{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T03:05:01Z","timestamp":1740107101045,"version":"3.37.3"},"reference-count":107,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2023,12,29]],"date-time":"2023-12-29T00:00:00Z","timestamp":1703808000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,29]],"date-time":"2023-12-29T00:00:00Z","timestamp":1703808000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100014718","name":"Innovative Research Group Project of the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072042"],"award-info":[{"award-number":["62072042"]}],"id":[{"id":"10.13039\/100014718","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012165","name":"Key Technologies Research and Development Program","doi-asserted-by":"publisher","award":["2020YFC0832502"],"award-info":[{"award-number":["2020YFC0832502"]}],"id":[{"id":"10.13039\/501100012165","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1007\/s00371-023-03182-5","type":"journal-article","created":{"date-parts":[[2023,12,29]],"date-time":"2023-12-29T10:02:46Z","timestamp":1703844166000},"page":"6547-6566","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Customizing the feature modulation for visual tracking"],"prefix":"10.1007","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9105-6621","authenticated-orcid":false,"given":"Yuping","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zepeng","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiahao","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fusheng","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,12,29]]},"reference":[{"key":"3182_CR1","doi-asserted-by":"publisher","first-page":"993","DOI":"10.1007\/s00371-020-01848-y","volume":"37","author":"MY Abbass","year":"2021","unstructured":"Abbass, M.Y., Kwon, K.-C., Kim, N., Abdelwahab, S.A., El-Samie, F.E.A., Khalaf, A.A.: A survey on online learning for visual tracking. Vis. Comput. 37, 993\u20131014 (2021)","journal-title":"Vis. Comput."},{"key":"3182_CR2","doi-asserted-by":"publisher","first-page":"831","DOI":"10.1007\/s00371-020-01833-5","volume":"37","author":"MY Abbass","year":"2021","unstructured":"Abbass, M.Y., Kwon, K.-C., Kim, N., Abdelwahab, S.A., El-Samie, F.E.A., Khalaf, A.A.: Efficient object tracking using hierarchical convolutional features model and correlation filters. Vis. Comput. 37, 831\u2013842 (2021)","journal-title":"Vis. Comput."},{"key":"3182_CR3","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1016\/j.cviu.2018.05.009","volume":"171","author":"J Choi","year":"2018","unstructured":"Choi, J., Kwon, J., Lee, K.M.: Real-time visual tracking by deep reinforced decision making. Comput. Vis. Image Underst. 171, 10\u201319 (2018)","journal-title":"Comput. Vis. Image Underst."},{"key":"3182_CR4","doi-asserted-by":"publisher","first-page":"103508","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.: Visual object tracking: a survey. Comput. Vis. Image Underst. 222, 103508 (2022)","journal-title":"Comput. Vis. Image Underst."},{"key":"3182_CR5","doi-asserted-by":"publisher","first-page":"102951","DOI":"10.1016\/j.cviu.2020.102951","volume":"195","author":"J Qiu","year":"2020","unstructured":"Qiu, J., Wang, L., Hu, Y.H., Wang, Y.: Two motion models for improving video object tracking performance. Comput. Vis. Image Underst. 195, 102951 (2020)","journal-title":"Comput. Vis. Image Underst."},{"key":"3182_CR6","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: Proceedings of the European Conference on Computer Vision, pp. 850\u2013865. Springer (2016)","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"3182_CR7","doi-asserted-by":"crossref","unstructured":"Valmadre, J., Bertinetto, L., Henriques, J., Vedaldi, A., Torr, P.H.: End-to-end representation learning for correlation filter based tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2805\u20132813 (2017)","DOI":"10.1109\/CVPR.2017.531"},{"issue":"5","key":"3182_CR8","doi-asserted-by":"publisher","first-page":"3943","DOI":"10.1109\/TITS.2020.3046478","volume":"23","author":"SM