{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,13]],"date-time":"2025-12-13T09:43:31Z","timestamp":1765619011869,"version":"3.48.0"},"reference-count":77,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100018905","name":"Environmentally Friendly Materials and Occupational Health Research Institute, Anhui University of Science and Technology","doi-asserted-by":"publisher","award":["ALW2021YF04"],"award-info":[{"award-number":["ALW2021YF04"]}],"id":[{"id":"10.13039\/100018905","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Medical Special Cultivation Project of Anhui University of Science and Technology","award":["YZ2023H2C005"],"award-info":[{"award-number":["YZ2023H2C005"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int. J. Mach. Learn. & Cyber."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1007\/s13042-024-02394-y","type":"journal-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T04:03:02Z","timestamp":1727668982000},"page":"9787-9806","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["SiamATA: an asymmetric target-aware and frequency domain task-aware Siamese network for visual tracking"],"prefix":"10.1007","volume":"16","author":[{"given":"Xingzhu","family":"Liang","sequence":"first","affiliation":[]},{"given":"Yunzhuang","family":"Xiao","sequence":"additional","affiliation":[]},{"given":"Yu-e","family":"Lin","sequence":"additional","affiliation":[]},{"given":"Xinyun","family":"Yan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,30]]},"reference":[{"key":"2394_CR1","doi-asserted-by":"crossref","unstructured":"Javed S, Danelljan M, Khan FS, Khan MH, Felsberg M, Matas J (2022) Visual object tracking with discriminative filters and siamese networks: a survey and outlook. IEEE Trans Pattern Anal Mach Intell 1\u201320","DOI":"10.1109\/TPAMI.2022.3212594"},{"issue":"5","key":"2394_CR2","doi-asserted-by":"publisher","first-page":"3943","DOI":"10.1109\/TITS.2020.3046478","volume":"23","author":"SM Marvasti-Zadeh","year":"2022","unstructured":"Marvasti-Zadeh SM, Cheng L, Ghanei-Yakhdan H, Kasaei S (2022) Deep learning for visual tracking: a comprehensive survey. IEEE Trans Intell Transport Syst 23(5):3943\u20133968","journal-title":"IEEE Trans Intell Transport Syst"},{"key":"2394_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2022.103508","volume":"222","author":"F Chen","year":"2022","unstructured":"Chen F, Wang X, Zhao Y, Lv S, Niu X (2022) Visual object tracking: a survey. Comput Vis Image Underst 222:103508","journal-title":"Comput Vis Image Underst"},{"key":"2394_CR4","doi-asserted-by":"crossref","unstructured":"Ojha S, Sakhare S (2015) Image processing techniques for object tracking in video surveillance\u2014a survey. In: 2015 international conference on pervasive computing (ICPC), pp 1\u20136","DOI":"10.1109\/PERVASIVE.2015.7087180"},{"issue":"6","key":"2394_CR5","doi-asserted-by":"publisher","first-page":"485","DOI":"10.1016\/j.imavis.2003.12.001","volume":"22","author":"J-C Tai","year":"2004","unstructured":"Tai J-C, Tseng S-T, Lin C-P, Song K-T (2004) Real-time image tracking for automatic traffic monitoring and enforcement applications. Image Vis Comput 22(6):485\u2013501","journal-title":"Image Vis Comput"},{"issue":"9","key":"2394_CR6","doi-asserted-by":"publisher","first-page":"1429","DOI":"10.1109\/TMM.2015.2455418","volume":"17","author":"K-H Lee","year":"2015","unstructured":"Lee K-H, Hwang J-N (2015) On-road pedestrian tracking across multiple driving recorders. IEEE Trans Multim 17(9):1429\u20131438","journal-title":"IEEE Trans Multim"},{"key":"2394_CR7","unstructured":"Liu L, Xing J, Ai H, Ruan X (2012) Hand posture recognition using finger geometric feature. In: International conference on pattern recognition (ICPR), pp 565\u2013568"},{"issue":"4","key":"2394_CR8","doi-asserted-by":"publisher","first-page":"701","DOI":"10.1109\/JAS.2021.1003919","volume":"8","author":"W