{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T00:47:53Z","timestamp":1780447673797,"version":"3.54.1"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2024,8,23]],"date-time":"2024-08-23T00:00:00Z","timestamp":1724371200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2024,8,23]],"date-time":"2024-08-23T00:00:00Z","timestamp":1724371200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"DOI":"10.1007\/s11063-024-11670-5","type":"journal-article","created":{"date-parts":[[2024,8,23]],"date-time":"2024-08-23T07:05:52Z","timestamp":1724396752000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Siamese Tracking Network with Multi-attention Mechanism"],"prefix":"10.1007","volume":"56","author":[{"given":"Yuzhuo","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ting","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bing","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fasheng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fuming","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,8,23]]},"reference":[{"key":"11670_CR1","unstructured":"You S, Zhu H, Li M, Li Y (2019) A review of visual trackers and analysis of its application to mobile robot. arXiv preprint arXiv:1910.09761"},{"key":"11670_CR2","doi-asserted-by":"publisher","first-page":"899","DOI":"10.1007\/s11263-022-01732-3","volume":"131","author":"F Wang","year":"2023","unstructured":"Wang F, Cao P, Li F, Wang X, He B, Sun F (2023) Watb: wild animal tracking benchmark. Int J Comput Vis 131:899\u2013917","journal-title":"Int J Comput Vis"},{"key":"11670_CR3","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1016\/j.neucom.2019.11.023","volume":"381","author":"G Ciaparrone","year":"2020","unstructured":"Ciaparrone G, S\u00e1nchez FL, Tabik S, Troiano L, Tagliaferri R (2020) Herrera F Deep learning in video multi-object tracking: a survey. Neurocomputing 381:61\u201388","journal-title":"Neurocomputing"},{"key":"11670_CR4","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1016\/j.patcog.2017.11.007","volume":"76","author":"P Li","year":"2018","unstructured":"Li P, Wang D, Wang L (2018) Deep visual tracking: review and experimental comparison. Pattern Recogn 76:323\u2013338","journal-title":"Pattern Recogn"},{"key":"11670_CR5","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 8-10 and 15-16, 2016, Proceedings, Part II 14, pp. 850\u2013865 (2016)","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"11670_CR6","doi-asserted-by":"crossref","unstructured":"Li B, Yan J, Wu W, Zhu Z, Hu X (2018) High performance visual tracking with siamese region proposal network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8971\u20138980","DOI":"10.1109\/CVPR.2018.00935"},{"key":"11670_CR7","first-page":"2969239","volume":"28","author":"S Ren","year":"2015","unstructured":"Ren S, He K, Girshick R (2015) Faster R-CNN: towards real-time object detection with region proposal networks. Adv Neural Inf Process Syst 28:2969239","journal-title":"Adv Neural Inf Process Syst"},{"key":"11670_CR8","doi-asserted-by":"crossref","unstructured":"Zhu Z, Wang Q, Li B, Wu W, Yan J, Hu W (2018) Distractor-aware siamese networks for visual object tracking. In: Proceedings of the European conference on computer vision (ECCV), pp. 101\u2013117","DOI":"10.1007\/978-3-030-01240-3_7"},{"key":"11670_CR9","doi-asserted-by":"crossref","unstructured":"Zhang Z, Peng H (2019) Deeper and wider siamese networks for real-time visual tracking. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 4591\u20134600","DOI":"10.1109\/CVPR.2019.00472"},{"key":"11670_CR10","doi-asserted-by":"crossref","unstructured":"Li B, Wu W, Wang Q, Zhang F, Xing J, Yan J (2019) 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","DOI":"10.1109\/CVPR.2019.00441"},{"key":"11670_CR11","doi-asserted-by":"crossref","unstructured":"Wang Q, Zhang L, Bertinetto L, Hu W, Torr PH (2019) Fast online object tracking and segmentation: a unifying approach. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 1328\u20131338","DOI":"10.1109\/CVPR.2019.00142"},{"key":"11670_CR12","doi-asserted-by":"crossref","unstructured":"Tao R, Gavves E, Smeulders AW (2016) Siamese instance search for tracking. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1420\u20131429","DOI":"10.1109\/CVPR.2016.158"},{"key":"11670_CR13","doi-asserted-by":"crossref","unstructured":"Xu Y, Wang Z, Li Z, Yuan Y, Yu G (2020) Siamfc++: towards robust and accurate visual tracking with target estimation guidelines. In: Proceedings of the AAAI conference on artificial intelligence, vol. 34, pp. 12549\u201312556","DOI":"10.1609\/aaai.v34i07.6944"},{"key":"11670_CR14","doi-asserted-by":"crossref","unstructured":"Zhang Z, Peng H, Fu J, Li B, Hu W (2020) 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","DOI":"10.1007\/978-3-030-58589-1_46"},{"key":"11670_CR15","doi-asserted-by":"crossref","unstructured":"Chen Z, Zhong B, Li G, Zhang S, Ji R (2020) Siamese box adaptive network for visual tracking. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 6668\u20136677","DOI":"10.1109\/CVPR42600.2020.00670"},{"key":"11670_CR16","doi-asserted-by":"crossref","unstructured":"Guo D, Wang J, Cui Y, Wang Z, Chen S (2020) Siamcar: siamese fully convolutional classification and regression for visual tracking. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 6269\u20136277","DOI":"10.1109\/CVPR42600.2020.00630"},{"key":"11670_CR17","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-023-11290-5","author":"F Wang","year":"2023","unstructured":"Wang F, Cao P, Wang X, He B (2023) Siamadt: siamese attention and deformable features fusion network for visual object tracking. Neural Process Lett. https:\/\/doi.org\/10.1007\/s11063-023-11290-5","journal-title":"Neural Process Lett"},{"key":"11670_CR18","doi-asserted-by":"crossref","unstructured":"Choi J, Kwon J, Lee KM (2019) Deep meta learning for real-time target-aware visual tracking. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 911\u2013920","DOI":"10.1109\/ICCV.2019.00100"},{"key":"11670_CR19","doi-asserted-by":"crossref","unstructured":"Li P, Chen B, Ouyang W, Wang D, Yang X, Lu H (2019) Gradnet: gradient-guided network for visual object tracking. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 6162\u20136171","DOI":"10.1109\/ICCV.2019.00626"},{"key":"11670_CR20","doi-asserted-by":"crossref","unstructured":"Zhang L, Gonzalez-Garcia A, Weijer JVD, Danelljan M, Khan FS (2019) Learning the model update for siamese trackers. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 4010\u20134019","DOI":"10.1109\/ICCV.2019.00411"},{"key":"11670_CR21","doi-asserted-by":"crossref","unstructured":"Chen X, Yan B, Zhu J, Wang D, Yang X, Lu H (2021) Transformer tracking. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 8126\u20138135","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"11670_CR22","doi-asserted-by":"crossref","unstructured":"Wang N, Zhou W, Wang J, Li H (2021) 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","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"11670_CR23","doi-asserted-by":"crossref","unstructured":"Bhat G, Danelljan M, Gool L.V, Timofte R (2019) Learning discriminative model prediction for tracking. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 6182\u20136191","DOI":"10.1109\/ICCV.2019.00628"},{"key":"11670_CR24","doi-asserted-by":"crossref","unstructured":"Yan B, Peng H, Fu J, Wang D, Lu H (2021) Learning spatio-temporal transformer for visual tracking. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 10448\u201310457","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"11670_CR25","doi-asserted-by":"crossref","unstructured":"Chen B, Li P, Bai L, Qiao L, Shen Q, Li B, Gan W, Wu W, Ouyang W (2022) Backbone is all your need: a simplified architecture for visual object tracking. In: European conference on computer vision, pp. 375\u2013392","DOI":"10.1007\/978-3-031-20047-2_22"},{"key":"11670_CR26","doi-asserted-by":"crossref","unstructured":"Fu Z, Fu Z, Liu Q, Cai W, Wang Y (2022) Sparsett: visual tracking with sparse transformers. arXiv preprint arXiv:2205.03776","DOI":"10.24963\/ijcai.2022\/127"},{"key":"11670_CR27","doi-asserted-by":"crossref","unstructured":"Cui Y, Jiang C, Wang L, Wu G (2022) 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","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"11670_CR28","doi-asserted-by":"crossref","unstructured":"Song Z, Yu J, Chen Y.