Marvasti-Zadeh","year":"2021","unstructured":"Marvasti-Zadeh, S.M., Cheng, L., Ghanei-Yakhdan, H., Kasaei, S.: Deep learning for visual tracking: a comprehensive survey. IEEE Trans. Intell. Transp. Syst. 23(5), 3943\u20133968 (2021)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"8","key":"3182_CR9","doi-asserted-by":"publisher","first-page":"1858","DOI":"10.3390\/s19081858","volume":"19","author":"S Chang","year":"2019","unstructured":"Chang, S., Li, W., Zhang, Y., Feng, Z.: Online siamese network for visual object tracking. Sensors 19(8), 1858 (2019)","journal-title":"Sensors"},{"key":"3182_CR10","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":"3182_CR11","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 Conference on Computer Vision and Pattern Recognition, pp. 4277\u20134286 (2019)","DOI":"10.1109\/CVPR.2019.00441"},{"key":"3182_CR12","doi-asserted-by":"crossref","unstructured":"Chen, Z., Zhong, B., Li, G., Zhang, S., Ji, R.: Siamese box adaptive network for visual tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6668\u20136677 (2020)","DOI":"10.1109\/CVPR42600.2020.00670"},{"key":"3182_CR13","doi-asserted-by":"crossref","unstructured":"Wang, Q., Teng, Z., Xing, J., Gao, J., Hu, W., Maybank, S.: Learning attentions: residual attentional siamese network for high performance online visual tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4854\u20134863 (2018)","DOI":"10.1109\/CVPR.2018.00510"},{"key":"3182_CR14","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Wang, Q., Li, B., Wu, W., Yan, J., Hu, W.: Distractor-aware siamese networks for visual object tracking. In: Proceedings of the European Conference on Computer Vision, pp. 101\u2013117 (2018)","DOI":"10.1007\/978-3-030-01240-3_7"},{"key":"3182_CR15","doi-asserted-by":"crossref","unstructured":"Gao, J., Zhang, T., Xu, C.: Graph convolutional tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4644\u20134654 (2019)","DOI":"10.1109\/CVPR.2019.00478"},{"key":"3182_CR16","doi-asserted-by":"crossref","unstructured":"Bao, J., Chen, K., Sun, X., Zhao, L., Diao, W., Yan, M.: Siamthn: siamese target highlight network for visual tracking. ArXiv:2303.12304 (2023)","DOI":"10.1109\/TCSVT.2023.3266485"},{"key":"3182_CR17","doi-asserted-by":"crossref","unstructured":"Cui, Y., Cheng, J., Wang, L., Wu, G.: Mixformer: end-to-end tracking with iterative mixed attention. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13598\u201313608 (2022)","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"3182_CR18","first-page":"3072","volume":"45","author":"W Hu","year":"2022","unstructured":"Hu, W., Wang, Q., Zhang, L., Bertinetto, L., Torr, P.H.S.: Siammask: a framework for fast online object tracking and segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 45, 3072\u20133089 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3182_CR19","doi-asserted-by":"publisher","first-page":"1541","DOI":"10.1109\/TIP.2023.3246800","volume":"32","author":"T Xu","year":"2023","unstructured":"Xu, T., Feng, Z., Wu, X., Kittler, J.: Toward robust visual object tracking with independent target-agnostic detection and effective siamese cross-task interaction. IEEE Trans. Image Process. 32, 1541\u20131554 (2023)","journal-title":"IEEE Trans. Image Process."},{"key":"3182_CR20","doi-asserted-by":"publisher","first-page":"4251","DOI":"10.1007\/s40747-022-00712-x","volume":"8","author":"H Zhang","year":"2022","unstructured":"Zhang, H., Li, H.: Interactive Spatio-temporal feature learning network for video foreground detection. Complex Intell. Syst. 8, 4251\u20134263 (2022)","journal-title":"Complex Intell. Syst."},{"key":"3182_CR21","doi-asserted-by":"crossref","unstructured":"Wang, N., Shi, J., Yeung, D.-Y., Jia, J.: Understanding and diagnosing visual tracking systems. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3101\u20133109 (2015)","DOI":"10.1109\/ICCV.2015.355"},{"key":"3182_CR22","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Peng, H., Fu, J., Li, B., Hu, W.: Ocean: object-aware anchor-free tracking. In: Proceedings of the European Conference on Computer Vision, pp. 771\u2013787. Springer (2020)","DOI":"10.1007\/978-3-030-58589-1_46"},{"key":"3182_CR23","doi-asserted-by":"crossref","unstructured":"Guo, D., Wang, J., Cui, Y., Wang, Z., Chen, S.: Siamcar: siamese fully convolutional classification and regression for visual tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00630"},{"key":"3182_CR24","doi-asserted-by":"crossref","unstructured":"Huang, L., Zhao, X., Huang, K.: Globaltrack: a simple and strong baseline for long-term tracking. In: Proceedings of the Association for the Advancement of Artificial Intelligence, vol. 34, pp. 11037\u201311044 (2020)","DOI":"10.1609\/aaai.v34i07.6758"},{"key":"3182_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Peng, H.: Deeper and wider siamese networks for real-time visual tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4591\u20134600 (2019)","DOI":"10.1109\/CVPR.2019.00472"},{"key":"3182_CR26","doi-asserted-by":"crossref","unstructured":"Fan, H., Ling, H.: Siamese cascaded region proposal networks for real-time visual tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7952\u20137961 (2019)","DOI":"10.1109\/CVPR.2019.00814"},{"key":"3182_CR27","doi-asserted-by":"crossref","unstructured":"Cao, Z., Fu, C., Ye, J., Li, B., Li, Y.: Hift: hierarchical feature transformer for aerial tracking. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 15457\u201315466 (2021)","DOI":"10.1109\/ICCV48922.2021.01517"},{"key":"3182_CR28","doi-asserted-by":"crossref","unstructured":"He, A., Luo, C., Tian, X., Zeng, W.: A twofold siamese network for real-time object tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4834\u20134843 (2018)","DOI":"10.1109\/CVPR.2018.00508"},{"key":"3182_CR29","doi-asserted-by":"crossref","unstructured":"Guo, Q., Feng, W., Zhou, C., Huang, R., Wan, L., Wang, S.: Learning dynamic siamese network for visual object tracking. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1763\u20131771 (2017)","DOI":"10.1109\/ICCV.2017.196"},{"key":"3182_CR30","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 International Conference on Computer Vision, pp. 10448\u201310457 (2021)","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"3182_CR31","doi-asserted-by":"crossref","unstructured":"Cao, Z., Huang, Z., Pan, L., Zhang, S., Liu, Z., Fu, C.: Tctrack: temporal contexts for aerial tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01438"},{"key":"3182_CR32","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":"3182_CR33","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 Conference on Computer Vision and Pattern Recognition, pp. 13774\u201313783 (2021)","DOI":"10.1109\/CVPR46437.2021.01356"},{"key":"3182_CR34","doi-asserted-by":"crossref","unstructured":"Ye, J., Fu, C., Zheng, G., Paudel, D.P., Chen, G.: Unsupervised domain adaptation for nighttime aerial tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8896\u20138905 (2022)","DOI":"10.1109\/CVPR52688.2022.00869"},{"key":"3182_CR35","doi-asserted-by":"crossref","unstructured":"Xing, D., Evangeliou, N., Tsoukalas, A., Tzes, A.: Siamese transformer pyramid networks for real-time UAV tracking. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 2139\u20132148 (2022)","DOI":"10.1109\/WACV51458.2022.00196"},{"key":"3182_CR36","doi-asserted-by":"publisher","unstructured":"Wang, H., Schmid, C.: Action recognition with improved trajectories. In: 2013 IEEE International Conference on Computer Vision, pp. 3551\u20133558 (2013). https:\/\/doi.org\/10.1109\/ICCV.2013.441","DOI":"10.1109\/ICCV.2013.441"},{"key":"3182_CR37","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1109\/TIP.2019.2925285","volume":"29","author":"L Wang","year":"2020","unstructured":"Wang, L., Huynh, D.Q., Koniusz, P.: A comparative review of recent kinect-based action recognition algorithms. IEEE Trans. Image Process. 29, 15\u201328 (2020). https:\/\/doi.org\/10.1109\/TIP.2019.2925285","journal-title":"IEEE Trans. Image Process."