","DOI":"10.1609\/aaai.v37i2.25327"},{"key":"2228_CR19","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":"2228_CR20","doi-asserted-by":"crossref","unstructured":"Mayer, C., Danelljan, M., Paudel, D.P., Van\u00a0Gool, L.: Learning target candidate association to keep track of what not to track. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13444\u201313454 (2021)","DOI":"10.1109\/ICCV48922.2021.01319"},{"key":"2228_CR21","doi-asserted-by":"crossref","unstructured":"Cai, W., Liu, Q., Wang, Y.: Hiptrack: visual tracking with historical prompts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19258\u201319267 (2024)","DOI":"10.1109\/CVPR52733.2024.01822"},{"key":"2228_CR22","doi-asserted-by":"crossref","unstructured":"Xie, J., Zhong, B., Mo, Z., Zhang, S., Shi, L., Song, S., Ji, R.: 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":"2228_CR23","unstructured":"Gu, A., Dao, T.: Mamba: linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752 (2023)"},{"key":"2228_CR24","doi-asserted-by":"publisher","first-page":"103031","DOI":"10.52202\/079017-3273","volume":"37","author":"Y Liu","year":"2024","unstructured":"Liu, Y., Tian, Y., Zhao, Y., Yu, H., Xie, L., Wang, Y., Ye, Q., Jiao, J., Liu, Y.: Vmamba: visual state space model. Adv. Neural. Inf. Process. Syst. 37, 103031\u2013103063 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2228_CR25","unstructured":"Zhu, L., Liao, B., Zhang, Q., Wang, X., Liu, W., Wang, X.: Vision mamba: efficient visual representation learning with bidirectional state space model. In: 41st International Conference on Machine Learning, pp. 62429\u201362442 (2024)"},{"key":"2228_CR26","doi-asserted-by":"crossref","unstructured":"Li, K., Li, X., Wang, Y., He, Y., Wang, Y., Wang, L., Qiao, Y.: Videomamba: state space model for efficient video understanding. In: European Conference on Computer Vision, pp. 237\u2013255 (2024). Springer","DOI":"10.1007\/978-3-031-73347-5_14"},{"key":"2228_CR27","doi-asserted-by":"crossref","unstructured":"Huang, J., Wang, S., Wang, S., Wu, Z., Wang, X., Jiang, B.: Mamba-fetrack: Frame-event tracking via state space model. In: Chinese Conference on Pattern Recognition and Computer Vision (PRCV), pp. 3\u201318 (2024). Springer","DOI":"10.1007\/978-981-97-8858-3_1"},{"key":"2228_CR28","doi-asserted-by":"crossref","unstructured":"Xiao, C., Cao, Q., Luo, Z., Lan, L.: Mambatrack: a simple baseline for multiple object tracking with state space model. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 4082\u20134091 (2024)","DOI":"10.1145\/3664647.3680944"},{"key":"2228_CR29","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. 39, pp. 8727\u20138735 (2025)","DOI":"10.1609\/aaai.v39i8.32943"},{"key":"2228_CR30","doi-asserted-by":"crossref","unstructured":"Lai, S., Liu, C., Zhu, J., Kang, B., Liu, Y., Wang, D., Lu, H.: Mambavt: Spatio-temporal contextual modeling for robust rgb-t tracking. arXiv preprint arXiv:2408.07889 (2024)","DOI":"10.1109\/TCSVT.2025.3557992"},{"key":"2228_CR31","unstructured":"Wang, X., Wang, S., Wang, X., Zhao, Z., Zhu, L., Jiang, B., et al.: Mambaevt: Event stream based visual object tracking using state space model. arXiv preprint arXiv:2408.10487 (2024)"},{"key":"2228_CR32","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 6000\u20136010 (2017)"},{"key":"2228_CR33","doi-asserted-by":"crossref","unstructured":"Bertinetto, L., Valmadre, J., Henriques, J.F., Vedaldi, A., Torr, P.H.: Fully-convolutional siamese networks for object tracking. In: Computer Vision\u2013ECCV 2016 Workshops: Amsterdam, The Netherlands, October 8\u201310 and 15-16, 2016, Proceedings, Part II 14, pp. 850\u2013865 (2016). Springer","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"2228_CR34","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":"2228_CR35","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2228_CR36","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"issue":"12","key":"2228_CR37","doi-asserted-by":"publisher","first-page":"10681","DOI":"10.1109\/TPAMI.2024.3448254","volume":"46","author":"F Xie","year":"2024","unstructured":"Xie, F., Yang, W., Wang, C., Chu, L., Cao, Y., Ma, C., Zeng, W.: Correlation-embedded transformer tracking: A single-branch framework. IEEE Trans. Pattern Anal. Mach. Intell. 