-P.P, Yang W (2022) Transformer tracking with cyclic shifting window attention. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 8791\u20138800","DOI":"10.1109\/CVPR52688.2022.00859"},{"key":"11670_CR29","unstructured":"Zhao M, Okada K, Inaba M (2021) Trtr: visual tracking with transformer. arXiv preprint arXiv:2105.03817"},{"key":"11670_CR30","first-page":"16743","volume":"35","author":"L Lin","year":"2022","unstructured":"Lin L, Fan H, Zhang Z, Xu Y (2022) Swintrack: a simple and strong baseline for transformer tracking. Adv Neural Inf Process Syst 35:16743\u201316754","journal-title":"Adv Neural Inf Process Syst"},{"key":"11670_CR31","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez A.N, Kaiser \u0141, Polosukhin I (2017)Attention is all you need. Advances in neural information processing systems. 30"},{"key":"11670_CR32","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S et al (2020) An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929"},{"key":"11670_CR33","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B (2021) Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 10012\u201310022","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"11670_CR34","doi-asserted-by":"crossref","unstructured":"Carion N, Massa F, Synnaeve G, Usunier N, Kirillov A, Zagoruyko S (2020) End-to-end object detection with transformers. In: European conference on computer vision, pp. 213\u2013229","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"11670_CR35","unstructured":"Cai W, Liu Q, Wang Y (2023) Learning historical status prompt for accurate and robust visual tracking. arXiv preprint arXiv:2311.02072"},{"key":"11670_CR36","doi-asserted-by":"crossref","unstructured":"Gao J, Zhong B, Chen Y (2023) Unambiguous object tracking by exploiting target cues. In: Proceedings of the 31st ACM international conference on multimedia, pp. 1997\u20132005","DOI":"10.1145\/3581783.3612240"},{"key":"11670_CR37","unstructured":"Luo Y, Guo X, Feng H, Ao L (2023) Rgb-t tracking via multi-modal mutual prompt learning. arXiv preprint arXiv:2308.16386"},{"key":"11670_CR38","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"11670_CR39","doi-asserted-by":"crossref","unstructured":"Ma F, Shou M.Z, Zhu L, Fan H, Xu Y, Yang Y, Yan Z (2022) Unified transformer tracker for object tracking. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 8781\u20138790","DOI":"10.1109\/CVPR52688.2022.00858"},{"key":"11670_CR40","unstructured":"Xie F, Wang C, Wang G, Cao Y, Yang W, Zeng W (2012) Correlation-aware deep tracking. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 8751\u20138760"},{"key":"11670_CR41","doi-asserted-by":"crossref","unstructured":"Song Z, Luo R, Yu J, Chen Y-PP, Yang W (2023) Compact transformer tracker with correlative masked modeling. arXiv preprint arXiv:2301.10938","DOI":"10.1609\/aaai.v37i2.25327"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-024-11670-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11063-024-11670-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-024-11670-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T11:53:31Z","timestamp":1730289211000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11063-024-11670-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,23]]},"references-count":41,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2024,10]]}},"alternative-id":["11670"],"URL":"https:\/\/doi.org\/10.1007\/s11063-024-11670-5","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-3296460\/v1","asserted-by":"object"}]},"ISSN":["1573-773X"],"issn-type":[{"value":"1573-773X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,23]]},"assertion":[{"value":"18 June 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 August 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors certify that they have no affiliations with or involvement in any organization or entity with any financial interest or non-financial interest in the subject matter or materials discussed in this manuscript.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"There is no ethical approval needed in the present study.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics Approval"}}],"article-number":"222"}}