},{"key":"3182_CR38","doi-asserted-by":"publisher","unstructured":"Wang, L., Koniusz, P., Huynh, D.: Hallucinating IDT descriptors and i3d optical flow features for action recognition with cnns. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 8697\u20138707 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00879","DOI":"10.1109\/ICCV.2019.00879"},{"key":"3182_CR39","doi-asserted-by":"crossref","unstructured":"Tang, Y., Ma, L., Zhou, L.: Hallucinating optical flow features for video classification. In: International Joint Conference on Artificial Intelligence (2019). https:\/\/api.semanticscholar.org\/CorpusID:167217361","DOI":"10.24963\/ijcai.2019\/130"},{"key":"3182_CR40","doi-asserted-by":"crossref","unstructured":"Wang, L., Koniusz, P.: Self-supervising action recognition by statistical moment and subspace descriptors. In Proceedings of the 29th ACM International Conference on Multimedia (2020)","DOI":"10.1145\/3474085.3475572"},{"key":"3182_CR41","doi-asserted-by":"crossref","unstructured":"Liao, B., Wang, C., Wang, Y., Wang, Y., Yin, J.: Pg-net: pixel to global matching network for visual tracking. In: Proceedings of the European Conference on Computer Vision, pp. 429\u2013444. Springer (2020)","DOI":"10.1007\/978-3-030-58542-6_26"},{"key":"3182_CR42","doi-asserted-by":"crossref","unstructured":"Han, W., Dong, X., Khan, F.S., Shao, L., Shen, J.: Learning to fuse asymmetric feature maps in siamese trackers. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 16570\u201316580 (2021)","DOI":"10.1109\/CVPR46437.2021.01630"},{"key":"3182_CR43","doi-asserted-by":"crossref","unstructured":"Yan, B., Zhang, X., Wang, D., Lu, H., Yang, X.: Alpha-refine: boosting tracking performance by precise bounding box estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5285\u20135294 (2021)","DOI":"10.1109\/CVPR46437.2021.00525"},{"key":"3182_CR44","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":"3182_CR45","doi-asserted-by":"crossref","unstructured":"Song, Z., Yu, J., Chen, Y.-P.P., Yang, W.: Transformer tracking with cyclic shifting window attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8791\u20138800 (2022)","DOI":"10.1109\/CVPR52688.2022.00859"},{"key":"3182_CR46","doi-asserted-by":"crossref","unstructured":"Wang, Q., Zhang, L., Bertinetto, L., Hu, W., Torr, P.H.: Fast online object tracking and segmentation: a unifying approach. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1328\u20131338 (2019)","DOI":"10.1109\/CVPR.2019.00142"},{"key":"3182_CR47","doi-asserted-by":"crossref","unstructured":"Tang, F., Ling, Q.: Ranking-based siamese visual tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8741\u20138750 (2022)","DOI":"10.1109\/CVPR52688.2022.00854"},{"key":"3182_CR48","doi-asserted-by":"crossref","unstructured":"Cheng, S., Zhong, B., Li, G., Liu, X., Tang, Z., Li, X., Wang, J.: Learning to filter: siamese relation network for robust tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4419\u20134429 (2021)","DOI":"10.1109\/CVPR46437.2021.00440"},{"key":"3182_CR49","doi-asserted-by":"crossref","unstructured":"Bhat, G., Danelljan, M., Gool, L.V., Timofte, R.: Learning discriminative model prediction for tracking. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6182\u20136191 (2019)","DOI":"10.1109\/ICCV.2019.00628"},{"key":"3182_CR50","doi-asserted-by":"crossref","unstructured":"Mayer, C., Danelljan, M., Bhat, G., Paul, M., Paudel, D.P., Yu, F., Van\u00a0Gool, L.: Transforming model prediction for tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8731\u20138740 (2022)","DOI":"10.1109\/CVPR52688.2022.00853"},{"key":"3182_CR51","doi-asserted-by":"crossref","unstructured":"Blatter, P., Kanakis, M., Danelljan, M., Van\u00a0Gool, L.: Efficient visual tracking with exemplar transformers. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 1571\u20131581 (2023)","DOI":"10.1109\/WACV56688.2023.00162"},{"key":"3182_CR52","doi-asserted-by":"crossref","unstructured":"Lukezic, A., Matas, J., Kristan, M.: D3s: a discriminative single shot segmentation tracker. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7133\u20137142 (2020)","DOI":"10.1109\/CVPR42600.2020.00716"},{"key":"3182_CR53","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: Cbam: convolutional block attention module. In: Proceedings of the European Conference on Computer Vision, pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"3182_CR54","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"3182_CR55","doi-asserted-by":"crossref","unstructured":"Roy, A.G., Navab, N., Wachinger, C.: Concurrent spatial and channel \u2018squeeze & excitation\u2019in fully convolutional networks. In: Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2018: 21st International Conference, Granada, Spain, September 16\u201320, 2018, Proceedings, Part I, pp. 421\u2013429. Springer (2018)","DOI":"10.1007\/978-3-030-00928-1_48"},{"key":"3182_CR56","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"3182_CR57","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"3182_CR58","unstructured":"Vaswani, A., Shazeer, N.M., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I.: Attention is all you need. In: Neural Information Processing Systems (2017). https:\/\/api.semanticscholar.org\/CorpusID:13756489"},{"key":"3182_CR59","doi-asserted-by":"publisher","unstructured":"Wang, L., Koniusz, P.: 3mformer: Multi-order multi-mode transformer for skeletal action recognition. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5620\u20135631 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.00544","DOI":"10.1109\/CVPR52729.2023.00544"},{"key":"3182_CR60","doi-asserted-by":"crossref","unstructured":"Das, S., Dai, R., Koperski, M., Minciullo, L., Garattoni, L., Bremond, F., Francesca, G.: Toyota smarthome: real-world activities of daily living. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 833\u2013842 (2019)","DOI":"10.1109\/ICCV.2019.00092"},{"key":"3182_CR61","doi-asserted-by":"crossref","unstructured":"Das, S., Chaudhary, A., Bremond, F., Thonnat, M.: Where to focus on for human action recognition? In: 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 71\u201380. IEEE (2019)","DOI":"10.1109\/WACV.2019.00015"},{"key":"3182_CR62","first-page":"1192","volume":"34","author":"L Ke","year":"2021","unstructured":"Ke, L., Li, X., Danelljan, M., Tai, Y.-W., Tang, C.-K., Yu, F.: Prototypical cross-attention networks for multiple object tracking and segmentation. Adv. Neural Inf. Process. Syst. 34, 1192\u20131203 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"3182_CR63","doi-asserted-by":"crossref","unstructured":"Yu, Y., Xiong, Y., Huang, W., Scott, M.R.: Deformable siamese attention networks for visual object tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6728\u20136737 (2020)","DOI":"10.1109\/CVPR42600.2020.00676"},{"issue":"11","key":"3182_CR64","doi-asserted-by":"publisher","first-page":"1254","DOI":"10.1109\/34.730558","volume":"20","author":"L Itti","year":"1998","unstructured":"Itti, L., Koch, C., Niebur, E.: A model of saliency-based visual attention for rapid scene analysis. IEEE Trans. Pattern Anal. Mach. Intell. 20(11), 1254\u20131259 (1998)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3182_CR65","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"702","DOI":"10.1007\/3-540-44868-3_89","volume-title":"Computational Methods in Neural Modeling","author":"N Ouerhani","year":"2003","unstructured":"Ouerhani, N., H\u00fcgli, H.: A model of dynamic visual attention for object tracking in natural image sequences. In: Computational Methods in Neural Modeling. Lecture Notes in Computer Science, vol. 2686, pp. 702\u2013709. Springer, New York (2003)"},{"key":"3182_CR66","doi-asserted-by":"crossref","unstructured":"Yang, M., Yuan, J., Wu, Y.: Spatial selection for attentional visual tracking. In: 2007 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20138 (2007)","DOI":"10.1109\/CVPR.2007.383178"},{"key":"3182_CR67","doi-asserted-by":"crossref","unstructured":"Fan, J., Wu, Y., Dai, S.: Discriminative spatial