Yue","year":"2021","unstructured":"Yue W, Wang Z, Zhang J, Liu X (2021) An overview of recommendation techniques and their applications in healthcare. IEEE\/CAA J Autom Sin 8(4):701\u2013717","journal-title":"IEEE\/CAA J Autom Sin"},{"key":"2394_CR9","doi-asserted-by":"crossref","unstructured":"Bertinetto L, Valmadre J, Henriques JF, Vedaldi A, Torr PHS (2016) Fully-convolutional siamese networks for object tracking. In: Proceedings of the European conference on computer vision (ECCV), pp 850\u2013865","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"2394_CR10","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\/CVF conference on computer vision and pattern recognition (CVPR), pp 8971\u20138980","DOI":"10.1109\/CVPR.2018.00935"},{"key":"2394_CR11","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 (CVPR), pp 4282\u20134291","DOI":"10.1109\/CVPR.2019.00441"},{"key":"2394_CR12","doi-asserted-by":"crossref","unstructured":"Tao R, Gavves E, Smeulders AWM (2016) Siamese instance search for tracking. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 1420\u20131429","DOI":"10.1109\/CVPR.2016.158"},{"key":"2394_CR13","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 (CVPR), pp 6668\u20136677","DOI":"10.1109\/CVPR42600.2020.00670"},{"key":"2394_CR14","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 (CVPR), pp 6268\u20136276","DOI":"10.1109\/CVPR42600.2020.00630"},{"key":"2394_CR15","doi-asserted-by":"crossref","unstructured":"Fu Z, Liu Q, Fu Z, Wang Y (2021) Stmtrack: template-free visual tracking with space-time memory networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 13774\u201313783","DOI":"10.1109\/CVPR46437.2021.01356"},{"key":"2394_CR16","doi-asserted-by":"crossref","unstructured":"Liao B, Wang C, Wang Y, Wang Y, Yin J (2020) Pg-Net: pixel to global matching network for visual tracking. In: Proceedings of the European conference on computer vision (ECCV), pp 429\u2013444","DOI":"10.1007\/978-3-030-58542-6_26"},{"key":"2394_CR17","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 (CVPR), pp 1571\u20131580","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"2394_CR18","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\/CVF conference on computer vision and pattern recognition (CVPR), pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"2394_CR19","doi-asserted-by":"crossref","unstructured":"Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 2818\u20132826","DOI":"10.1109\/CVPR.2016.308"},{"key":"2394_CR20","doi-asserted-by":"crossref","unstructured":"Sandler M, Howard AG, Zhu M, Zhmoginov A , Chen L-C (2018) Mobilenetv2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 4510\u20134520","DOI":"10.1109\/CVPR.2018.00474"},{"key":"2394_CR21","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 international conference on computer vision (ICCV), pp 9992\u201310002","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2394_CR22","doi-asserted-by":"crossref","unstructured":"Li X, Ma C, Wu B, He Z, Yang M-H (2019) Target-aware deep tracking. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 1369\u20131378","DOI":"10.1109\/CVPR.2019.00146"},{"key":"2394_CR23","doi-asserted-by":"crossref","unstructured":"Wang Q, Teng Z, Xing J, Gao J, Hu W, Maybank SJ (2018) Learning attentions: residual attentional siamese network for high performance online visual tracking. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 4854\u20134863","DOI":"10.1109\/CVPR.2018.00510"},{"key":"2394_CR24","doi-asserted-by":"crossref","unstructured":"Wu Y, Chen Y, Yuan L, Liu Z, Wang L, Li H, Fu Y (2020) Rethinking classification and localization for object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 10183\u201310192","DOI":"10.1109\/CVPR42600.2020.01020"},{"key":"2394_CR25","unstructured":"Zhuang J, Qin Z, Yu H, Chen X (2023) Task-specific context decoupling for object detection. arXiv:abs\/2303.01047"},{"key":"2394_CR26","doi-asserted-by":"crossref","unstructured":"Li S, He C, Li R, Zhang L (2022) A dual weighting label assignment scheme for object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 9377\u20139386","DOI":"10.1109\/CVPR52688.2022.00917"},{"key":"2394_CR27","doi-asserted-by":"crossref","unstructured":"Tang F, Ling Q (2022) Ranking-based siamese visual tracking. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 8731\u20138740","DOI":"10.1109\/CVPR52688.2022.00854"},{"key":"2394_CR28","doi-asserted-by":"crossref","unstructured":"Peng J, Jiang Z, Gu Y, Wu Y, Wang Y, Tai Y, Wang C, Lin W (2021) Siamrcr: reciprocal classification and regression for visual object tracking. In: International joint conference on artificial intelligence (IJCAI), pp 952\u2013958","DOI":"10.24963\/ijcai.2021\/132"},{"key":"2394_CR29","doi-asserted-by":"crossref","unstructured":"Xu Y, Wang Z, Li Z, Ye Y, Yu G (2020) Siamfc++: towards robust and accurate visual tracking with target estimation guidelines. In: AAAI conference on artificial intelligence (AAAI), pp 12549\u201312556","DOI":"10.1609\/aaai.v34i07.6944"},{"issue":"1","key":"2394_CR30","doi-asserted-by":"publisher","first-page":"1451","DOI":"10.1109\/TCSS.2023.3235649","volume":"11","author":"S Hu","year":"2024","unstructured":"Hu S, Zhou S, Lu J, Yu H (2024) Flexible dual-branch siamese network: learning location quality estimation and regression distribution for visual tracking. IEEE Trans Comput Soc Syst 11(1):1451\u20131459","journal-title":"IEEE Trans Comput Soc Syst"},{"key":"2394_CR31","doi-asserted-by":"crossref","unstructured":"Han W, Dong X, Khan FS, Shao L, Shen J (2021) Learning to fuse asymmetric feature maps in siamese trackers. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 16570\u201316580","DOI":"10.1109\/CVPR46437.2021.01630"},{"key":"2394_CR32","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 7132\u20137141","DOI":"10.1109\/CVPR.2018.00745"},{"key":"2394_CR33","doi-asserted-by":"crossref","unstructured":"Wang X, Girshick RB, Gupta A, He K (2018) Non-local neural networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 7794\u20137803","DOI":"10.1109\/CVPR.2018.00813"},{"key":"2394_CR34","first-page":"1","volume":"60","author":"Y Liu","year":"2022","unstructured":"Liu Y, Li Q, Yuan Y, Du Q, Wang Q (2022) Abnet: adaptive balanced network for multiscale object detection in remote sensing imagery. IEEE Trans Geosci Remote Sens 60:1\u201314","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"2394_CR35","doi-asserted-by":"publisher","first-page":"110043","DOI":"10.1016\/j.patcog.2023.110043","volume":"146","author":"Z Heng","year":"2024","unstructured":"Heng Z, Chunna T, Zhenxi Z, Chengyang L, Yongqiang X, Zhongbo L (2024) Frequency-aware feature aggregation network with dual-task consistency for RGB-T salient object detection. Pattern Recognit 146:110043\u2013110043","journal-title":"Pattern Recognit"},{"key":"2394_CR36","doi-asserted-by":"crossref","unstructured":"Bai Y, Liu Y, Li Y (2024) Learning frequency-aware cross-modal interaction for multimodal fake news detection. IEEE Trans Comput Soc Syst 1\u201312","DOI":"10.1109\/TCSS.2024.3415160"},{"key":"2394_CR37","doi-asserted-by":"crossref","unstructured":"Ouyang D, He S, Zhang G, Luo M, Guo H, Zhan J, Huang Z (2023) Efficient multi-scale attention module with cross-spatial learning. In: IEEE international conference on acoustics, speech, and signal processing (ICASSP), pp 1\u20135","DOI":"10.1109\/ICASSP49357.2023.10096516"},{"key":"2394_CR38","doi-asserted-by":"crossref","unstructured":"Yu Y, Xiong Y, Huang W, Scott MR (2020) Deformable siamese attention networks for visual object tracking. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 6727\u20136736","DOI":"10.1109\/CVPR42600.2020.00676"},{"key":"2394_CR39","doi-asserted-by":"crossref","unstructured":"Guo D, Shao Y, Cui Y, Wang Z, Zhang L, Shen C (2021) Graph attention tracking. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 9543\u20139552","DOI":"10.1109\/CVPR46437.2021.00942"},{"key":"2394_CR40","doi-asserted-by":"crossref","unstructured":"Zhang H, Ma Z, Zhao Y, Wang Y, Jiang B (2024) Reciprocal interlayer-temporal discriminative target model for robust visual tracking. Int J Mach Learn Cybern 1\u201316","DOI":"10.1007\/s13042-024-02296-z"},{"issue":"10","key":"2394_CR41","doi-asserted-by":"publisher","first-page":"3607","DOI":"10.1007\/s13042-023-01853-2","volume":"14","author":"J Li","year":"2023","unstructured":"Li J, Li B, Ding G, Zhuo L (2023) Siamese global location-aware network for visual object tracking. Int J Mach Learn Cybern 14(10):3607\u20133620","journal-title":"Int J Mach Learn Cybern"},{"key":"2394_CR42","doi-asserted-by":"crossref","unstructured":"Bolme DS, Beveridge JR, Draper BA, Lui YM (2010) Visual object tracking using adaptive correlation filters. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 2544\u20132550","DOI":"10.1109\/CVPR.2010.5539960"},{"key":"2394_CR43","doi-asserted-by":"crossref","unstructured":"Danelljan M, Bhat G, Khan FS, Felsberg M (2017) Eco: efficient convolution operators for tracking. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 6638-6646","DOI":"10.1109\/CVPR.2017.733"},{"key":"2394_CR44","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 (CVPR), pp 8126-8135","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"2394_CR45","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 international conference on computer vision (ICCV), pp 10428\u201310437","DOI":"10.1109\/ICCV48922.2021.01028"},{"issue":"6","key":"2394_CR46","doi-asserted-by":"publisher","first-page":"4129","DOI":"10.1109\/TPAMI.2024.3349519","volume":"46","author":"Y Cui","year":"2024","unstructured":"Cui Y, Jiang C, Wu G, Wang L (2024) Mixformer: end-to-end tracking with iterative mixed attention. IEEE Trans Pattern Anal Mach Intell 46(6):4129\u20134146","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2394_CR47","doi-asserted-by":"crossref","unstructured":"Zhang J, Li X, Li J, Liu L, Xue Z, Zhang B, Jiang Z, Huang T, Wang Y, Wang C (2023) Rethinking mobile block for efficient attention-based models. In: Proceedings of the IEEE international conference on computer vision (ICCV), pp 1389\u20131400","DOI":"10.1109\/ICCV51070.2023.00134"},{"key":"2394_CR48","unstructured":"Vaswani A, Shazeer NM, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. In: Neural information processing systems, pp 5998\u20136008"},{"key":"2394_CR49","doi-asserted-by":"crossref","unstructured":"Tatsunami Y, Taki M (2024) Fft-based dynamic token mixer for vision. In: AAAI conference on artificial intelligence (AAAI), pp 15328\u201315336","DOI":"10.1609\/aaai.v38i14.29457"},{"issue":"2","key":"2394_CR50","doi-asserted-by":"publisher","first-page":"896","DOI":"10.1109\/TPAMI.2023.3329173","volume":"46","author":"W Yu","year":"2024","unstructured":"Yu W, Si C, Zhou P, Luo M, Zhou Y, Feng J, Yan S, Wang X (2024) Metaformer baselines for vision. IEEE Trans Pattern Anal Mach Intell 46(2):896\u2013912","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"9","key":"2394_CR51","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 (2015) Object tracking benchmark. IEEE Trans Pattern Anal Mach Intell 37(9):1834\u20131848","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2394_CR52","doi-asserted-by":"crossref","unstructured":"Mueller M, Smith N, Ghanem B (2016) A benchmark and simulator for UAV tracking. In: Proceedings of the European conference on computer vision (ECCV), pp 445\u2013461","DOI":"10.1007\/978-3-319-46448-0_27"},{"key":"2394_CR53","unstructured":"Kristan M, Leonardis A, Matas J, al F (2018) The sixth visual object tracking VOT2018 challenge results. In: Proceedings of the European conference on computer vision (ECCV), pp 