46(12), 10681\u201310696 (2024)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2228_CR38","doi-asserted-by":"crossref","unstructured":"Lin, L., Fan, H., Zhang, Z., Wang, Y., Xu, Y., Ling, H.: Tracking meets lora: Faster training, larger model, stronger performance. In: European Conference on Computer Vision, pp. 300\u2013318 (2024). Springer","DOI":"10.1007\/978-3-031-73232-4_17"},{"key":"2228_CR39","doi-asserted-by":"crossref","unstructured":"Bhat, G., Danelljan, M., Van\u00a0Gool, L., Timofte, R.: Know your surroundings: exploiting scene information for object tracking. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XXIII 16, pp. 205\u2013221 (2020). Springer","DOI":"10.1007\/978-3-030-58592-1_13"},{"key":"2228_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":"2228_CR41","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":"2228_CR42","first-page":"14903","volume":"37","author":"X Feng","year":"2025","unstructured":"Feng, X., Li, X., Hu, S., Zhang, D., Zhang, J., Chen, X., Huang, K., et al.: Memvlt: vision-language tracking with adaptive memory-based prompts. Adv. Neural. Inf. Process. Syst. 37, 14903\u201314933 (2025)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2228_CR43","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":"2228_CR44","doi-asserted-by":"crossref","unstructured":"Peng, K., Fu, J., Yang, K., Wen, D., Chen, Y., Liu, R., Zheng, J., Zhang, J., Sarfraz, M.S., Stiefelhagen, R., et\u00a0al.: Referring atomic video action recognition. In: European Conference on Computer Vision, pp. 166\u2013185 (2024). Springer","DOI":"10.1007\/978-3-031-72655-2_10"},{"key":"2228_CR45","unstructured":"Peng, K., Huang, J., Huang, X., Wen, D., Zheng, J., Chen, Y., Yang, K., Wu, J., Hao, C., Stiefelhagen, R.: Hopadiff: holistic-partial aware fourier conditioned diffusion for referring human action segmentation in multi-person scenarios. arXiv preprint arXiv:2506.09650 (2025)"},{"key":"2228_CR46","doi-asserted-by":"crossref","unstructured":"Peng, K., Wen, D., Fu, J., Wu, J., Yang, K., Zheng, J., Liu, R., Chen, Y., Fu, Y., Paudel, D.P., et al.: Refatomnet++: advancing referring atomic video action recognition using semantic retrieval based multi-trajectory mamba. arXiv preprint arXiv:2510.16444 (2025)","DOI":"10.1007\/978-3-031-72655-2_10"},{"key":"2228_CR47","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. 39, pp. 4986\u20134994 (2025)","DOI":"10.1609\/aaai.v39i5.32528"},{"key":"2228_CR48","unstructured":"Zhang, X., Tian, Y., Xie, L., Huang, W., Dai, Q., Ye, Q., Tian, Q.: Hivit: a simpler and more efficient design of hierarchical vision transformer. In: International Conference on Learning Representations (2023)"},{"key":"2228_CR49","unstructured":"Zhang, B., Sennrich, R.: Root mean square layer normalization. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"2228_CR50","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.neunet.2017.12.012","volume":"107","author":"S Elfwing","year":"2018","unstructured":"Elfwing, S., Uchibe, E., Doya, K.: Sigmoid-weighted linear units for neural network function approximation in reinforcement learning. Neural Netw. 107, 3\u201311 (2018)","journal-title":"Neural Netw."},{"key":"2228_CR51","first-page":"572","volume":"34","author":"A Gu","year":"2021","unstructured":"Gu, A., Johnson, I., Goel, K., Saab, K., Dao, T., Rudra, A., R\u00e9, C.: Combining recurrent, convolutional, and continuous-time models with linear state space layers. Adv. Neural. Inf. Process. Syst. 34, 572\u2013585 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2228_CR52","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":"2228_CR53","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"2228_CR54","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 658\u2013666 