attention for robust tracking. In: Computer Vision\u2013ECCV 2010: 11th European Conference on Computer Vision, Heraklion, Crete, Greece, September 5-11, 2010, Proceedings, Part I 11, pp. 480\u2013493. Springer (2010)","DOI":"10.1007\/978-3-642-15549-9_35"},{"key":"3182_CR68","doi-asserted-by":"crossref","unstructured":"Choi, J., Jin\u00a0Chang, H., Yun, S., Fischer, T., Demiris, Y., Young\u00a0Choi, J.: Attentional correlation filter network for adaptive visual tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4807\u20134816 (2017)","DOI":"10.1109\/CVPR.2017.513"},{"key":"3182_CR69","doi-asserted-by":"crossref","unstructured":"Lukezic, A., Vojir, T., \u010cehovin\u00a0Zajc, L., Matas, J., Kristan, M.: Discriminative correlation filter with channel and spatial reliability. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6309\u20136318 (2017)","DOI":"10.1109\/CVPR.2017.515"},{"key":"3182_CR70","doi-asserted-by":"crossref","unstructured":"Cui, Z., Xiao, S., Feng, J., Yan, S.: Recurrently target-attending tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1449\u20131458 (2016)","DOI":"10.1109\/CVPR.2016.161"},{"key":"3182_CR71","doi-asserted-by":"crossref","unstructured":"Guo, D., Shao, Y., Cui, Y., Wang, Z., Zhang, L., Shen, C.: Graph attention tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9543\u20139552 (2021)","DOI":"10.1109\/CVPR46437.2021.00942"},{"key":"3182_CR72","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":"3182_CR73","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"3","key":"3182_CR74","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, M.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vis."},{"key":"3182_CR75","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: Proceedings of the European Conference on Computer Vision, pp. 740\u2013755. Springer (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"issue":"5","key":"3182_CR76","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.: Got-10k: a large high-diversity benchmark for generic object tracking in the wild. IEEE Trans. Pattern Anal. Mach. Intell. 43(5), 1562\u20131577 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3182_CR77","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 Conference on Computer Vision and Pattern Recognition, pp. 5374\u20135383 (2019)","DOI":"10.1109\/CVPR.2019.00552"},{"key":"3182_CR78","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":"3182_CR79","doi-asserted-by":"crossref","unstructured":"Song, Y., Ma, C., Wu, X., Gong, L., Bao, L., Zuo, W., Shen, C., Lau, R.W., Yang, M.-H.: Vital: visual tracking via adversarial learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8990\u20138999 (2018)","DOI":"10.1109\/CVPR.2018.00937"},{"key":"3182_CR80","doi-asserted-by":"crossref","unstructured":"Nam, H., Han, B.: Learning multi-domain convolutional neural networks for visual tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4293\u20134302 (2016)","DOI":"10.1109\/CVPR.2016.465"},{"key":"3182_CR81","doi-asserted-by":"crossref","unstructured":"Li, P., Chen, B., Ouyang, W., Wang, D., Yang, X., Lu, H.: Gradnet: gradient-guided network for visual object tracking. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 6161\u20136170 (2019)","DOI":"10.1109\/ICCV.2019.00626"},{"key":"3182_CR82","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Bhat, G., Khan, F.S., Felsberg, M.: Atom: accurate tracking by overlap maximization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4655\u20134664 (2019)","DOI":"10.1109\/CVPR.2019.00479"},{"key":"3182_CR83","doi-asserted-by":"crossref","unstructured":"Dong, X., Shen, J., Shao, L., Porikli, F.: Clnet: A compact latent network for fast adjusting siamese trackers. In: European Conference on Computer Vision, pp. 378\u2013395. Springer (2020)","DOI":"10.1007\/978-3-030-58565-5_23"},{"key":"3182_CR84","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: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14572\u201314581 (2023)","DOI":"10.1109\/CVPR52729.2023.01400"},{"issue":"12","key":"3182_CR85","doi-asserted-by":"publisher","first-page":"5630","DOI":"10.1109\/TIP.2015.2482905","volume":"24","author":"P Liang","year":"2015","unstructured":"Liang, P., Blasch, E., Ling, H.: Encoding color information for visual tracking: algorithms and benchmark. IEEE Trans. Image Process. 