3\u201353"},{"key":"2394_CR54","doi-asserted-by":"crossref","unstructured":"Kristan M, Berg A, Zheng L, al R (2019) The seventh visual object tracking VOT2019 challenge results. In: Proceedings of the IEEE international conference on computer vision (ICCV), pp 2206\u20132241","DOI":"10.1109\/ICCVW.2019.00276"},{"issue":"5","key":"2394_CR55","doi-asserted-by":"publisher","first-page":"1562","DOI":"10.1109\/TPAMI.2019.2957464","volume":"43","author":"L Huang","year":"2021","unstructured":"Huang L, Zhao X, Huang K (2021) Got-10k: a large high-diversity benchmark for generic object tracking in the wild. IEEE Trans Pattern Anal Mach Intell 43(5):1562\u20131577","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2394_CR56","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 (2019) Lasot: a high-quality benchmark for large-scale single object tracking. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 5374\u20135383","DOI":"10.1109\/CVPR.2019.00552"},{"issue":"3","key":"2394_CR57","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein MS, Berg AC, Fei-Fei L (2015) Imagenet large scale visual recognition challenge. Int J Comput Vis 115(3):211\u2013252","journal-title":"Int J Comput Vis"},{"key":"2394_CR58","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Maire M, Belongie SJ, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick CL (2014) Microsoft COCO: common objects in context. In: Proceedings of the European conference on computer vision (ECCV), pp 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2394_CR59","doi-asserted-by":"crossref","unstructured":"Real E, Shlens J, Mazzocchi S, Pan X, Vanhoucke V (2017) Youtube-BoundingBoxes: a large high-precision human-annotated data set for object detection in video. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 7464\u20137473","DOI":"10.1109\/CVPR.2017.789"},{"key":"2394_CR60","unstructured":"Li X, Wang W, Wu L, Chen S, Hu X, Li J, Tang J, Yang J (2020) Generalized focal loss: learning qualified and distributed bounding boxes for dense object detection. In: Proceedings of the conference on neural information processing systems (NeurIPS), pp 21002\u201321012"},{"key":"2394_CR61","doi-asserted-by":"crossref","unstructured":"Li X, Wang W, Hu X, Li J, Tang J, Yang J (2021) Generalized focal loss V2: learning reliable localization quality estimation for dense object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 11632\u201311641","DOI":"10.1109\/CVPR46437.2021.01146"},{"key":"2394_CR62","doi-asserted-by":"crossref","unstructured":"Yu J, Jiang Y, Wang Z, Cao Z, Huang TS (2016) Unitbox: an advanced object detection network. In: ACM international conference on multimedia (MM), pp 516\u2013520","DOI":"10.1145\/2964284.2967274"},{"key":"2394_CR63","doi-asserted-by":"crossref","unstructured":"Zhang Z, Peng H, Fu J, Li B, Hu W (2020) Ocean: object-aware anchor-free tracking. In: Proceedings of the European conference on computer vision (ECCV), pp 771\u2013787","DOI":"10.1007\/978-3-030-58589-1_46"},{"issue":"2","key":"2394_CR64","doi-asserted-by":"publisher","first-page":"550","DOI":"10.1007\/s11263-021-01559-4","volume":"130","author":"Y Cui","year":"2022","unstructured":"Cui Y, Guo D, Shao Y, Wang Z, Shen C, Zhang L, Chen S (2022) Joint classification and regression for visual tracking with fully convolutional siamese networks. Int J Comput Vis 130(2):550\u2013566","journal-title":"Int J Comput Vis"},{"key":"2394_CR65","doi-asserted-by":"crossref","unstructured":"Danelljan M, Bhat G, Khan FS, Felsberg M (2019) Atom: accurate tracking by overlap maximization. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 4660\u20134669","DOI":"10.1109\/CVPR.2019.00479"},{"issue":"11","key":"2394_CR66","doi-asserted-by":"publisher","first-page":"5596","DOI":"10.1109\/TIP.2019.2919201","volume":"28","author":"T Xu","year":"2019","unstructured":"Xu T, Feng Z-H, Wu X-J, Kittler J (2019) Learning adaptive discriminative correlation filters via temporal consistency preserving spatial feature selection for robust visual object tracking. IEEE Trans Image Process 28(11):5596\u20135609","journal-title":"IEEE Trans Image Process"},{"key":"2394_CR67","doi-asserted-by":"crossref","unstructured":"Bai S, He Z, Dong Y, Bai H (2020) Multi-hierarchical independent correlation filters for visual tracking. In: IEEE international conference on multimedia and expo (ICME), pp 1\u20136","DOI":"10.1109\/ICME46284.2020.9102759"},{"key":"2394_CR68","doi-asserted-by":"crossref","unstructured":"Wang G, Luo C, Xiong Z, Zeng W (2019) Spm-tracker: series-parallel matching for real-time visual object tracking. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 3643\u20133652","DOI":"10.1109\/CVPR.2019.00376"},{"key":"2394_CR69","unstructured":"Zhao M, Okada K, Inaba M (2021) Trtr: visual tracking with transformer. arXiv:abs\/2105.03817"},{"issue":"3","key":"2394_CR70","first-page":"3072","volume":"45","author":"W Hu","year":"2023","unstructured":"Hu W, Wang Q, Zhang L, Bertinetto L, Torr PHS (2023) Siammask: a framework for fast online object tracking and segmentation. IEEE Trans Pattern Anal Mach Intell 45(3):3072\u20133089","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2394_CR71","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 (CVPR), pp 4591\u20134600","DOI":"10.1109\/CVPR.2019.00472"},{"key":"2394_CR72","doi-asserted-by":"crossref","unstructured":"Bhat G, Danelljan M, Gool LV, Timofte R (2019) Learning discriminative model prediction for tracking. In: Proceedings of the IEEE international conference on computer vision (ICCV), pp 6181\u20136190","DOI":"10.1109\/ICCV.2019.00628"},{"key":"2394_CR73","doi-asserted-by":"crossref","unstructured":"Su H, Jampani V, Sun D, Gallo O, Learned-Miller EG, Kautz J (2019) Pixel-adaptive convolutional neural networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 11166\u201311175","DOI":"10.1109\/CVPR.2019.01142"},{"key":"2394_CR74","doi-asserted-by":"crossref","unstructured":"Danelljan M, Bhat G, Khan FS, Felsberg M (2017) Eco: efficient convolution operators for tracking. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 6931\u20136939","DOI":"10.1109\/CVPR.2017.733"},{"key":"2394_CR75","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 103\u2013119","DOI":"10.1007\/978-3-030-01240-3_7"},{"key":"2394_CR76","doi-asserted-by":"crossref","unstructured":"Fan H, Ling H (2019) Siamese cascaded region proposal networks for real-time visual tracking. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 7952\u20137961","DOI":"10.1109\/CVPR.2019.00814"},{"key":"2394_CR77","doi-asserted-by":"crossref","unstructured":"Liu X, Peng H, Zheng N, Yang Y, Hu H, Yuan Y (2023) Efficientvit: memory efficient vision transformer with cascaded group attention. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 14420\u201314430","DOI":"10.1109\/CVPR52729.2023.01386"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-024-02394-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13042-024-02394-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-024-02394-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,13]],"date-time":"2025-12-13T09:40:42Z","timestamp":1765618842000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13042-024-02394-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"references-count":77,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["2394"],"URL":"https:\/\/doi.org\/10.1007\/s13042-024-02394-y","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"type":"print","value":"1868-8071"},{"type":"electronic","value":"1868-808X"}],"subject":[],"published":{"date-parts":[[2024,9,30]]},"assertion":[{"value":"6 June 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 September 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 September 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}