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"2228_CR55","doi-asserted-by":"crossref","unstructured":"Fan, H., Lin, L., Yang, F., Chu, P., Deng, G., Yu, S., Bai, H., Xu, Y., Liao, C., Ling, H.: 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":"2228_CR56","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft coco: common objects in context. In: Computer vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, pp. 740\u2013755 (2014). Springer","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2228_CR57","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"},{"issue":"5","key":"2228_CR58","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":"2228_CR59","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"2228_CR60","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2019). https:\/\/openreview.net\/forum?id=Bkg6RiCqY7"},{"key":"2228_CR61","doi-asserted-by":"crossref","unstructured":"Xu, C., Zhong, B., Liang, Q., Zheng, Y., Li, G., Song, S.: Less is more: token context-aware learning for object tracking. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, pp. 8824\u20138832 (2025)","DOI":"10.1609\/aaai.v39i8.32954"},{"key":"2228_CR62","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":"2228_CR63","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. 37, pp. 773\u2013780 (2023)","DOI":"10.1609\/aaai.v37i1.25155"},{"key":"2228_CR64","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Peng, H., Fu, J., Li, B., Hu, W.: Ocean: object-aware anchor-free tracking. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XXI 16, pp. 771\u2013787 (2020). Springer","DOI":"10.1007\/978-3-030-58589-1_46"},{"key":"2228_CR65","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":"2228_CR66","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Bhat, G., Shahbaz\u00a0Khan, F., Felsberg, M.: Eco: efficient convolution operators for tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6638\u20136646 (2017)","DOI":"10.1109\/CVPR.2017.733"},{"key":"2228_CR67","doi-asserted-by":"crossref","unstructured":"Fan, H., Bai, H., Lin, L., Yang, F., Chu, P., Deng, G., Yu, S., Harshit, Huang, M., Liu, J., et\u00a0al.: Lasot: a high-quality large-scale single object tracking benchmark. International Journal of Computer Vision 129, 439\u2013461 (2021)","DOI":"10.1007\/s11263-020-01387-y"},{"key":"2228_CR68","doi-asserted-by":"crossref","unstructured":"Wang, X., Shu, X., Zhang, Z., Jiang, B., Wang, Y., Tian, Y., Wu, F.: Towards more flexible and accurate object tracking with natural language: algorithms and benchmark. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13763\u201313773 (2021)","DOI":"10.1109\/CVPR46437.2021.01355"},{"key":"2228_CR69","doi-asserted-by":"crossref","unstructured":"Shao, Y., He, S., Ye, Q., Feng, Y., Luo, W., Chen, J.: Context-aware integration of language and visual references for natural language tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19208\u201319217 (2024)","DOI":"10.1109\/CVPR52733.2024.01817"},{"key":"2228_CR70","unstructured":"Benchmark, U.: A benchmark and simulator for uav tracking. In: European Conference on Computer Vision, vol. 7 (2016)"},{"issue":"9","key":"2228_CR71","doi-asserted-by":"publisher","first-page":"1834","DOI":"10.1109\/TPAMI.2014.2388226","volume":"37","author":"Y Wu","year":"2015","unstructured":"Wu, Y., Lim, J., Yang, M.-H.: Object tracking benchmark. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1834\u20131848 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02228-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-026-02228-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02228-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T05:01:55Z","timestamp":1783314115000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-026-02228-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,10]]},"references-count":71,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["2228"],"URL":"https:\/\/doi.org\/10.1007\/s00530-026-02228-7","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,10]]},"assertion":[{"value":"18 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"175"}}