24(12), 5630\u20135644 (2015)","journal-title":"IEEE Trans. Image Process."},{"key":"3182_CR86","doi-asserted-by":"crossref","unstructured":"Zhang, J., Ma, S., Sclaroff, S.: Meem: robust tracking via multiple experts using entropy minimization. In: Proceedings of the European Conference on Computer Vision (2014)","DOI":"10.1007\/978-3-319-10599-4_13"},{"key":"3182_CR87","doi-asserted-by":"crossref","unstructured":"Wang, L., Ouyang, W., Wang, X., Lu, H.: Visual tracking with fully convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3119\u20133127 (2015)","DOI":"10.1109\/ICCV.2015.357"},{"key":"3182_CR88","doi-asserted-by":"crossref","unstructured":"Chen, B., Wang, D., Li, P., Wang, S., Lu, H.: Real-time \u2018actor-critic\u2019 tracking. In: Proceedings of the European Conference on Computer Vision, pp. 318\u2013334 (2018)","DOI":"10.1007\/978-3-030-01234-2_20"},{"key":"3182_CR89","doi-asserted-by":"crossref","unstructured":"Fan, H., Ling, H.: Parallel tracking and verifying: a framework for real-time and high accuracy visual tracking. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5487\u20135495 (2017)","DOI":"10.1109\/ICCV.2017.585"},{"key":"3182_CR90","doi-asserted-by":"crossref","unstructured":"Li, S., Yeung, D.-Y.: Visual object tracking for unmanned aerial vehicles: a benchmark and new motion models. In: Proceedings of the Association for the Advancement of Artificial Intelligence (2017)","DOI":"10.1609\/aaai.v31i1.11205"},{"key":"3182_CR91","doi-asserted-by":"crossref","unstructured":"Li, X., Ma, C., Wu, B., He, Z., Yang, M.-H.: Target-aware deep tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1369\u20131378 (2019)","DOI":"10.1109\/CVPR.2019.00146"},{"issue":"2","key":"3182_CR92","doi-asserted-by":"publisher","first-page":"674","DOI":"10.1109\/TCSVT.2021.3063001","volume":"32","author":"Y Cao","year":"2021","unstructured":"Cao, Y., Ji, H., Zhang, W., Shirani, S.: Feature aggregation networks based on dual attention capsules for visual object tracking. IEEE Trans. Circuits Syst. Video Technol. 32(2), 674\u2013689 (2021)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"3182_CR93","unstructured":"Fu, C., Jin, J., Ding, F., Li, Y., Lu, G.: Spatial reliability enhanced correlation filter: an efficient approach for real-time uav tracking. IEEE Trans. Multimedia (2021)"},{"key":"3182_CR94","doi-asserted-by":"crossref","unstructured":"Li, Y., Fu, C., Ding, F., Huang, Z., Lu, G.: Autotrack: towards high-performance visual tracking for uav with automatic spatio-temporal regularization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 11923\u201311932 (2020)","DOI":"10.1109\/CVPR42600.2020.01194"},{"key":"3182_CR95","doi-asserted-by":"crossref","unstructured":"Wang, N., Zhou, W., Tian, Q., Hong, R., Wang, M., Li, H.: Multi-cue correlation filters for robust visual tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4844\u20134853 (2018)","DOI":"10.1109\/CVPR.2018.00509"},{"key":"3182_CR96","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Chen, Y., Jing, Y., Zhou, P., Zhang, Y.: Fratcf: feature-residue real-time UAV tracking based on automatic spatio-temporal regularization correlation filter. In: 2022 IEEE International Conference on Multimedia and Expo, pp. 1\u20136 (2022)","DOI":"10.1109\/ICME52920.2022.9859881"},{"key":"3182_CR97","doi-asserted-by":"crossref","unstructured":"Li, F., Tian, C., Zuo, W., Zhang, L., Yang, M.-H.: Learning spatial-temporal regularized correlation filters for visual tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4904\u20134913 (2018)","DOI":"10.1109\/CVPR.2018.00515"},{"key":"3182_CR98","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1109\/TMM.2021.3050073","volume":"24","author":"X-F Zhu","year":"2021","unstructured":"Zhu, X.-F., Wu, X.-J., Xu, T., Feng, Z.-H., Kittler, J.: Robust visual object tracking via adaptive attribute-aware discriminative correlation filters. IEEE Trans. Multimedia 24, 301\u2013312 (2021)","journal-title":"IEEE Trans. Multimedia"},{"key":"3182_CR99","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Robinson, A., Khan, F.S., Felsberg, M.: Beyond correlation filters: learning continuous convolution operators for visual tracking. In: Proceedings of the European Conference on Computer Vision, pp. 472\u2013488. Springer (2016)","DOI":"10.1007\/978-3-319-46454-1_29"},{"key":"3182_CR100","first-page":"1","volume":"60","author":"C Fu","year":"2021","unstructured":"Fu, C., Cao, Z., Li, Y., Ye, J., Feng, C.: Onboard real-time aerial tracking with efficient siamese anchor proposal network. IEEE Trans. Geosci. Remote Sens. 60, 1\u201313 (2021)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"3182_CR101","doi-asserted-by":"crossref","unstructured":"Cao, Z., Fu, C., Ye, J., Li, B., Li, Y.: Siamapn++: siamese attentional aggregation network for real-time uav tracking. In: 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3086\u20133092. IEEE (2021)","DOI":"10.1109\/IROS51168.2021.9636309"},{"key":"3182_CR102","doi-asserted-by":"crossref","unstructured":"Wang, X., Zeng, D., Zhao, Q., Li, S.: Rank-based filter pruning for real-time uav tracking. In: 2022 IEEE International Conference on Multimedia and Expo, pp. 01\u201306 (2022)","DOI":"10.1109\/ICME52920.2022.9859656"},{"key":"3182_CR103","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Hager, G., Shahbaz\u00a0Khan, F., Felsberg, M.: Convolutional features for correlation filter based visual tracking. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 58\u201366 (2015)","DOI":"10.1109\/ICCVW.2015.84"},{"key":"3182_CR104","doi-asserted-by":"crossref","unstructured":"Bertinetto, L., Valmadre, J., Golodetz, S., Miksik, O., Torr, P.H.: Staple: complementary learners for real-time tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1401\u20131409 (2016)","DOI":"10.1109\/CVPR.2016.156"},{"key":"3182_CR105","doi-asserted-by":"crossref","unstructured":"Dong, X., Shen, J.: Triplet loss in siamese network for object tracking. In: Proceedings of the European Conference on Computer Vision, pp. 459\u2013474 (2018)","DOI":"10.1007\/978-3-030-01261-8_28"},{"issue":"3","key":"3182_CR106","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1109\/TPAMI.2014.2345390","volume":"37","author":"JF Henriques","year":"2014","unstructured":"Henriques, J.F., Caseiro, R., Martins, P., Batista, J.: High-speed tracking with kernelized correlation filters. IEEE Trans. Pattern Anal. Mach. Intell. 37(3), 583\u2013596 (2014)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3182_CR107","doi-asserted-by":"crossref","unstructured":"Yang, T., Chan, A.B.: Learning dynamic memory networks for object tracking. In: Proceedings of the European Conference on Computer Vision, pp. 152\u2013167 (2018)","DOI":"10.1007\/978-3-030-01240-3_10"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-023-03182-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-023-03182-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-023-03182-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T15:25:03Z","timestamp":1723562703000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-023-03182-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,29]]},"references-count":107,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2024,9]]}},"alternative-id":["3182"],"URL":"https:\/\/doi.org\/10.1007\/s00371-023-03182-5","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"type":"print","value":"0178-2789"},{"type":"electronic","value":"1432-2315"}],"subject":[],"published":{"date-parts":[[2023,12,29]]},"assertion":[{"value":"10 November 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 December 2023","order":2,"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 that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}}]}}